JP2025049064A - system - Google Patents

Abstract

To provide a system.SOLUTION: A system includes means for generating a button for sending a message in a specific language, means for inputting an input message as a prompt sentence to a generative AI model when the button is pressed, means for the generative AI model to translate the input message, and means for sending the translated message to a transmission destination.SELECTED DRAWING: Figure 1

Description

The technology disclosed herein relates to a system.

Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description of the chatbot character and an associated instruction sentence, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

JP 2022-180282 A

Currently, when communicating with foreigners using messenger apps or social media, users must take the time to copy and paste messages that have been translated using external services. This poses the problem that communication across language barriers cannot be carried out smoothly.

To solve this problem, the present invention provides a system that creates a new "Send in XX language" button next to the message sending means in messenger apps and SNS, automatically translates the message into XX language when the button is pressed, and sends the translated message. This allows users to translate and send the message directly within the app at the same time without using an external service, further lowering the language barrier.

1 is a conceptual diagram showing an example of a configuration of a data processing system according to a first embodiment. 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. 11 is a conceptual diagram showing an example of a configuration of a data processing system according to a second embodiment. FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped. FIG. 11 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. FIG. 11 is a sequence diagram showing a process flow of the data processing system in application example 1 of embodiment 1. FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second form example. FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third embodiment of the third aspect. FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 3 of embodiment 3. FIG. 13 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example when an emotion engine is combined. FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in application example 1 of embodiment 1 when combined with an emotion engine. FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment of the second form example when an emotion engine is combined. FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in application example 2 of embodiment 2 when combined with an emotion engine. FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the third embodiment of the third form example when an emotion engine is combined. FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in application example 3 of embodiment 3 when combined with an emotion engine.

Below, an example of an embodiment of a system related to the technology disclosed herein is described with reference to the attached drawings.

First, let us explain the terminology used in the following explanation.

In the following embodiments, the coded processor (hereinafter simply referred to as the "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. The processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

In the following embodiments, a signed random access memory (RAM) is a memory in which information is temporarily stored and is used as a working memory by the processor.

In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

In the following embodiments, a communication I/F (Interface) with a code is an interface including a communication processor and an antenna, etc. The communication I/F controls communication between multiple computers. Examples of communication standards applied to the communication I/F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

In the following embodiments, "A and/or B" is synonymous with "at least one of A and B." In other words, "A and/or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same concept as "A and/or B" is also applied when three or more things are expressed by connecting them with "and/or."

[First embodiment]

Figure 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I/F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and/or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

As shown in FIG. 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. Data generation model 58 and emotion identification model 59 are used by the identification processing unit 290.

In the smart device 14, the reception output process is performed by the processor 46. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12.

"Example 1"

As one embodiment of the present invention, a "Send in English" button is placed next to the message input field on the message sending screen of a messenger app or SNS. When a user inputs a message and presses the "Send in English" button, the input message is automatically translated into English and the translated message is sent.

"Example 2"

Furthermore, we provide a function that automatically selects the language of the "Send in ____" button from the available languages based on the user's settings. For example, if the user frequently communicates with people who speak French, the "Send in French" button will be automatically generated based on the user's settings.

"Example 3"

The service also provides a function that selects the most appropriate translation based on the context of the message entered by the user. For example, if the user enters "I'm fine," this will be translated as "I'm fine." However, if the user enters "It's fine," this will be translated as "It's fine." In this way, the translation method for the same "fine" changes depending on the context.

The process flow for each example is explained below.

"Example 1"

Step 1: The user opens the message sending screen of a messenger app or SNS.

Step 2: Make sure the "Send in English" button is located next to the message input field.

Step 3: The user enters a message and presses the "Send in English" button.

Step 4: The system will automatically translate the message you entered into English.

Step 5: The system sends the translated message.

"Example 2"

Step 1: The user opens the settings screen of the messenger app or SNS.

Step 2: The user selects the language from the available options for the "Send in" button. Step 3: The user saves the settings and returns to the message sending screen.

Step 4: Make sure there is a "Send in XXX" button in the user's chosen language next to the message input field.

"Example 3"

Step 1: User enters message.

Step 2: The system selects the best translation based on the context of the message entered by the user.

Step 3: The system displays the selected translation to the user.

Step 4: The user presses the "Send in XXX language" button and the system sends the selected translation.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, the translation was often inaccurate and did not provide an appropriate translation based on the context, which could impair smooth communication. To solve these problems, a system was needed that would allow users to easily translate and send messages in a specific language.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in specific language" button generating means disposed next to the message sending means, a means for automatically translating the message into a specific language when the "Send in specific language" button is pressed, a means for sending the automatically translated message, a means for inputting the message into a generative AI model as a prompt sentence, a means for the generative AI model to translate the message, and a means for sending the translated message to a destination. This enables a user to easily translate and send a message into a specific language.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that is placed next to the message sending means and generates a button for sending a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

A "generative AI model" is an artificial intelligence model for performing natural language processing and capable of translating input text into other languages.

A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

"Means for sending translated messages" refers to a function for sending messages translated by the automatic translation means to a specified destination.

"Optimal translation based on context" refers to providing the most appropriate translation by taking into account the content and intent of the message entered by the user.

This invention is a system that allows users to easily translate and send messages into a specific language in messenger apps and SNS. A specific embodiment of this system is described below.

First, a user opens the message sending screen of a messenger app or SNS and enters a message in the message input field. For example, the user might enter "Hello, how are you?". Next, the user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in an appropriate format. The server inputs the received message into a generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, it sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

The generative AI model receives the prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" to "Hello, how are you?". The server sends the translated message received from the generative AI model to the device. At this time, the translated message is sent to the device in the appropriate format.

The device then sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend. In this way, a message entered by the user in Japanese is automatically translated into a specific language and sent.

As a concrete example, consider a case where a user wants to send a message to a friend saying "Hello, how are you?" The user enters "Hello, how are you?" in the message input field and presses the "Send in specific language" button. The system translates this message into "Hello, how are you?" and sends it to the friend.

Example of a prompt to input to a generative AI model:

"Please translate 'Hello, how are you?' into English."

This system allows users to easily translate and send messages into a specific language. The hardware used includes the user's device (smartphone, tablet, PC, etc.) and a server. The software used includes messenger apps, SNS applications, and generative AI models (e.g., GPT-4 (registered trademark)).

The flow of the identification process in Example 1 is explained using Figure 11.

Step 1:

The user enters a message in the message input field.

Enter: "Hello, how are you?"

Output: Input message "Hello, how are you?"

Specific actions: The user opens the message sending screen of a messenger app or SNS and types "Hello, how are you?" in the message input field.

Step 2:

The user presses the "Send in specific language" button.

Input: User presses the "Send in specific language" button

Output: Event that the send button was pressed

Specific behavior: The user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

Step 3:

The device sends the entered message to the server.

Input: An event that inputs the message "Hello, how are you?" and presses the send button

Output: Message sent to server: "Hello, how are you?"

Specific operation: The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in the appropriate format.

Step 4:

The server inputs the message into the generation AI model as a prompt.

Input: Message sent to server: "Hello, how are you?"

Output: Prompt sent to the generative AI model: "Please translate 'Hello, how are you?' into English."

Specific operation: The server inputs the received message into the generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, the server sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

Step 5:

A generative AI model translates the message into English.

Input: Prompt text: "Please translate 'Hello, how are you?' into English."

Output: The translated message "Hello, how are you?"

Specific behavior: The generative AI model receives a prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" into "Hello, how are you?".

Step 6:

The server sends the translated message to the device.

Input: translated message "Hello, how are you?"

Output: The translated message "Hello, how are you?" sent to the device.

Specific operation: The server sends the translated message received from the generative AI model to the terminal. At this time, the translated message is sent to the terminal in an appropriate format.

Step 7:

Your device will then send the translated message to the recipient.

Input: The translated message sent to the device: "Hello, how are you?"

Output: The message "Hello, how are you?" sent to the destination.

Specific operation: The device sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

With the current trend of globalization, communication with foreign customers has become important in brick-and-mortar stores. However, the language barrier makes it difficult for store staff to communicate smoothly with foreign customers. To solve this problem, real-time language translation is necessary, but current technology is not sufficient.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a voice input means, a means for converting voice acquired by the voice input means into text, a means for translating the text into XXX language, and a means for vocally outputting the translated text. This enables smooth real-time communication between store staff and foreign customers in physical stores.

"Message sending means" refers to an interface that allows a user to input and send text messages.

The "means for generating a send button in XX language" is a function that generates a button for translating and sending a message into a language selected by the user.

"Means for automatic translation" refers to a function for automatically translating an input text message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to the other party.

"Voice input means" is an interface for capturing the user's voice and acquiring it as digital data.

"Means for converting voice to text" refers to a function for converting acquired voice data into text data.

"Means of translating text into XX language" is a function for translating text data into a specified language.

"Means for outputting translated text as audio" refers to a function for playing back translated text as audio.

To implement this invention, the following system configuration and program are required.

First, the server provides a message sending means, which is an interface that allows the user to input and send a text message. Next, the server provides a "Send in XX language" button generating means, which is a function that generates a button for translating and sending a message into a language selected by the user.

When a user presses the "Send in XXX language" button, the server uses an automatic translation means to automatically translate the entered text message into the specified language. This translated message is then sent to the recipient by a means for sending an automatically translated message.

Furthermore, the server provides a voice input means, which is an interface for capturing the user's voice and acquiring it as digital data. The acquired voice data is converted into text data by a voice-to-text conversion means.

The converted text data is translated into a specified language by a means for translating text into a specific language. The translated text is played as audio by a means for outputting the translated text as audio.

To realize this system, the following hardware and software are used:

Hardware: Smart glasses (capable of voice input and output)

Software:

speech_recognition library: convert speech to text

googletrans library: translate text

pyttsx3 library: convert text to speech

As a concrete example, when a store clerk says, "Where is this product located?", the voice is captured by the microphone of the smart glasses. The voice data is converted to text using the speech_recognition library, and the text is translated into English using the googletrans library. The translated text is converted to speech using the pyttsx3 library, and "Where is this product located?" is played from the speaker of the smart glasses.

Example of a prompt to input to a generative AI model:

When a user says "Where is this product located?", convert that speech to text, translate it into English, display "Where is this product located?" and play it aloud.

The flow of the specific processing in application example 1 is explained using Figure 12.

Step 1:

The user speaks into the smart glasses. The microphone in the smart glasses captures the voice and obtains it as voice data. This voice data becomes the input.

Step 2:

The voice data acquired by the device (smart glasses) is converted into text data using the speech_recognition library. The voice data is analyzed and corresponding text data is generated. This text data becomes the output.

Step 3:

Translates text data generated by the device into a specified language (e.g. English) using the googletrans library. Takes text data as input and generates translated text data. This translated text data is the output.

Step 4:

The device converts the translated text data into speech data using the pyttsx3 library. It takes the translated text data as input and generates the corresponding speech data. This speech data becomes the output.

Step 5:

The device then plays the generated voice data through the smart glasses' speakers, allowing the user to listen to the translated audio.

Specifically, when a user says "Where is this product located?", the voice is captured by the microphone in the smart glasses. The voice data is converted into text data saying "Where is this product located?" using the speech_recognition library. The text data is translated into English as "Where is this product located?" using the googletrans library. The translated text data is converted into voice data using the pyttsx3 library, and "Where is this product located?" is played from the speaker in the smart glasses.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messaging apps and SNS, when users wanted to send a message in a different language, they had to translate it manually, which was a time-consuming process. In addition, there was no function to automatically select frequently used languages, so users had to select the language every time, which was inconvenient. Furthermore, the quality of the translation was not consistent, so the translation did not always match the context of the message.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a means for acquiring user setting information, a means for sending a prompt sentence to the generative AI model based on the acquired setting information, a means for generating a "Send in XXX language" button based on a response from the generative AI model, a means for displaying the generated "Send in XXX language" button in a user interface, and a means for sending a message when the user clicks the "Send in XXX language" button. This makes it possible to automatically select a language frequently used by the user and perform an appropriate translation.

"User settings information" refers to the individual language and other customization information that a user sets within the system.

A "generative AI model" is a model designed to perform specific tasks using artificial intelligence. In this case, its role is to generate prompts based on user settings and generate appropriate language selection buttons.

A "prompt sentence" refers to an input sentence that gives specific instructions or asks a question to a generative AI model.

"Send in XXX language button" refers to a button on the interface that allows a user to send a message in a specific language of their choice.

"User interface" refers to the screens and operating means that allow users to interact with the system.

"Means of sending messages" refers to the functionality for sending messages entered by the user in the selected language.

This invention relates to a system for messenger apps and SNS that automatically selects a language frequently used by a user and performs appropriate translation. A specific embodiment of this system is described below.

Server processing

The server retrieves the user's settings information from a database. Specifically, it uses a database management system such as MySQL (registered trademark) to retrieve information on the languages frequently used by the user. For example, it executes an SQL query that retrieves the corresponding language settings using the user ID as a key.

The server then sends a prompt to a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) based on the retrieved user settings. The prompt includes instructions to generate a "Send in XXX language" button based on the user's frequently used language.

Example of a prompt:

"Based on the user's preferences, select the frequently used language and generate a corresponding submit button. For example, if the user selects French, generate a 'Submit in French' button."

The server that receives the response from the generative AI model generates the data to display in the user interface. Specifically, it generates HTML and JavaScript (registered trademark) code and creates buttons that correspond to the language selected by the user.

Terminal processing

The terminal receives the data sent from the server and reflects it in the user interface. Specifically, it dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React.

User operations

The user selects the languages they use most frequently in the settings screen. For example, if the user selects French, a "Send in French" button will be automatically generated from next time. The user can click this button to send messages in the selected language.

Specific examples

For example, if a user selects "French" in the settings screen, the "Send in French" button will be automatically generated next time. When the user clicks this button, the message will be sent in French.

In this way, it is possible to automatically select the language that the user frequently uses and provide an appropriate translation. This saves the user the trouble of having to manually select the language, allowing for smoother communication.

The flow of the identification process in Example 2 is explained using Figure 13.

Step 1:

Get user settings information

The server retrieves the user's preference information from a database. As input, a user ID is given. The server uses a database management system such as MySQL (registered trademark) to retrieve information about the user's frequently used languages. Specifically, it executes an SQL query using the user ID as a key to retrieve the corresponding language preference. As output, the user's preference information (e.g., French) is obtained.

Step 2:

Generating and sending prompts

The server sends a prompt to the generative AI model based on the acquired user setting information. The user's setting information is given as input. The prompt includes an instruction to generate a "Send in XX language" button based on the language the user frequently uses. An example of a specific prompt is "Based on the user's settings, please select the language that is frequently used and generate a corresponding send button. For example, if the user selects French, please generate a 'Send in French' button." The output is a response from the generative AI model.

Step 3:

Generate language selection button

The server generates a "Send in XXX language" button based on the response from the generative AI model. The response from the generative AI model is given as input. The server generates HTML and JavaScript (registered trademark) code to create a button that corresponds to the language selected by the user. The output is the data for the generated "Send in XXX language" button.

Step 4:

Display language selection button

The terminal receives the data sent from the server and reflects it in the user interface. As input, it is given the data for the "Send in XX language" button sent from the server. The terminal dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React. As output, it obtains the button displayed in the user interface.

Step 5:

Send a message

The user clicks the generated "Send in French" button. As input, the user's click event is given. When the click event occurs, a message is sent in the selected language. Specifically, a JavaScript® event listener is used to catch the button click event and process the message sending. As output, the message sent in the selected language is obtained.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users communicate in different languages, they have to translate manually, which is inefficient. In addition, there was a lack of functionality to automatically learn frequently used languages and send messages in the appropriate language, which made it inconvenient for users.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means. In this invention, the server includes a message sending means, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a means for acquiring user setting information, a means for learning frequently used languages based on the setting information, a means for automatically generating the "Send in XXX language" button based on the learned languages, a means for translating the message in real time, and a means for sending the translated message. This makes it possible to automatically learn languages frequently used by the user and send messages in the appropriate language.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending translated messages to other users.

"Means for acquiring user setting information" refers to a function for acquiring the language and other setting information previously set by the user.

"Means for learning frequently used languages" refers to a function for learning the languages that a user frequently uses based on the user's past message history and settings information.

"Means of real-time translation" refers to a function that translates a message into a specified language in real time as the user types the message.

The system for implementing this invention is composed of a server and a user terminal. The server includes a message sending means, a "send in XX language" button generating means, an automatic translation means, a sending means, a means for acquiring user setting information, a means for learning frequently used languages, and a means for translating in real time.

Program processing explanation

Hardware to be used

Server: Any cloud server (e.g. AWS (registered trademark), Google (registered trademark) Cloud)

Client: Smartphone (iOS or ANDROID (registered trademark))

Software to be used

Framework: Flask (Python)

Translation API: Googletrans (Python wrapper for Google Translate API)

Data processing and data calculations

1. How to get user settings information:

The server retrieves the user's pre-selected language and other preferences. This information is used to learn the user's frequently used languages based on their past message history and preferences.

2. Ways to learn frequently used languages:

The server learns which languages the user frequently uses based on the user's past message history and preferences. This allows it to identify the language the user uses most often and automatically generate a button to send messages in that language.

3. How to generate the "Send in ____ language" button:

The server automatically generates a button to send a message in a specific language based on the user's preferences. This button is displayed when the user types a message.

4. Ways to translate in real time:

As users type their messages, the server translates them into the specified language in real time, allowing users to see the translated message instantly.

5. Automatic translation methods:

When a user presses the "Send in XXX language" button, the server automatically translates the message into the specified language. This translation is done using a translation API such as GoogleTrans.

6. Transmission method:

The translated messages are then sent to other users via the server, allowing users who speak different languages to communicate smoothly.

Specific examples

For example, if the user is "user1" and sends the message "Hello, how are you?", the server will translate this message into French and return it as "Bonjour, comment ça va?".

Example of a prompt

User ID: user1

Message: Hello, how are you?

When you send this prompt to the server, you will get a response like this:

{

"original_message": "Hello, how are you?",

"translated_message": "Bonjour, comment ça va?",

"language": "fr"

}

In this way, a system can be created that automatically selects a language based on the user's settings and then translates and sends the message.

The flow of the specific processing in application example 2 is explained using Figure 14.

Step 1:

The user inputs a message. The user inputs a text message using the smartphone's message sending means. This input message is sent to the server.

Step 2:

The server retrieves the user's preferences. The server retrieves the user's preferences from a database and identifies the user's frequently used languages. This preference information includes languages the user has used in the past and languages that have been preset by the user.

Step 3:

The server learns which languages are used most frequently. Based on the configuration information obtained, the server learns which languages are used most frequently by users. Based on the results of this learning, it generates a "Send in XXX" button for sending messages in a specific language.

Step 4:

The server generates a "Send in XX language" button. Based on the learning results, the server automatically generates a button for sending messages in the language the user frequently uses and displays it on the user's device.

Step 5:

The user presses the "Send in XXX" button. By pressing the generated "Send in XXX" button, the user instructs the message they typed to be translated into a specific language.

Step 6:

The server translates the message in real time. The server translates the message entered by the user into the specified language in real time. This translation uses a translation API such as Googletrans.

Step 7:

The server sends the translated message. The server returns the translated message to the user's device so that the user can review it. The server then sends the translated message to other users.

Step 8:

Other users receive the translated message. Other users receive and display the translated message sent from the server. This allows users who speak different languages to communicate smoothly.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messaging apps and SNS, it was difficult to provide appropriate translations based on the context when users sent messages. In particular, when the same word had different meanings depending on the context, it was difficult to select the appropriate translation.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a message sending means, a "send with translation" button generating means disposed next to the message sending means, a means for automatically translating the message when the "send with translation" button is pressed, a means for sending the automatically translated message, a means for receiving a message input by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to the user. This makes it possible to provide an optimal translation based on the context of the message input by the user.

"Message sending means" refers to a means for sending messages entered by a user to other users.

The "translation and send button generation means" is a means for generating a button that enables a user to translate and send a message.

"Means for automatic translation" refers to a means for automatically translating a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to means for sending translated messages to other users.

"Means for receiving messages entered by users" refers to the means by which the server receives messages entered by users.

"Means for inputting a message into a generative AI model" refers to means for inputting a received message into a generative AI model.

"Means by which a generative AI model generates a context-based translation" refers to the means by which a generative AI model analyzes the context of a message and generates an optimal translation.

"Means for receiving the generated translation results" refers to means for receiving the translation results generated from the generative AI model.

"Means for displaying the translation result to the user" refers to means for displaying the received translation result to the user.

This invention relates to a system that optimally translates a message entered by a user based on the context. This system includes a message sending means, a translation send button generating means, an automatic translation means, a means for sending the automatically translated message, a means for receiving a message entered by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to a user.

Hardware and software used

This system uses a server, a terminal, and a generative AI model. Specifically, the server receives messages, inputs them into the generative AI model, and receives and sends translation results. The terminal inputs messages from users and displays the translation results. For example, OpenAI's GPT-4 (registered trademark) is used as the generative AI model.

Data processing and data calculations

The server receives the message entered by the user on the device and inputs the message into the generative AI model. The generative AI model analyzes the context of the message and generates the optimal translation. The generated translation result is returned to the server, which then sends the result to the device. The device displays the translation result to the user.

Specific examples

As a concrete example, consider the case where a user types "I'm fine." In this case, the server uses a generative AI model to generate the translation "I'm fine." On the other hand, if the user types "It's fine.", the server generates the translation "It's fine."

Example of a prompt

"If the user types 'I'm fine.', translate this as 'I'm fine.'"

"If the user types 'It's fine.', translate this to 'That's fine.'"

In this way, the system can properly translate the user's input message based on the context. The flow of the specific process in Example 3 is explained with reference to FIG. 15.

Step 1:

The user enters a message. The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." This input message becomes the input data for the next processing step.

Step 2:

The terminal sends a message to the server. The terminal sends the message entered by the user to the server using an HTTP request. In this case, the input data is the message entered by the user, and the output data is the message sent to the server.

Step 3:

The server receives the message. The server receives the message sent from the terminal and temporarily stores it in memory. The input data is the message sent from the terminal, and the output data is the message stored on the server.

Step 4:

The server inputs messages into the generative AI model. The server calls an API to input the received messages into the generative AI model. The input data is the message stored on the server, and the output data is the message passed to the generative AI model.

Step 5:

The generative AI model generates a translation based on the context. The generative AI model analyzes the context of the input message and generates the optimal translation. For example, for the message "I'm fine," it generates the translation "I'm fine." The input data is the message passed to the generative AI model, and the output data is the generated translation result.

Step 6:

The server receives the translation results. The server receives the translation results generated from the generative AI model and stores them in memory. The input data is the translation results returned from the generative AI model, and the output data is the translation results stored on the server.

Step 7:

The server sends the translation results to the terminal. The server sends the translation results to the terminal using an HTTP response. The input data is the translation results stored on the server, and the output data is the translation results sent to the terminal.

Step 8:

The terminal displays the translation result to the user. The terminal displays the translation result received from the server to the user. For example, the translation result "I'm fine" is displayed on the terminal screen. The input data is the translation result sent to the terminal, and the output data is the translation result displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messaging apps and social media, accurate translations based on context were often not provided when users communicated in different languages. In addition, in virtual stores, users were not provided with appropriate translations when searching for product information or contacting customer support, resulting in a poor user experience.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in Language" button generating means arranged next to the message sending means, a means for automatically translating the message into a language when the "Send in Language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for providing an optimal translation based on context when a user searches for product information or makes an inquiry to customer support in a virtual store. This allows accurate translations based on context to be provided when users communicate in different languages, improving the user experience in the virtual store.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the message entered by the user and selects the translation that best suits that context.

A "virtual store" is a virtual store that offers products and services over the Internet.

"Means for searching product information" refers to a function that enables users to search for information about products and services offered in the virtual store.

"Means to contact customer support" refers to a feature that allows users to report questions or issues to the virtual store's support team.

To implement this invention, the following system configuration is required. The system includes a message sending means, a language send button generating means, an automatic translation means, a sending means, a means for selecting the optimal translation based on the context, a means for searching for product information in a virtual store, and a means for making an inquiry to customer support.

The server receives the message entered by the user and uses a generative AI model to provide the best translation based on the context. Specifically, it uses Hugging Face's Transformers library to translate from English to Japanese. Once the user enters a message, it is sent to the server, which uses the generative AI model to translate it based on the context.

The terminal provides an interface for the user to input and send a message. The terminal includes a message sending means and a send in language button generating means, and allows the user to send a message in a language selected by the user. When the user presses the "send in language" button, the message is automatically translated and sent to other users via the sending means.

As a concrete example, suppose a user types "Can I return this item?" and presses the "Send in Japanese" button. In this case, the server uses the generative AI model to translate it to "Can I return this item?" and sends the translated message to other users via the sending means.

The same process also applies when users search for product information or contact customer support in the virtual store. For example, if a user types "I need help with my order" to contact the support team, the server translates it to "I need help with my order" and provides the appropriate support.

An example of a prompt to input to the generative AI model could be "Translate the following English sentence to Japanese considering the context: 'I need help with my order.'" Using this prompt, the server can provide the best translation based on the context.

The flow of the specific processing in application example 3 is explained using Figure 16.

Step 1:

The user types a message at the terminal. The user types a text message using the message sending means and presses the send button in the language. The input is the user's text message and the output is the typed message displayed at the terminal.

Step 2:

The terminal sends the entered message to the server. The terminal sends the entered message to the server along with send button information in the language pressed by the user. The input is the user's text message and the selected language, and the output is the message data sent to the server.

Step 3:

The server receives the message and performs a translation based on the context. The server analyzes the received message and uses a generative AI model to perform the optimal translation based on the context. The input is the message data sent to the server, and the output is the translated message. Specifically, the translation is performed using Hugging Face's Transformers library.

Step 4:

The server sends the translated message to the terminal. The server sends the translated message to the terminal and displays it to the user. The input is the translated message and the output is the translated message sent to the terminal.

Step 5:

The terminal displays the translated message and transmits it to other users through the transmission means. The terminal displays the translated message to the user and, after the user has confirmed it, transmits the message to other users through the transmission means. The input is the translated message and the output is the message transmitted to other users.

Step 6:

Checks the message received by other users. Other users check the received message and reply if necessary. The input is the received message and the output is the other users' checked message.

In this way, messages entered by users are optimally translated based on the context and accurately conveyed to other users.

Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

"Example 1"

As one embodiment of the present invention, a message translation system incorporating an emotion engine is provided. In this system, when a user types a message in a messenger app or SNS, the emotion engine recognizes the user's emotion. The emotion engine infers the user's emotion from, for example, the context of the user's message, the use of emojis, typing speed, etc. Then, the translation of the message is adjusted based on that emotion. For example, if the user types "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!".

"Example 2"

In another embodiment of the present invention, a system is provided that includes emotion recognition means for an emotion engine to recognize an emotion of a user, and emotion adjustment means for adjusting the translation of a message based on the recognized emotion. The emotion recognition means infers the emotion of the user from the context of the user's message, the use of emojis, typing speed, etc. The emotion adjustment means adjusts the translation of the message based on the recognized emotion. For example, if the user types "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

"Example 3"

Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. In this system, the emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. For example, if the user inputs "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!". On the other hand, if the user inputs "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

The process flow for each example is explained below.

"Example 1"

Step 1: The user types a message in a messenger app or on a social networking site.

Step 2: The emotion engine infers the user's emotion from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

"Example 2"

Step 1: User enters message.

Step 2: The emotion recognition tool infers the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion adjustment mechanism adjusts the translation of the message based on the recognized emotion.

"Example 3"

Step 1: User enters message.

Step 2: The emotion engine recognizes the user's emotions.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users translated and sent messages into other languages, the quality of the translation often lacked emotional expression, and there was a problem that the user's intentions and feelings were not conveyed accurately. In addition, it was inconvenient for users to take the time to translate manually.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a message sending means, a "send in specific language" button generating means, a means for automatically translating the message into a specific language when the "send in specific language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the emotion of the user, and a means for adjusting the translation based on the result of the emotion recognition means. This makes it possible to send a high-quality translated message that reflects the emotion of the user.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that generates a button that is placed next to the message input field and allows the user to send a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

The "translation adjustment means" is a function that adjusts the expression of a translated message based on the results of the emotion recognition means.

Form for implementing the invention

This invention is a system that places a "Send in specific language" button on the message sending screen of a messenger app or SNS, and when a user inputs a message and presses the "Send in specific language" button, the input message is automatically translated into the specific language and the translated message is sent. It also includes a function that recognizes the user's emotions and adjusts the translation based on those emotions by combining it with an emotion engine.

Hardware and software used

Hardware:

Device: The device on which the user types messages (smartphone, tablet, PC, etc.)

Server: A remote server for message translation and emotion recognition.

Software:

Messenger apps and social media applications

Emotion engine (e.g. EmotionAI)

Translation API (e.g. Google Translate API, DeepL API)

Data processing and data calculations

1. Get message:

The device retrieves the message entered by the user.

2. Emotion recognition:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

3. Message translation:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

4. Sending a translated message:

The device will then send the translated message.

Specific examples

When a user types "Today is the best day ever!" into a messenger app and presses the "Send in specific language" button, the process goes like this:

1. The user types, "Today is the best day ever!".

2. The user presses the "Send in specific language" button.

3. Your device will receive the message "Today is a great day!"

4. The server uses "EmotionAI" to recognize the emotion of joy from the message.

5. The server uses the Google Translate API to translate "Today is the best day ever!" to "Today is the best day ever!".

6. The device sends the message "Today is the best day ever!".

Example of a prompt

"Design a system that translates messages typed by users in a messenger app into a specific language and adjusts the message to the appropriate wording based on emotion. For example, if a user types, 'Today is the best day ever!', the emotion engine should recognize joy and translate the message to, 'Today is the best day ever!'"

In this way, a system is realized that appropriately translates and sends messages entered by users based on emotions.

The flow of the identification process in Example 1 is explained using Figure 17.

Step 1:

The user enters a message into the message input field of a messenger app or social networking site.

Input: User types "Today is the best day ever!"

Specific action: The user types a message using a keyboard or touchscreen.

Output: "Today is the best day ever!" is displayed in the message input field.

Step 2:

The user presses the "Send in specific language" button located next to the message input field.

Input: User clicks the "Submit in specific language" button.

Specific action: The user presses a button using a mouse or touch screen.

Output: An event occurs when the button is pressed.

Step 3:

The device retrieves the message entered by the user.

Input: The event of a button being pressed and the input message "Today is the best day ever!".

Specific operation: The device reads text data from the message input field.

Output: The retrieved message "Today is the best day ever!" is stored in memory.

Step 4:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Input: Retrieved message: "Today is the best day ever!".

What it does: The server uses an emotion engine (e.g. EmotionAI) to analyze the message context, detect emojis, and analyze typing speed.

Output: The emotion engine recognizes the user's emotion as "joy".

Step 5:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

Input: Emotion engine result "Joy" and original message "Today is a great day!".

Specific operation: The server uses a translation API (e.g. Google Translate API) to perform translation that takes emotional expressions into account.

Output: The translated message "Today is the best day ever!".

Step 6:

The device will then send the translated message.

Input: Translated message: "Today is the best day ever!".

Specific operation: The device uses the message sending function to send the translated message.

Output: The sent message "Today is the best day ever!" will appear in the recipient's message inbox.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

When users send messages in different languages on traditional messaging apps and social media, the quality of the translation often does not accurately reflect their emotions, lowering the quality of communication. In addition, because the translation does not take into account the user's emotions, there is a risk of misunderstandings and discomfort.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means. In this invention, the server includes a message sending means in a messenger app or SNS, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion analysis means for analyzing the user's emotions, and a means for adjusting the translation based on the emotion analysis means. This enables a natural translation that takes the user's emotions into account.

"Messenger apps and social networking sites" are software applications that allow users to send and receive text messages, images, videos, etc.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

"Means for generating a send button in XX language" is a function that generates a button that allows a user to send a message in a specific language.

"Means for automatic translation" refers to a function that automatically translates a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to other users.

"Emotion analysis means" refers to a function that analyzes a user's emotions from messages entered by the user and other information.

The "means for adjusting the translation" refers to a function for adjusting the translated message based on the emotional information obtained by the emotional analysis means.

To implement this invention, it is necessary to build a system that takes emotions into account when a user sends a message in a messenger app or on a social networking site. This system includes the following main components:

1. Means of sending messages

It provides an interface for users to type and send messages. This can be a messaging app or social networking application that runs on a device such as a smartphone or computer.

2. How to generate a "Send in XX language" button

Creates a "Send in XXX" button that is placed next to the message sending method. This button allows the user to send a message in a specific language. It is automatically selected from the available languages based on the user's preferences.

3. Means of automatic translation

When a user presses the "Send in XXX language" button, the entered message is automatically translated into the specified language. This function is achieved using a generative AI model. Specifically, a translation model using the Transformers library is used.

4. How to send automatically translated messages

Send the translated message to other users. This feature will also be implemented as part of a messaging app or social networking application.

5. Sentiment analysis methods

Analyze user sentiment from messages entered by users and other information. This function is achieved using a generative AI model. Specifically, a sentiment analysis model using the Transformers library is used.

6. Ways to adjust translations

Adjust the translated message based on the emotional information obtained by the emotion analysis means. For example, if positive emotions are detected, change the translated message to a more positive expression.

Hardware and software used

Hardware: servers (cloud servers or on-premise servers), smartphones, computers

Software: Python, Flask, Transformers library

Specific examples

When a user types "Today is the best day ever!" and presses the "Send in English" button, the sentiment analyzer recognizes the joy and the message is translated and sent as "Today is the best day ever!".

Example of a prompt

"Today is the best day!"

The flow of the specific processing in application example 1 is explained using Figure 18.

Step 1:

The user opens a messenger app or social networking application and types a message. The typed message is saved in text format on the device.

Step 2:

The user presses the "Send in XXX language" button. This action causes the device to send the entered message to the server. The data sent includes the message text and the user's selected language.

Step 3:

The server passes the received message text to a sentiment analyzer, which uses a generative AI model to analyze the sentiment of the message. The input is the message text and the output is a sentiment label (e.g. positive, negative, neutral).

Step 4:

The server passes the message text to the translation means based on the emotion label obtained from the emotion analysis means. The translation means translates the message into the specified language using a generative AI model. The input is the message text and the emotion label, and the output is the translated message text.

Step 5:

The server adjusts the translated message text based on the emotion label. For example, if a positive emotion is detected, it changes the translated message to a more positive expression. The input is the translated message text and the emotion label, and the output is the adjusted message text.

Step 6:

The server sends the adjusted message text to the terminal. The terminal displays the received message and sends it to other users. The input is the adjusted message text, and the output is the displayed and sent message.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

In conventional messaging apps and social media, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, because the translation was done without taking into account the user's feelings, there was a risk that unintended nuances would be conveyed. This led to a problem of a decline in the quality of communication.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the user's emotion, and an emotion adjustment means for adjusting the translation of the message based on the recognized emotion. This makes it possible to automatically select a language frequently used by the user and provide an appropriate translation according to the emotion.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

The "means for generating a send button in XX language" is a function that automatically selects an appropriate language from available languages based on the user's settings, and generates a button for sending a message in that language.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

"Emotion adjustment means" is a function that adjusts the translation of a message based on the recognized emotions of the user.

This invention is a system that reduces the effort required for users to send messages in different languages and provides appropriate translations according to emotions. A specific embodiment of this system is described below.

Hardware and software used

Server: Responsible for data processing and storage. Specifically, it uses cloud services (e.g. AWS (registered trademark), Google Cloud Platform).

Device: The device used by the user. This includes smartphones, tablets, PCs, etc.

Generative AI model: A model for performing natural language processing. For example, OpenAI's GPT-3 (registered trademark) or GPT-4 (registered trademark) are used.

Emotion engine: An engine for recognizing user emotions. For example, using IBM Watson (registered trademark) emotion analysis API.

System processing flow

1. User language settings

Users select the language they frequently use in the application settings screen.

The device sends the selected language information to the server.

The server stores the received language information in a database.

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

2. Create a language selection button

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

3. Enter your message

The user enters text into the message input field.

The device sends the entered message to the server in real time.

What it does: When a user types "Today is the worst day...", the text is instantly sent to the server.

4. Emotion Recognition

The server sends the received message to the emotion engine.

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

The server receives the results from the emotion engine and stores the emotion information.

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

5. Translation adjustments

The server sends a translation request to the generative AI model based on the recognized emotion.

The generative AI model generates appropriate translations based on emotions.

The server sends the generated translation to the device.

Specific operation: The generative AI model generates the translation "Today is the worst day..." and the server sends it to the device.

6. Sending a message

The user presses the "Send in French" button.

The device sends the translated message to the server.

The server receives the message and sends it to the specified recipient.

Specific operation: When the user presses the "Send in French" button, the device sends the message "Aujourd'hui est le pire jour..." to the server, which then sends it to the recipient.

Example of a prompt

"Please explain the function that allows users to set their frequently used language and automatically generate a submit button in that language on subsequent visits."

"Please explain the functionality that recognizes user emotions and adjusts the translation of the message based on the recognized emotion."

To improve user convenience, the system automatically selects frequently used languages and provides appropriate translations according to sentiment.

The flow of the identification process in Example 2 is explained using Figure 19.

Step 1:

Users select the language they frequently use in the application settings screen.

Input: The language selected by the user in the settings screen (e.g. French)

Output: Selected language information

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

Step 2:

The device sends the selected language information to the server.

Enter: Selected language information

Output: Language information sent to the server

Specific operation: The device sends the user's selected language information to the server.

Step 3:

The server stores the received language information in a database.

Input: Language information sent to the server

Output: Language information stored in the database

Specific operation: The server stores the language information received in the database.

Step 4:

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Input: Language information stored in the database

Output: Submit button information in generated language

Specific behavior: The server retrieves language information from the database and generates information for the "Submit in French" button.

Step 5:

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Input: Submit button information for generated language

Output: A submit button displayed in the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

Step 6:

The user enters text into the message input field.

Input: A message typed by the user (e.g., "Today is the worst day...")

Output: The message entered

Specific action: User types, "Today is the worst day..."

Step 7:

The device sends the entered message to the server in real time.

Input: Message entered

Output: Message sent to server

Specific operation: The device sends the entered message to the server.

Step 8:

The server sends the received message to the emotion engine.

Input: Message sent to server

Output: Message sent to emotion engine

Specific operation: The server sends the received message to the emotion engine.

Step 9:

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

Input: Message sent to emotion engine

Output: Inferred emotion information (e.g. sadness)

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

Step 10:

The server receives the results from the emotion engine and stores the emotion information.

Input: Inferred emotion information

Output: Stored emotion information

Specific operation: The server receives emotion information from the emotion engine and stores it in the database.

Step 11:

The server sends a translation request to the generative AI model based on the recognized emotion.

Input: Stored emotion information, user message

Output: Translation request sent to generative AI model

Specific operation: The server sends emotion information and the user's message to the generative AI model.

Step 12:

The generative AI model generates appropriate translations based on emotions.

Input: Translation request sent to generative AI model

Output: Generated translation (e.g. "Today is the worst day...")

Specific behavior: The generative AI model generates the translation "Today is the worst day..."

Step 13:

The server sends the generated translation to the device.

Input: Generated translation

Output: Translation sent to device

Specific operation: The server sends the generated translation to the device.

Step 14:

The user presses the "Send in French" button.

Input: User operation

Output: Send button press information

Specific action: The user presses the "Send in French" button.

Step 15:

The device sends the translated message to the server.

Input: Send button press information, generated translation

Output: The translated message sent to the server

Specific action: The device sends the message "Aujourd'hui est le pire jour..." to the server.

Step 16:

The server receives the message and sends it to the specified recipient.

Input: Translation message sent to server

Output: Message sent to recipient

Specific operation: The server sends the translated message to the recipient.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

Existing messenger apps and SNS lack the ability to automatically select the language frequently used by the user or adjust the translation of messages based on the user's emotions, limiting the user experience. There is also a demand for more natural and appropriate communication by recognizing the user's emotions and adjusting the translation based on them. Furthermore, content distribution services also face the challenge of improving the viewing experience by adjusting subtitles and audio translations based on the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means.

In this invention, the server includes a message sending means for a messenger app or SNS, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing a user's emotion, an emotion adjustment means for adjusting the translation of the message based on the recognized emotion, a language selection means for automatically selecting a language based on the user's settings and past usage history, and a translation adjustment means for adjusting the translation of subtitles and audio based on the user's emotion. This makes it possible to automatically select a language frequently used by the user and adjust the translation of messages and content based on the user's emotion.

"Message sending means" refers to an interface that allows users to input and send messages.

The "send button generation means in XX language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings and usage history.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" is technology for recognizing emotions from user input, facial expressions, voice, etc.

"Emotion adjustment means" is a function that adjusts the translation or display of a message based on the recognized emotion.

"Language selection means" is a function that automatically selects the most appropriate language based on the user's settings and past usage history.

"Translation adjustment means" is a function that adjusts the translation of subtitles and audio based on the user's emotions.

The following system configuration is described as a form for implementing this invention.

System configuration

This system includes a means for sending messages in messenger apps and SNS, a means for generating send buttons in a certain language, an automatic translation means, an emotion recognition means, an emotion adjustment means, a language selection means, and a translation adjustment means.

Method of sending message

An interface that allows users to input and send messages. It is implemented as an application on a smartphone or PC.

How to generate a send button in XX language

This function automatically generates buttons for sending messages in a specific language based on the user's settings and usage history. It automatically selects the language the user frequently uses and displays it as a button.

Automatic translation methods

This function automatically translates messages entered by users into a specified language. It is implemented using a translation API such as Google Translator.

Emotion recognition means

This is a technology for recognizing emotions from user input, facial expressions, voice, etc. It uses software such as OpenCV and EmotionRecognizer to analyze data from the camera and microphone.

Methods of emotion regulation

This feature adjusts the translation and display of messages based on the recognized emotion. For example, if the user has a sad expression, the translated message will be adjusted accordingly.

Language selection method

This function automatically selects the most suitable language based on the user's settings and past usage history. Content from the next time onwards will also be automatically selected based on the user's viewing history and settings information.

Translation adjustment methods

This feature adjusts subtitle and audio translations based on the user's emotions. For example, if the user looks sad, the subtitle translation will be adjusted accordingly.

Program processing explanation

The server captures data from the camera and microphone and recognizes the user's emotions using OpenCV and EmotionRecognizer. Based on the recognized emotions, it translates the message using a translation API such as Google Translator and displays the message adjusted by the emotion adjustment means. Based on the user's settings and past usage history, the language selection means automatically selects the most suitable language.

Specific examples

If a user frequently speaks French, the application will automatically provide content in French. And if the user has a sad expression, the subtitle translation will adjust accordingly.

Example of a prompt

Develop a smartphone application that automatically selects the language that the user frequently uses and uses an emotion engine to recognize the user's emotions and adjust the translation accordingly. For example, if the user frequently uses French, the application automatically provides content in French. Also, if the user has a sad expression, the subtitle translation will be adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

The flow of the specific processing in application example 2 is explained using Figure 20.

Step 1:

The server captures the user's video and audio data from the device through the camera and microphone. The input is the user's video and audio data, and the output is the captured raw data. This data is used in subsequent processing steps.

Step 2:

The server analyzes the captured video and audio data using OpenCV and EmotionRecognizer to recognize the user's emotions. The input is the captured raw data, and the output is the recognized emotional information. Specifically, it analyzes the user's facial expressions and tone of voice, and classifies emotions into "happiness," "sadness," "anger," etc.

Step 3:

The server uses a language selection means to automatically select the most appropriate language based on the user's settings and past usage history. The input is the user's settings information and usage history, and the output is the selected language information. Specifically, the language that the user frequently uses is obtained from the database and applied to the next and subsequent content.

Step 4:

The user enters a message and presses the send button. The input is the message entered by the user, and the output is the event information that the send button has been pressed. Specifically, this includes the action of the user entering a message into a text box and pressing the "Send in XX language" button.

Step 5:

When the send button is pressed, the server uses a translation API such as Google Translator to automatically translate the entered message into the selected language. The input is the message entered by the user and the selected language information, and the output is the translated message. Specifically, the message and target language are sent to the API and the translation result is received.

Step 6:

The server adjusts the translated message based on the recognized emotion with an emotion adjustment means. The input is the translated message and the recognized emotion information, and the output is the adjusted message. Specifically, if the user is expressing a sad emotion, the translated message is adjusted to be more negative accordingly.

Step 7:

The server sends the adjusted message through the message sending means. The input is the adjusted message and the output is the sent message. Specifically, the server sends the adjusted message to the recipient and displays a notification of the completion of the sending on the user's interface.

Step 8:

The server adjusts the subtitle and audio translations in the content delivery service based on the user's emotions. The input is the user's emotional information and content data, and the output is the adjusted subtitles and audio. Specifically, if the user has a sad expression, the subtitle translation is adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

Conventional message translation systems perform simple translations without considering the context or emotions of the message entered by the user, which often results in inappropriate translations. In addition, there is a problem that the quality of communication declines because the translation cannot reflect the user's emotions. This creates an issue in that it becomes difficult to convey the exact meaning and emotions intended by the user.

The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "send in translation language" button generating means located next to the message sending means, a means for automatically translating the message into the translation language when the "send in translation language" button is pressed, a means for sending the automatically translated message, a context analysis means for selecting an optimal translation based on the context of a message input by a user, and an emotion analysis means for recognizing the user's emotion and adjusting the translation based on that emotion. This makes it possible to provide an optimal translation of a user's input message based on the context and emotion.

"Message sending means" is a function for sending messages entered by a user to other users.

The "means for generating a send button in a translated language" is a function for generating a button for sending a message in a translated language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified translation language.

"Context analysis means" is a function that analyzes the context of the message entered by the user and selects the most appropriate translation based on that context.

"Sentiment analysis means" is a function that recognizes the emotion of the message entered by the user and adjusts the translation based on that emotion.

"Transmission means" is a function for sending translated messages to other users.

"User settings" are settings that users make to customize system behavior, translation languages, etc.

"Translation language" is the language the user uses to translate the message.

Form for implementing the invention

This invention is a system that provides an optimal translation of a message entered by a user based on the context and emotion. A specific embodiment of this system is described below.

System configuration

The system mainly consists of the following components:

1. Means of sending messages

2. How to generate a send button in a translated language

3. Automatic translation methods

4. Contextual analysis methods

5. Sentiment analysis methods

6. Transmission method

Hardware and software used

The server uses the following hardware and software to receive, parse, translate, and send messages:

Server hardware: A server with a powerful processor and sufficient memory

Software: Python, NLTK library, Google Natural Language API

The device uses the following hardware and software to allow users to enter messages and display translation results:

Device hardware: smartphones, tablets, PCs, etc.

Software: Messenger apps, SNS apps

System operation

The user inputs a message into an input field on the terminal. For example, the user inputs "I'm fine." The terminal sends this message to the server. The server sends the received message to the context analysis means, which analyzes the context of the message. The context analysis means analyzes the context using, for example, Python's NLTK library, and translates the message "I'm fine." into "I'm fine."

The server then sends the translation to the sentiment analyzer, which uses Google's Natural Language API to analyze the sentiment of the message. For example, if the user types "Today is the best day ever!" and the sentiment analyzer recognizes joy, the translation is adjusted to "Today is the best day ever!".

Finally, the server sends the adjusted translation result to the terminal, and the terminal displays the translation result to the user. The user can check the translation result on the terminal screen.

Specific examples

As a concrete example, consider the case where a user types "I'm fine" into a terminal. This message is sent to the server, where the context analysis means translates it as "I'm fine." If the user then types "Today is the best day ever!", the emotion analysis means will recognize the joy, and the server will translate it as "Today is the best day ever!".

Example of a prompt:

If a user types "I'm fine," choose the appropriate translation based on the context and analyze the sentiment using sentiment analysis tools.

If a user types "Today is a great day!", use sentiment analysis to recognize the sentiment and choose the appropriate translation.

This system supports more natural and appropriate communication by providing an optimal translation of the user's input message based on the context and emotion. The flow of the specific process in Example 3 is explained with reference to FIG. 21.

Step 1:

The user types a message.

The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." The entered message is passed to the terminal's message sending means.

Step 2:

The device sends the message to the server.

The terminal sends the message entered by the user to the server. At this time, the message is sent as an HTTP request. The input is the user's message, and the output is an HTTP request to the server.

Step 3:

The server receives the message and sends it to the context analysis means.

The server sends the received message to the contextual analyzer, which analyzes the context using, for example, Python's NLTK library. The input is the user's message and the output is the data to the contextual analyzer.

Step 4:

The contextual analysis means analyzes the context of the message and selects the appropriate translation.

The contextual analysis means analyzes the context of the message and selects the appropriate translation. For example, the message "I'm fine." is translated as "I'm fine." The input is the user's message and the output is the translation result.

Step 5:

The server sends the translation results to the sentiment analysis means.

The server transmits the translation results obtained from the context analysis means to the sentiment analysis means. The sentiment analysis means analyzes sentiment using, for example, Google's (registered trademark) Natural Language API. The input is the translation result, and the output is data to the sentiment analysis means.

Step 6:

Sentiment analysis tools analyze the sentiment of the message and adjust the translation.

The sentiment analyzer analyzes the sentiment of the message and adjusts the translation. For example, if the message "Today is the best day ever!" is recognized as expressing joy, the translation is adjusted to "Today is the best day ever!". The input is the translation and the output is the adjusted translation.

Step 7:

The server sends the final translation results to the device.

The server sends the final translation result obtained from the sentiment analysis means to the terminal. At this time, the translation result is sent as an HTTP response. The input is the adjusted translation result, and the output is the HTTP response to the terminal.

Step 8:

The device displays the translation results to the user.

The terminal displays the translation results received from the server to the user. The user can check the translation results on the terminal screen. The input is the translation result from the server, and the output is what is displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

Conventional message translation systems perform translation without considering the context or emotion of the message entered by the user, resulting in unnatural translations or failure to accurately convey the user's intent. In addition, since translations cannot reflect emotion, it is difficult to properly convey the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in language" button generating means located next to the message sending means, a means for automatically translating the message into a language when the "Send in language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for recognizing the user's emotion using an emotion engine and adjusting the translation based on that emotion. This enables a natural and appropriate translation that takes into account the context and emotion of the message input by the user.

"Message sending means" refers to an interface that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Means for automatic translation" refers to a function that automatically translates an input message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the input message and selects the translation that best suits that context.

The "emotion engine" is a system that recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

"Means for adjusting a translation based on emotion" refers to a function for adjusting a translated message based on a user's emotion as recognized by an emotion engine.

A system for implementing the present invention includes a message sending means, a language send button generating means, a means for automatic translation, a means for sending the automatically translated message, a means for selecting an optimal translation based on context, an emotion engine, and a means for adjusting the translation based on emotion.

System configuration

The server uses the following hardware and software:

Hardware: The server uses a computer system with a high-performance processor and sufficient memory. Specifically, Intel Xeon processors and AMD EPYC processors are suitable.

Software: The server uses the Python programming language and the transformers natural language processing library. It also uses the nltk library for sentiment analysis.

Processing flow

1. Message sending means: Provides an interface for users to enter text messages. This is an application that runs on a mobile device such as a smartphone or tablet.

2. Send in language button generator: Generates a button to send a message in the language selected by the user. This button is automatically selected based on the user's settings.

3. Means of automatic translation: Automatically translate messages entered by users into a specified language. This translation is done using a generative AI model.

4. How to send an automatically translated message: Send an automatically translated message to other users.

5. A means to select the best translation based on context: Analyze the context of the message entered by the user and select the translation that best suits that context.

6. Emotion engine: Recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

7. Means to tailor translation based on emotion: Adjust the translated message based on the user's emotion as recognized by the emotion engine.

Specific examples

For example, if a user is watching a movie and a character says, "I'm so happy today!", the emotion engine will recognize the positive emotion and adjust the translation to "I'm so happy today!".

Example of a prompt to input to the generative AI model:

"Translate the following text to Japanese and adjust the translation based on the detected emotion: 'I'm so happy today!'"

In this way, the user's viewing experience can be enriched.

The flow of the specific processing in application example 3 is explained using Figure 22.

Step 1:

The user enters a message on the terminal. The entered message is sent to the server in text format. The input data is the text message entered by the user.

Step 2:

The server analyzes the received messages and performs natural language processing (NLP) to understand the context. For this process, it uses the transformers library. The input data is the text message entered by the user, and the output data is the analysis result including contextual information.

Step 3:

The server uses a generative AI model to generate an optimal translation based on the analysis results. Specifically, it uses a translation model from the transformers library to translate the message into the specified language. The input data is the analysis results including contextual information, and the output data is the translated text message.

Step 4:

The server passes the translated message to an emotion engine to recognize the user's emotion. The emotion engine uses the nltk library. The input data is the translated text message, and the output data is the emotion label (e.g. positive, negative).

Step 5:

The server adjusts the translated message based on the emotion label. For example, for positive emotion it adds "Da yo!" to the translated message, and for negative emotion it adds "Da...". The input data are the emotion label and the translated text message, and the output data is the adjusted translated message.

Step 6:

The server sends the adjusted translation message to the terminal. The terminal displays the received message to the user. The input data is the adjusted translation message, and the output data is the text message displayed to the user.

Step 7:

The user checks the displayed message and replies if necessary. The reply message is sent again through the process from step 1. The input data is the reply message entered by the user, and the output data is the translated and adjusted reply message.

The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input for the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (registered trademark) (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

Another example of generative AI is Gemini (registered trademark) (Internet search <URL: https://gemini.google.com/?hl=ja>).

In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart device 14.

[Second embodiment]

Figure 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

As shown in FIG. 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I/F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is performed in a secure state.

Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. Data generation model 58 and emotion identification model 59 are used by the identification processing unit 290.

In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12.

"Example 1"

As one embodiment of the present invention, a "Send in English" button is placed next to the message input field on the message sending screen of a messenger app or SNS. When a user inputs a message and presses the "Send in English" button, the input message is automatically translated into English and the translated message is sent.

"Example 2"

Furthermore, we provide a function that automatically selects the language of the "Send in ____" button from the available languages based on the user's settings. For example, if the user frequently communicates with people who speak French, the "Send in French" button will be automatically generated based on the user's settings.

"Example 3"

The service also provides a function that selects the most appropriate translation based on the context of the message entered by the user. For example, if the user enters "I'm fine," this will be translated as "I'm fine." However, if the user enters "It's fine," this will be translated as "It's fine." In this way, the translation method for the same "fine" changes depending on the context.

The process flow for each example is explained below.

"Example 1"

Step 1: The user opens the message sending screen of a messenger app or SNS.

Step 2: Make sure the "Send in English" button is located next to the message input field.

Step 3: The user enters a message and presses the "Send in English" button.

Step 4: The system will automatically translate the message you entered into English.

Step 5: The system sends the translated message.

"Example 2"

Step 1: The user opens the settings screen of the messenger app or SNS.

Step 2: The user selects the language from the available options for the "Send in" button. Step 3: The user saves the settings and returns to the message sending screen.

Step 4: Make sure there is a "Send in XXX" button in the user's chosen language next to the message input field.

"Example 3"

Step 1: User enters message.

Step 2: The system selects the best translation based on the context of the message entered by the user.

Step 3: The system displays the selected translation to the user.

Step 4: The user presses the "Send in XXX language" button and the system sends the selected translation.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, the translation was often inaccurate and did not provide an appropriate translation based on the context, which could impair smooth communication. To solve these problems, a system was needed that would allow users to easily translate and send messages in a specific language.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in specific language" button generating means disposed next to the message sending means, a means for automatically translating the message into a specific language when the "Send in specific language" button is pressed, a means for sending the automatically translated message, a means for inputting the message into a generative AI model as a prompt sentence, a means for the generative AI model to translate the message, and a means for sending the translated message to a destination. This enables a user to easily translate and send a message into a specific language.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that is placed next to the message sending means and generates a button for sending a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

A "generative AI model" is an artificial intelligence model for performing natural language processing and capable of translating input text into other languages.

A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

"Means for sending translated messages" refers to a function for sending messages translated by the automatic translation means to a specified destination.

"Optimal translation based on context" refers to providing the most appropriate translation by taking into account the content and intent of the message entered by the user.

This invention is a system that allows users to easily translate and send messages into a specific language in messenger apps and SNS. A specific embodiment of this system is described below.

First, a user opens the message sending screen of a messenger app or SNS and enters a message in the message input field. For example, the user might enter "Hello, how are you?". Next, the user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in an appropriate format. The server inputs the received message into a generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, it sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

The generative AI model receives the prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" to "Hello, how are you?". The server sends the translated message received from the generative AI model to the device. At this time, the translated message is sent to the device in the appropriate format.

The device then sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend. In this way, a message entered by the user in Japanese is automatically translated into a specific language and sent.

As a concrete example, consider a case where a user wants to send a message to a friend saying "Hello, how are you?" The user enters "Hello, how are you?" in the message input field and presses the "Send in specific language" button. The system translates this message into "Hello, how are you?" and sends it to the friend.

Example of a prompt to input to a generative AI model:

"Please translate 'Hello, how are you?' into English."

This system allows users to easily translate and send messages into a specific language. The hardware used includes the user's device (smartphone, tablet, PC, etc.) and a server. The software used includes messenger apps, SNS applications, and generative AI models (e.g., GPT-4 (registered trademark)).

The flow of the identification process in Example 1 is explained using Figure 11.

Step 1:

The user enters a message in the message input field.

Enter: "Hello, how are you?"

Output: Input message "Hello, how are you?"

Specific actions: The user opens the message sending screen of a messenger app or SNS and types "Hello, how are you?" in the message input field.

Step 2:

The user presses the "Send in specific language" button.

Input: User presses the "Send in specific language" button

Output: Event that the send button was pressed

Specific behavior: The user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

Step 3:

The device sends the entered message to the server.

Input: An event that inputs the message "Hello, how are you?" and presses the send button

Output: Message sent to server: "Hello, how are you?"

Specific operation: The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in the appropriate format.

Step 4:

The server inputs the message into the generation AI model as a prompt.

Input: Message sent to server: "Hello, how are you?"

Output: Prompt sent to the generative AI model: "Please translate 'Hello, how are you?' into English."

Specific operation: The server inputs the received message into the generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, the server sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

Step 5:

A generative AI model translates the message into English.

Input: Prompt text: "Please translate 'Hello, how are you?' into English."

Output: The translated message "Hello, how are you?"

Specific behavior: The generative AI model receives a prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" into "Hello, how are you?".

Step 6:

The server sends the translated message to the device.

Input: translated message "Hello, how are you?"

Output: The translated message "Hello, how are you?" sent to the terminal.

Specific operation: The server sends the translated message received from the generative AI model to the terminal. At this time, the translated message is sent to the terminal in an appropriate format.

Step 7:

Your device will then send the translated message to the recipient.

Input: The translated message sent to the device: "Hello, how are you?"

Output: The message "Hello, how are you?" sent to the destination.

Specific operation: The device sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

With the current trend of globalization, communication with foreign customers has become important in brick-and-mortar stores. However, the language barrier makes it difficult for store staff to communicate smoothly with foreign customers. To solve this problem, real-time language translation is necessary, but current technology is not sufficient.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a voice input means, a means for converting voice acquired by the voice input means into text, a means for translating the text into XXX language, and a means for vocally outputting the translated text. This enables smooth real-time communication between store staff and foreign customers in physical stores.

"Message sending means" refers to an interface that allows a user to input and send text messages.

The "means for generating a send button in XX language" is a function that generates a button for translating and sending a message into a language selected by the user.

"Means for automatic translation" refers to a function for automatically translating an input text message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to the other party.

"Voice input means" is an interface for capturing the user's voice and acquiring it as digital data.

"Means for converting voice to text" refers to a function for converting acquired voice data into text data.

"Means of translating text into XX language" is a function for translating text data into a specified language.

"Means for outputting translated text as audio" refers to a function for playing back translated text as audio.

To implement this invention, the following system configuration and program are required.

First, the server provides a message sending means, which is an interface that allows the user to input and send a text message. Next, the server provides a "Send in XX language" button generating means, which is a function that generates a button for translating and sending a message into a language selected by the user.

When a user presses the "Send in XXX language" button, the server uses an automatic translation means to automatically translate the entered text message into the specified language. This translated message is then sent to the recipient by a means for sending an automatically translated message.

Furthermore, the server provides a voice input means, which is an interface for capturing the user's voice and acquiring it as digital data. The acquired voice data is converted into text data by a voice-to-text conversion means.

The converted text data is translated into a specified language by a means for translating text into a specific language. The translated text is played as audio by a means for outputting the translated text as audio.

To realize this system, the following hardware and software are used:

Hardware: Smart glasses (capable of voice input and output)

Software:

speech_recognition library: convert speech to text

googletrans library: translate text

pyttsx3 library: convert text to speech

As a concrete example, when a store clerk says, "Where is this product located?", the voice is captured by the microphone of the smart glasses. The voice data is converted to text using the speech_recognition library, and the text is translated into English using the googletrans library. The translated text is converted to speech using the pyttsx3 library, and "Where is this product located?" is played from the speaker of the smart glasses.

Example of a prompt to input to a generative AI model:

When a user says "Where is this product located?", convert that speech to text, translate it into English, display "Where is this product located?" and play it aloud.

The flow of the specific processing in application example 1 is explained using Figure 12.

Step 1:

The user speaks into the smart glasses. The microphone in the smart glasses captures the voice and obtains it as voice data. This voice data becomes the input.

Step 2:

The voice data acquired by the device (smart glasses) is converted into text data using the speech_recognition library. The voice data is analyzed and corresponding text data is generated. This text data becomes the output.

Step 3:

Translates text data generated by the device into a specified language (e.g. English) using the googletrans library. Takes text data as input and generates translated text data. This translated text data is the output.

Step 4:

The device converts the translated text data into speech data using the pyttsx3 library. It takes the translated text data as input and generates the corresponding speech data. This speech data becomes the output.

Step 5:

The device then plays the generated voice data through the smart glasses' speakers, allowing the user to listen to the translated audio.

Specifically, when a user says "Where is this product located?", the voice is captured by the microphone in the smart glasses. The voice data is converted into text data saying "Where is this product located?" using the speech_recognition library. The text data is translated into English as "Where is this product located?" using the googletrans library. The translated text data is converted into voice data using the pyttsx3 library, and "Where is this product located?" is played from the speaker in the smart glasses.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

In conventional messaging apps and SNS, when users wanted to send a message in a different language, they had to translate it manually, which was a time-consuming process. In addition, there was no function to automatically select frequently used languages, so users had to select the language every time, which was inconvenient. Furthermore, the quality of the translation was not consistent, so the translation did not always match the context of the message.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a means for acquiring user setting information, a means for sending a prompt sentence to the generative AI model based on the acquired setting information, a means for generating a "Send in XXX language" button based on a response from the generative AI model, a means for displaying the generated "Send in XXX language" button in a user interface, and a means for sending a message when the user clicks the "Send in XXX language" button. This makes it possible to automatically select a language frequently used by the user and perform an appropriate translation.

"User settings information" refers to the individual language and other customization information that a user sets within the system.

A "generative AI model" is a model designed to perform specific tasks using artificial intelligence. In this case, its role is to generate prompts based on user settings and generate appropriate language selection buttons.

A "prompt sentence" refers to an input sentence that gives specific instructions or asks a question to a generative AI model.

"Send in XXX language button" refers to a button on the interface that allows a user to send a message in a specific language of their choice.

"User interface" refers to the screens and operating means that allow users to interact with the system.

"Means of sending messages" refers to the functionality for sending messages entered by the user in the selected language.

This invention relates to a system for messenger apps and SNS that automatically selects a language frequently used by a user and performs appropriate translation. A specific embodiment of this system is described below.

Server processing

The server retrieves the user's settings information from a database. Specifically, it uses a database management system such as MySQL (registered trademark) to retrieve information on the languages frequently used by the user. For example, it executes an SQL query that retrieves the corresponding language settings using the user ID as a key.

The server then sends a prompt to a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) based on the retrieved user settings. The prompt includes instructions to generate a "Send in XXX language" button based on the user's frequently used language.

Example of a prompt:

"Based on the user's preferences, select the frequently used language and generate a corresponding submit button. For example, if the user selects French, generate a 'Submit in French' button."

The server that receives the response from the generative AI model generates the data to display in the user interface. Specifically, it generates HTML and JavaScript (registered trademark) code and creates buttons that correspond to the language selected by the user.

Terminal processing

The terminal receives the data sent from the server and reflects it in the user interface. Specifically, it dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React.

User operations

The user selects the languages they use most frequently in the settings screen. For example, if the user selects French, a "Send in French" button will be automatically generated from next time. The user can click this button to send messages in the selected language.

Specific examples

For example, if a user selects "French" in the settings screen, the "Send in French" button will be automatically generated next time. When the user clicks this button, the message will be sent in French.

In this way, it is possible to automatically select the language that the user frequently uses and provide an appropriate translation. This saves the user the trouble of having to manually select the language, allowing for smoother communication.

The flow of the identification process in Example 2 is explained using Figure 13.

Step 1:

Get user settings information

The server retrieves the user's preference information from a database. As input, a user ID is given. The server uses a database management system such as MySQL (registered trademark) to retrieve information about the user's frequently used languages. Specifically, it executes an SQL query using the user ID as a key to retrieve the corresponding language preference. As output, the user's preference information (e.g., French) is obtained.

Step 2:

Generating and sending prompts

The server sends a prompt to the generative AI model based on the acquired user setting information. The user's setting information is given as input. The prompt includes an instruction to generate a "Send in XX language" button based on the language the user frequently uses. An example of a specific prompt is "Based on the user's settings, please select the language that is frequently used and generate a corresponding send button. For example, if the user selects French, please generate a 'Send in French' button." The output is a response from the generative AI model.

Step 3:

Generate language selection button

The server generates a "Send in XXX language" button based on the response from the generative AI model. The response from the generative AI model is given as input. The server generates HTML and JavaScript (registered trademark) code to create a button that corresponds to the language selected by the user. The output is the data for the generated "Send in XXX language" button.

Step 4:

Display language selection button

The terminal receives the data sent from the server and reflects it in the user interface. As input, it is given the data for the "Send in XX language" button sent from the server. The terminal dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React. As output, it obtains the button displayed in the user interface.

Step 5:

Send a message

The user clicks the generated "Send in French" button. As input, the user's click event is given. When the click event occurs, a message is sent in the selected language. Specifically, a JavaScript® event listener is used to catch the button click event and process the message sending. As output, the message sent in the selected language is obtained.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

In conventional messenger apps and SNS, when users communicate in different languages, they have to translate manually, which is inefficient. In addition, there was a lack of functionality to automatically learn frequently used languages and send messages in the appropriate language, which made it inconvenient for users.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means. In this invention, the server includes a message sending means, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a means for acquiring user setting information, a means for learning frequently used languages based on the setting information, a means for automatically generating the "Send in XXX language" button based on the learned languages, a means for translating the message in real time, and a means for sending the translated message. This makes it possible to automatically learn languages frequently used by the user and send messages in the appropriate language.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending translated messages to other users.

"Means for acquiring user setting information" refers to a function for acquiring the language and other setting information previously set by the user.

"Means for learning frequently used languages" refers to a function for learning the languages that a user frequently uses based on the user's past message history and settings information.

"Means of real-time translation" refers to a function that translates a message into a specified language in real time as the user types the message.

The system for implementing this invention is composed of a server and a user terminal. The server includes a message sending means, a "send in XX language" button generating means, an automatic translation means, a sending means, a means for acquiring user setting information, a means for learning frequently used languages, and a means for translating in real time.

Program processing explanation

Hardware to be used

Server: Any cloud server (e.g. AWS (registered trademark), Google Cloud)

Client: Smartphone (iOS or ANDROID (registered trademark))

Software to be used

Framework: Flask (Python)

Translation API: Googletrans (Python wrapper for Google Translate API)

Data processing and data calculations

1. How to get user settings information:

The server retrieves the user's pre-selected language and other preferences. This information is used to learn the user's frequently used languages based on their past message history and preferences.

2. Ways to learn frequently used languages:

The server learns which languages the user frequently uses based on the user's past message history and preferences. This allows it to identify the language the user uses most often and automatically generate a button to send messages in that language.

3. How to generate the "Send in ____ language" button:

The server automatically generates a button to send a message in a specific language based on the user's preferences. This button is displayed when the user types a message.

4. Ways to translate in real time:

As users type their messages, the server translates them into the specified language in real time, allowing users to see the translated message instantly.

5. Automatic translation methods:

When a user presses the "Send in XXX language" button, the server automatically translates the message into the specified language. This translation is done using a translation API such as GoogleTrans.

6. Transmission method:

The translated messages are then sent to other users via the server, allowing users who speak different languages to communicate smoothly.

Specific examples

For example, if the user is "user1" and sends the message "Hello, how are you?", the server will translate this message into French and return it as "Bonjour, comment &ccedil;a va?".

Example of a prompt

User ID: user1

Message: Hello, how are you?

When you send this prompt to the server, you will get a response like this:

{

"original_message": "Hello, how are you?",

"translated_message": "Bonjour, comment &ccedil;a va?",

"language": "fr"

}

In this way, a system can be created that automatically selects a language based on the user's settings and then translates and sends the message.

The flow of the specific processing in application example 2 is explained using Figure 14.

Step 1:

The user inputs a message. The user inputs a text message using the smartphone's message sending means. This input message is sent to the server.

Step 2:

The server retrieves the user's preferences. The server retrieves the user's preferences from a database and identifies the user's frequently used languages. This preference information includes languages the user has used in the past and languages that have been preset by the user.

Step 3:

The server learns which languages are used most frequently. Based on the configuration information obtained, the server learns which languages are used most frequently by users. Based on the results of this learning, it generates a "Send in XXX" button for sending messages in a specific language.

Step 4:

The server generates a "Send in XX language" button. Based on the learning results, the server automatically generates a button for sending messages in the language the user frequently uses and displays it on the user's device.

Step 5:

The user presses the "Send in XXX" button. By pressing the generated "Send in XXX" button, the user instructs the message they typed to be translated into a specific language.

Step 6:

The server translates the message in real time. The server translates the message entered by the user into the specified language in real time. This translation uses a translation API such as Googletrans.

Step 7:

The server sends the translated message. The server returns the translated message to the user's device so that the user can review it. The server then sends the translated message to other users.

Step 8:

Other users receive the translated message. Other users receive and display the translated message sent from the server. This allows users who speak different languages to communicate smoothly.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

In conventional messaging apps and SNS, it was difficult to provide appropriate translations based on the context when users sent messages. In particular, when the same word had different meanings depending on the context, it was difficult to select the appropriate translation.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a message sending means, a "send with translation" button generating means disposed next to the message sending means, a means for automatically translating the message when the "send with translation" button is pressed, a means for sending the automatically translated message, a means for receiving a message input by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to the user. This makes it possible to provide an optimal translation based on the context of the message input by the user.

"Message sending means" refers to a means for sending messages entered by a user to other users.

The "translation and send button generation means" is a means for generating a button that enables a user to translate and send a message.

"Means for automatic translation" refers to a means for automatically translating a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to means for sending translated messages to other users.

"Means for receiving messages entered by users" refers to the means by which the server receives messages entered by users.

"Means for inputting a message into a generative AI model" refers to means for inputting a received message into a generative AI model.

"Means by which a generative AI model generates a context-based translation" refers to the means by which a generative AI model analyzes the context of a message and generates an optimal translation.

"Means for receiving the generated translation results" refers to means for receiving the translation results generated from the generative AI model.

"Means for displaying the translation result to the user" refers to means for displaying the received translation result to the user.

This invention relates to a system that optimally translates a message entered by a user based on the context. This system includes a message sending means, a translation send button generating means, an automatic translation means, a means for sending the automatically translated message, a means for receiving a message entered by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to a user.

Hardware and software used

This system uses a server, a terminal, and a generative AI model. Specifically, the server receives messages, inputs them into the generative AI model, and receives and sends translation results. The terminal inputs messages from users and displays the translation results. For example, OpenAI's GPT-4 (registered trademark) is used as the generative AI model.

Data processing and data calculations

The server receives the message entered by the user on the device and inputs the message into the generative AI model. The generative AI model analyzes the context of the message and generates the optimal translation. The generated translation result is returned to the server, which then sends the result to the device. The device displays the translation result to the user.

Specific examples

As a concrete example, consider the case where a user types "I'm fine." In this case, the server uses a generative AI model to generate the translation "I'm fine." On the other hand, if the user types "It's fine.", the server generates the translation "It's fine."

Example of a prompt

"If the user types 'I'm fine.', translate this as 'I'm fine.'"

"If the user types 'It's fine.', translate this to 'That's fine.'"

In this way, the system can properly translate the user's input message based on the context. The flow of the specific process in Example 3 is explained with reference to FIG. 15.

Step 1:

The user enters a message. The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." This input message becomes the input data for the next processing step.

Step 2:

The terminal sends a message to the server. The terminal sends the message entered by the user to the server using an HTTP request. In this case, the input data is the message entered by the user, and the output data is the message sent to the server.

Step 3:

The server receives the message. The server receives the message sent from the terminal and temporarily stores it in memory. The input data is the message sent from the terminal, and the output data is the message stored on the server.

Step 4:

The server inputs messages into the generative AI model. The server calls an API to input the received messages into the generative AI model. The input data is the message stored on the server, and the output data is the message passed to the generative AI model.

Step 5:

The generative AI model generates a translation based on the context. The generative AI model analyzes the context of the input message and generates the optimal translation. For example, for the message "I'm fine," it generates the translation "I'm fine." The input data is the message passed to the generative AI model, and the output data is the generated translation result.

Step 6:

The server receives the translation results. The server receives the translation results generated from the generative AI model and stores them in memory. The input data is the translation results returned from the generative AI model, and the output data is the translation results stored on the server.

Step 7:

The server sends the translation results to the terminal. The server sends the translation results to the terminal using an HTTP response. The input data is the translation results stored on the server, and the output data is the translation results sent to the terminal.

Step 8:

The terminal displays the translation result to the user. The terminal displays the translation result received from the server to the user. For example, the translation result "I'm fine" is displayed on the terminal screen. The input data is the translation result sent to the terminal, and the output data is the translation result displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

In conventional messaging apps and social media, accurate translations based on context were often not provided when users communicated in different languages. In addition, in virtual stores, users were not provided with appropriate translations when searching for product information or contacting customer support, resulting in a poor user experience.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in Language" button generating means arranged next to the message sending means, a means for automatically translating the message into a language when the "Send in Language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for providing an optimal translation based on context when a user searches for product information or makes an inquiry to customer support in a virtual store. This allows accurate translations based on context to be provided when users communicate in different languages, improving the user experience in the virtual store.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the message entered by the user and selects the translation that best suits that context.

A "virtual store" is a virtual store that offers products and services over the Internet.

"Means for searching product information" refers to a function that enables users to search for information about products and services offered in the virtual store.

"Means to contact customer support" refers to the functionality that allows users to report questions or issues to the virtual store's support team.

To implement this invention, the following system configuration is required. The system includes a message sending means, a language send button generating means, an automatic translation means, a sending means, a means for selecting the optimal translation based on the context, a means for searching for product information in a virtual store, and a means for making an inquiry to customer support.

The server receives the message entered by the user and uses a generative AI model to provide the best translation based on the context. Specifically, it uses Hugging Face's Transformers library to translate from English to Japanese. Once the user enters a message, it is sent to the server, which uses the generative AI model to translate it based on the context.

The terminal provides an interface for the user to input and send a message. The terminal includes a message sending means and a send in language button generating means, and allows the user to send a message in a language selected by the user. When the user presses the "send in language" button, the message is automatically translated and sent to other users via the sending means.

As a concrete example, suppose a user types "Can I return this item?" and presses the "Send in Japanese" button. In this case, the server uses the generative AI model to translate it into "Can I return this item?" and sends the translated message to other users via the sending means.

The same process also applies when users search for product information or contact customer support in the virtual store. For example, if a user types "I need help with my order" to contact the support team, the server translates it to "I need help with my order" and provides the appropriate support.

An example of a prompt to input to the generative AI model could be "Translate the following English sentence to Japanese considering the context: 'I need help with my order.'" Using this prompt, the server can provide the best translation based on the context.

The flow of the specific processing in application example 3 is explained using Figure 16.

Step 1:

The user types a message at the terminal. The user types a text message using the message sending means and presses the send button in the language. The input is the user's text message and the output is the typed message displayed at the terminal.

Step 2:

The terminal sends the entered message to the server. The terminal sends the entered message to the server along with send button information in the language pressed by the user. The input is the user's text message and the selected language, and the output is the message data sent to the server.

Step 3:

The server receives the message and performs a translation based on the context. The server analyzes the received message and uses a generative AI model to perform the optimal translation based on the context. The input is the message data sent to the server, and the output is the translated message. Specifically, the translation is performed using Hugging Face's Transformers library.

Step 4:

The server sends the translated message to the terminal. The server sends the translated message to the terminal and displays it to the user. The input is the translated message and the output is the translated message sent to the terminal.

Step 5:

The terminal displays the translated message and transmits it to other users through the transmission means. The terminal displays the translated message to the user and, after the user has confirmed it, transmits the message to other users through the transmission means. The input is the translated message and the output is the message transmitted to other users.

Step 6:

Checks the message received by other users. Other users check the received message and reply if necessary. The input is the received message and the output is the other users' checked message.

In this way, messages entered by users are optimally translated based on the context and accurately conveyed to other users.

Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

"Example 1"

As one embodiment of the present invention, a message translation system incorporating an emotion engine is provided. In this system, when a user types a message in a messenger app or SNS, the emotion engine recognizes the user's emotion. The emotion engine infers the user's emotion from, for example, the context of the user's message, the use of emojis, typing speed, etc. Then, the translation of the message is adjusted based on that emotion. For example, if the user types "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!".

"Example 2"

In another embodiment of the present invention, a system is provided that includes emotion recognition means for an emotion engine to recognize an emotion of a user, and emotion adjustment means for adjusting the translation of a message based on the recognized emotion. The emotion recognition means infers the emotion of the user from the context of the user's message, the use of emojis, typing speed, etc. The emotion adjustment means adjusts the translation of the message based on the recognized emotion. For example, if the user types "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

"Example 3"

Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. In this system, the emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. For example, if the user inputs "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!". On the other hand, if the user inputs "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

The process flow for each example is explained below.

"Example 1"

Step 1: The user types a message in a messenger app or on a social networking site.

Step 2: The emotion engine infers the user's emotion from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

"Example 2"

Step 1: User enters message.

Step 2: The emotion recognition tool infers the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion adjustment mechanism adjusts the translation of the message based on the recognized emotion.

"Example 3"

Step 1: User enters message.

Step 2: The emotion engine recognizes the user's emotions.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users translated and sent messages into other languages, the quality of the translation often lacked emotional expression, and there was a problem that the user's intentions and feelings were not conveyed accurately. In addition, it was inconvenient for users to translate manually, which was time-consuming.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a message sending means, a "send in specific language" button generating means, a means for automatically translating the message into a specific language when the "send in specific language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the emotion of the user, and a means for adjusting the translation based on the result of the emotion recognition means. This makes it possible to send a high-quality translated message that reflects the emotion of the user.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that generates a button that is placed next to the message input field and allows the user to send a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

The "translation adjustment means" is a function that adjusts the expression of a translated message based on the results of the emotion recognition means.

Form for implementing the invention

This invention is a system that places a "Send in specific language" button on the message sending screen of a messenger app or SNS, and when a user inputs a message and presses the "Send in specific language" button, the input message is automatically translated into the specific language and the translated message is sent. It also includes a function that recognizes the user's emotions and adjusts the translation based on those emotions by combining it with an emotion engine.

Hardware and software used

Hardware:

Device: The device on which the user types messages (smartphone, tablet, PC, etc.)

Server: A remote server for message translation and emotion recognition.

Software:

Messenger apps and social media applications

Emotion engine (e.g. EmotionAI)

Translation API (e.g. Google Translate API, DeepL API)

Data processing and data calculations

1. Get message:

The device retrieves the message entered by the user.

2. Emotion recognition:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

3. Message translation:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

4. Sending a translated message:

The device will then send the translated message.

Specific examples

When a user types "Today is the best day ever!" into a messenger app and presses the "Send in specific language" button, the process goes like this:

1. The user types, "Today is the best day ever!".

2. The user presses the "Send in specific language" button.

3. Your device will receive the message "Today is a great day!"

4. The server uses "EmotionAI" to recognize the emotion of joy from the message.

5. The server uses the Google Translate API to translate "Today is the best day ever!" to "Today is the best day ever!".

6. The device sends the message "Today is the best day ever!".

Example of a prompt

"Design a system that translates messages typed by users in a messenger app into a specific language and adjusts the message to the appropriate wording based on emotion. For example, if a user types, 'Today is the best day ever!', the emotion engine should recognize joy and translate the message to, 'Today is the best day ever!'"

In this way, a system is realized that appropriately translates and sends messages entered by users based on emotions.

The flow of the identification process in Example 1 is explained using Figure 17.

Step 1:

The user enters a message into the message input field of a messenger app or social networking site.

Input: User types "Today is the best day ever!"

Specific action: The user types a message using a keyboard or touchscreen.

Output: "Today is the best day ever!" is displayed in the message input field.

Step 2:

The user presses the "Send in specific language" button located next to the message input field.

Input: User clicks the "Submit in specific language" button.

Specific action: The user presses a button using a mouse or touch screen.

Output: An event occurs when the button is pressed.

Step 3:

The device retrieves the message entered by the user.

Input: The event of a button being pressed and the input message "Today is the best day ever!".

Specific operation: The device reads text data from the message input field.

Output: The retrieved message "Today is the best day ever!" is stored in memory.

Step 4:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Input: Retrieved message: "Today is the best day ever!".

What it does: The server uses an emotion engine (e.g. EmotionAI) to analyze the message context, detect emojis, and analyze typing speed.

Output: The emotion engine recognizes the user's emotion as "joy".

Step 5:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

Input: Emotion engine result "Joy" and original message "Today is a great day!".

Specific operation: The server uses a translation API (e.g. Google Translate API) to perform translation that takes emotional expressions into account.

Output: The translated message "Today is the best day ever!".

Step 6:

The device will then send the translated message.

Input: Translated message: "Today is the best day ever!".

Specific operation: The device uses the message sending function to send the translated message.

Output: The sent message "Today is the best day ever!" will appear in the recipient's message inbox.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

When users send messages in different languages on traditional messaging apps and social media, the quality of the translation often does not accurately reflect their emotions, lowering the quality of communication. In addition, because the translation does not take into account the user's emotions, there is a risk of misunderstandings and discomfort.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means. In this invention, the server includes a message sending means in a messenger app or SNS, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion analysis means for analyzing the user's emotions, and a means for adjusting the translation based on the emotion analysis means. This enables a natural translation that takes the user's emotions into account.

"Messenger apps and social networking sites" are software applications that allow users to send and receive text messages, images, videos, etc.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

"Means for generating a send button in XX language" is a function that generates a button that allows a user to send a message in a specific language.

"Means for automatic translation" refers to a function that automatically translates a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to other users.

"Emotion analysis means" refers to a function that analyzes a user's emotions from messages entered by the user and other information.

The "means for adjusting the translation" refers to a function for adjusting the translated message based on the emotional information obtained by the emotional analysis means.

To implement this invention, it is necessary to build a system that takes emotions into account when a user sends a message in a messenger app or on a social networking site. This system includes the following main components:

1. Means of sending messages

It provides an interface for users to type and send messages. This can be a messaging app or social networking application that runs on a device such as a smartphone or computer.

2. How to generate a "Send in XX language" button

Creates a "Send in XXX" button that is placed next to the message sending method. This button allows the user to send a message in a specific language. It is automatically selected from the available languages based on the user's preferences.

3. Means of automatic translation

When a user presses the "Send in XXX language" button, the entered message is automatically translated into the specified language. This function is achieved using a generative AI model. Specifically, a translation model using the Transformers library is used.

4. How to send automatically translated messages

Send the translated message to other users. This feature will also be implemented as part of a messaging app or social networking application.

5. Sentiment analysis methods

Analyze user sentiment from messages entered by users and other information. This function is achieved using a generative AI model. Specifically, a sentiment analysis model using the Transformers library is used.

6. Ways to adjust translations

Adjust the translated message based on the emotional information obtained by the emotion analysis means. For example, if positive emotions are detected, change the translated message to a more positive expression.

Hardware and software used

Hardware: servers (cloud servers or on-premise servers), smartphones, computers

Software: Python, Flask, Transformers library

Specific examples

When a user types "Today is the best day ever!" and presses the "Send in English" button, the sentiment analyzer recognizes the joy and the message is translated and sent as "Today is the best day ever!".

Example of a prompt

"Today is the best day!"

The flow of the specific processing in application example 1 is explained using Figure 18.

Step 1:

The user opens a messenger app or social networking application and types a message. The typed message is saved in text format on the device.

Step 2:

The user presses the "Send in XXX language" button. This action causes the device to send the entered message to the server. The data sent includes the message text and the user's selected language.

Step 3:

The server passes the received message text to a sentiment analyzer, which uses a generative AI model to analyze the sentiment of the message. The input is the message text and the output is a sentiment label (e.g. positive, negative, neutral).

Step 4:

The server passes the message text to the translation means based on the emotion label obtained from the emotion analysis means. The translation means translates the message into the specified language using a generative AI model. The input is the message text and the emotion label, and the output is the translated message text.

Step 5:

The server adjusts the translated message text based on the emotion label. For example, if a positive emotion is detected, it changes the translated message to a more positive expression. The input is the translated message text and the emotion label, and the output is the adjusted message text.

Step 6:

The server sends the adjusted message text to the terminal. The terminal displays the received message and sends it to other users. The input is the adjusted message text, and the output is the displayed and sent message.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

In conventional messaging apps and social media, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, because the translation was done without taking into account the user's feelings, there was a risk that unintended nuances would be conveyed. This led to a problem of a decline in the quality of communication.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the user's emotion, and an emotion adjustment means for adjusting the translation of the message based on the recognized emotion. This makes it possible to automatically select a language frequently used by the user and provide an appropriate translation according to the emotion.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

The "means for generating a send button in XX language" is a function that automatically selects an appropriate language from available languages based on the user's settings, and generates a button for sending a message in that language.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

"Emotion adjustment means" is a function that adjusts the translation of a message based on the recognized emotions of the user.

This invention is a system that reduces the effort required for users to send messages in different languages and provides appropriate translations according to emotions. A specific embodiment of this system is described below.

Hardware and software used

Server: Responsible for data processing and storage. Specifically, it uses cloud services (e.g. AWS (registered trademark), Google Cloud Platform).

Device: The device used by the user. This includes smartphones, tablets, PCs, etc.

Generative AI model: A model for performing natural language processing. For example, OpenAI's GPT-3 or GPT-4 (registered trademark) are used.

Emotion engine: An engine for recognizing user emotions. For example, using IBM Watson's emotion analysis API.

System processing flow

1. User language settings

Users select the language they frequently use in the application settings screen.

The device sends the selected language information to the server.

The server stores the received language information in a database.

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

2. Create a language selection button

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

3. Enter your message

The user enters text into the message input field.

The device sends the entered message to the server in real time.

What it does: When a user types "Today is the worst day...", the text is instantly sent to the server.

4. Emotion Recognition

The server sends the received message to the emotion engine.

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

The server receives the results from the emotion engine and stores the emotion information.

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

5. Translation adjustments

The server sends a translation request to the generative AI model based on the recognized emotion.

The generative AI model generates appropriate translations based on emotions.

The server sends the generated translation to the device.

Specific operation: The generative AI model generates the translation "Today is the worst day..." and the server sends it to the device.

6. Sending a message

The user presses the "Send in French" button.

The device sends the translated message to the server.

The server receives the message and sends it to the specified recipient.

Specific operation: When the user presses the "Send in French" button, the device sends the message "Aujourd'hui est le pire jour..." to the server, which then sends it to the recipient.

Example of a prompt

"Please explain the function that allows users to set their frequently used language and automatically generate the submit button in that language on subsequent visits."

"Please explain the functionality that recognizes user emotions and adjusts the translation of the message based on the recognized emotion."

To improve user convenience, the system automatically selects frequently used languages and provides appropriate translations according to sentiment.

The flow of the identification process in Example 2 is explained using Figure 19.

Step 1:

Users select the language they frequently use in the application settings screen.

Input: The language selected by the user in the settings screen (e.g. French)

Output: Selected language information

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

Step 2:

The device sends the selected language information to the server.

Enter: Selected language information

Output: Language information sent to the server

Specific operation: The device sends the user's selected language information to the server.

Step 3:

The server stores the received language information in a database.

Input: Language information sent to the server

Output: Language information stored in the database

Specific operation: The server stores the language information it receives in the database.

Step 4:

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Input: Language information stored in the database

Output: Submit button information in generated language

Specific behavior: The server retrieves language information from the database and generates information for the "Submit in French" button.

Step 5:

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Input: Submit button information for generated language

Output: A submit button displayed in the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

Step 6:

The user enters text into the message input field.

Input: A message typed by the user (e.g., "Today is the worst day...")

Output: The message entered

Specific action: User types, "Today is the worst day..."

Step 7:

The device sends the entered message to the server in real time.

Input: Message entered

Output: Message sent to server

Specific operation: The device sends the entered message to the server.

Step 8:

The server sends the received message to the emotion engine.

Input: Message sent to server

Output: Message sent to emotion engine

Specific operation: The server sends the received message to the emotion engine.

Step 9:

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

Input: Message sent to emotion engine

Output: Inferred emotion information (e.g. sadness)

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

Step 10:

The server receives the results from the emotion engine and stores the emotion information.

Input: Inferred emotion information

Output: Stored emotion information

Specific operation: The server receives emotion information from the emotion engine and stores it in the database.

Step 11:

The server sends a translation request to the generative AI model based on the recognized emotion.

Input: Stored emotion information, user message

Output: Translation request sent to generative AI model

Specific operation: The server sends emotion information and the user's message to the generative AI model.

Step 12:

The generative AI model generates appropriate translations based on emotions.

Input: Translation request sent to generative AI model

Output: Generated translation (e.g. "Today is the worst day...")

Specific behavior: The generative AI model generates the translation "Today is the worst day..."

Step 13:

The server sends the generated translation to the device.

Input: Generated translation

Output: Translation sent to device

Specific operation: The server sends the generated translation to the device.

Step 14:

The user presses the "Send in French" button.

Input: User operation

Output: Send button press information

Specific action: The user presses the "Send in French" button.

Step 15:

The device sends the translated message to the server.

Input: Send button press information, generated translation

Output: The translated message sent to the server

Specific action: The device sends the message "Aujourd'hui est le pire jour..." to the server.

Step 16:

The server receives the message and sends it to the specified recipient.

Input: Translation message sent to server

Output: Message sent to recipient

Specific operation: The server sends the translated message to the recipient.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Existing messenger apps and SNS lack the ability to automatically select the language frequently used by the user or adjust the translation of messages based on the user's emotions, limiting the user experience. There is also a demand for more natural and appropriate communication by recognizing the user's emotions and adjusting the translation based on them. Furthermore, content distribution services also face the challenge of improving the viewing experience by adjusting subtitles and audio translations based on the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means.

In this invention, the server includes a message sending means for a messenger app or SNS, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing a user's emotion, an emotion adjustment means for adjusting the translation of the message based on the recognized emotion, a language selection means for automatically selecting a language based on the user's settings and past usage history, and a translation adjustment means for adjusting the translation of subtitles and audio based on the user's emotion. This makes it possible to automatically select a language frequently used by the user and adjust the translation of messages and content based on the user's emotion.

"Message sending means" refers to an interface that allows users to input and send messages.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings and usage history.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" refers to technology for recognizing emotions from user input, facial expressions, voice, etc.

"Emotion adjustment means" is a function that adjusts the translation or display of a message based on the recognized emotion.

"Language selection means" is a function that automatically selects the most appropriate language based on the user's settings and past usage history.

"Translation adjustment means" is a function that adjusts the translation of subtitles and audio based on the user's emotions.

The following system configuration is described as a form for implementing this invention.

System configuration

This system includes a means for sending messages in messenger apps and SNS, a means for generating send buttons in a certain language, an automatic translation means, an emotion recognition means, an emotion adjustment means, a language selection means, and a translation adjustment means.

Method of sending message

An interface that allows users to input and send messages. It is implemented as an application on a smartphone or PC.

How to generate a send button in XX language

This function automatically generates buttons for sending messages in a specific language based on the user's settings and usage history. It automatically selects the language the user frequently uses and displays it as a button.

Automatic translation methods

This function automatically translates messages entered by users into a specified language. It is implemented using a translation API such as Google Translator.

Emotion recognition means

This is a technology for recognizing emotions from user input, facial expressions, voice, etc. It uses software such as OpenCV and EmotionRecognizer to analyze data from the camera and microphone.

Methods of emotion regulation

This feature adjusts the translation and display of messages based on the recognized emotion. For example, if the user has a sad expression, the translated message will be adjusted accordingly.

Language selection method

This function automatically selects the most suitable language based on the user's settings and past usage history. Content from the next time onwards will also be automatically selected based on the user's viewing history and settings information.

Translation adjustment methods

This feature adjusts subtitle and audio translations based on the user's emotions. For example, if the user looks sad, the subtitle translation will be adjusted accordingly.

Program processing explanation

The server captures data from the camera and microphone and recognizes the user's emotions using OpenCV and EmotionRecognizer. Based on the recognized emotions, it translates the message using a translation API such as Google Translator and displays the message adjusted by the emotion adjustment means. Based on the user's settings and past usage history, the language selection means automatically selects the most suitable language.

Specific examples

If a user frequently speaks French, the application will automatically provide content in French. And if the user has a sad expression, the subtitle translation will adjust accordingly.

Example of a prompt

Develop a smartphone application that automatically selects the language that the user frequently uses and uses an emotion engine to recognize the user's emotions and adjust the translation accordingly. For example, if the user frequently uses French, the application automatically provides content in French. Also, if the user has a sad expression, the subtitle translation will be adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

The flow of the specific processing in application example 2 is explained using Figure 20.

Step 1:

The server captures the user's video and audio data from the device through the camera and microphone. The input is the user's video and audio data, and the output is the captured raw data. This data is used in subsequent processing steps.

Step 2:

The server analyzes the captured video and audio data using OpenCV and EmotionRecognizer to recognize the user's emotions. The input is the captured raw data, and the output is the recognized emotional information. Specifically, it analyzes the user's facial expressions and tone of voice, and classifies emotions into "happiness," "sadness," "anger," etc.

Step 3:

The server uses a language selection means to automatically select the most appropriate language based on the user's settings and past usage history. The input is the user's settings information and usage history, and the output is the selected language information. Specifically, the language that the user frequently uses is obtained from the database and applied to the next and subsequent content.

Step 4:

The user enters a message and presses the send button. The input is the message entered by the user, and the output is the event information that the send button has been pressed. Specifically, this includes the action of the user entering a message into a text box and pressing the "Send in XX language" button.

Step 5:

When the send button is pressed, the server uses a translation API such as Google Translator to automatically translate the entered message into the selected language. The input is the message entered by the user and the selected language information, and the output is the translated message. Specifically, the message and target language are sent to the API and the translation result is received.

Step 6:

The server adjusts the translated message based on the recognized emotion with an emotion adjustment means. The input is the translated message and the recognized emotion information, and the output is the adjusted message. Specifically, if the user is expressing a sad emotion, the translated message is adjusted to be more negative accordingly.

Step 7:

The server sends the adjusted message through the message sending means. The input is the adjusted message and the output is the sent message. Specifically, the server sends the adjusted message to the recipient and displays a notification of the completion of the sending on the user's interface.

Step 8:

The server adjusts the subtitle and audio translations in the content delivery service based on the user's emotions. The input is the user's emotional information and content data, and the output is the adjusted subtitles and audio. Specifically, if the user has a sad expression, the subtitle translation is adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

Conventional message translation systems perform simple translations without considering the context or emotions of the message entered by the user, which often results in inappropriate translations. In addition, there is a problem that the quality of communication declines because the translation cannot reflect the user's emotions. This creates an issue in that it becomes difficult to convey the exact meaning and emotions intended by the user.

The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "send in translation language" button generating means located next to the message sending means, a means for automatically translating the message into the translation language when the "send in translation language" button is pressed, a means for sending the automatically translated message, a context analysis means for selecting an optimal translation based on the context of a message input by a user, and an emotion analysis means for recognizing the user's emotion and adjusting the translation based on that emotion. This makes it possible to provide an optimal translation of a user's input message based on the context and emotion.

"Message sending means" is a function for sending messages entered by a user to other users.

The "means for generating a send button in a translated language" is a function for generating a button for sending a message in a translated language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified translation language.

"Context analysis means" is a function that analyzes the context of the message entered by the user and selects the most appropriate translation based on that context.

"Sentiment analysis means" is a function that recognizes the emotion of the message entered by the user and adjusts the translation based on that emotion.

"Transmission means" is a function for sending translated messages to other users.

"User settings" are settings that users make to customize system behavior, translation languages, etc.

"Translation language" is the language the user uses to translate the message.

Form for implementing the invention

This invention is a system that provides an optimal translation of a message entered by a user based on the context and emotion. A specific embodiment of this system is described below.

System configuration

The system mainly consists of the following components:

1. Means of sending messages

2. How to generate a send button in a translated language

3. Automatic translation methods

4. Contextual analysis methods

5. Sentiment analysis methods

6. Transmission method

Hardware and software used

The server uses the following hardware and software to receive, parse, translate, and send messages:

Server hardware: A server with a powerful processor and sufficient memory

Software: Python, NLTK library, Google Natural Language API

The device uses the following hardware and software to allow users to enter messages and display translation results:

Device hardware: smartphones, tablets, PCs, etc.

Software: Messenger apps, SNS apps

System operation

The user inputs a message into an input field on the terminal. For example, the user inputs "I'm fine." The terminal sends this message to the server. The server sends the received message to the context analysis means, which analyzes the context of the message. The context analysis means analyzes the context using, for example, Python's NLTK library, and translates the message "I'm fine." into "I'm fine."

The server then sends the translation to the sentiment analyzer, which uses Google's Natural Language API to analyze the sentiment of the message. For example, if the user types "Today is the best day ever!" and the sentiment analyzer recognizes joy, the translation is adjusted to "Today is the best day ever!".

Finally, the server sends the adjusted translation result to the terminal, and the terminal displays the translation result to the user. The user can check the translation result on the terminal screen.

Specific examples

As a concrete example, consider the case where a user types "I'm fine" into a terminal. This message is sent to the server, where the context analysis means translates it as "I'm fine." If the user then types "Today is the best day ever!", the emotion analysis means will recognize the joy, and the server will translate it as "Today is the best day ever!".

Example of a prompt:

If a user types "I'm fine," choose the appropriate translation based on the context and analyze the sentiment using sentiment analysis tools.

If a user types "Today is a great day!", use sentiment analysis to recognize the sentiment and choose the appropriate translation.

This system supports more natural and appropriate communication by providing an optimal translation of the user's input message based on the context and emotion. The flow of the specific process in Example 3 is explained with reference to FIG. 21.

Step 1:

The user types a message.

The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." The entered message is passed to the terminal's message sending means.

Step 2:

The device sends the message to the server.

The terminal sends the message entered by the user to the server. At this time, the message is sent as an HTTP request. The input is the user's message, and the output is an HTTP request to the server.

Step 3:

The server receives the message and sends it to the context analysis means.

The server sends the received message to the contextual analyzer, which analyzes the context using, for example, Python's NLTK library. The input is the user's message and the output is the data to the contextual analyzer.

Step 4:

The contextual analysis means analyzes the context of the message and selects the appropriate translation.

The contextual analysis means analyzes the context of the message and selects the appropriate translation. For example, the message "I'm fine." is translated as "I'm fine." The input is the user's message and the output is the translation result.

Step 5:

The server sends the translation results to the sentiment analysis means.

The server transmits the translation results obtained from the context analysis means to the sentiment analysis means. The sentiment analysis means analyzes sentiment using, for example, Google's (registered trademark) Natural Language API. The input is the translation result, and the output is data to the sentiment analysis means.

Step 6:

Sentiment analysis tools analyze the sentiment of the message and adjust the translation.

The sentiment analyzer analyzes the sentiment of the message and adjusts the translation. For example, if the message "Today is the best day ever!" is recognized as expressing joy, the translation is adjusted to "Today is the best day ever!". The input is the translation and the output is the adjusted translation.

Step 7:

The server sends the final translation results to the device.

The server sends the final translation result obtained from the sentiment analysis means to the terminal. At this time, the translation result is sent as an HTTP response. The input is the adjusted translation result, and the output is the HTTP response to the terminal.

Step 8:

The device displays the translation results to the user.

The terminal displays the translation results received from the server to the user. The user can check the translation results on the terminal screen. The input is the translation result from the server, and the output is what is displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

Conventional message translation systems perform translation without considering the context or emotion of the message entered by the user, resulting in unnatural translations or failure to accurately convey the user's intent. In addition, since translations cannot reflect emotion, it is difficult to properly convey the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in language" button generating means located next to the message sending means, a means for automatically translating the message into a language when the "Send in language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for recognizing the user's emotion using an emotion engine and adjusting the translation based on that emotion. This enables a natural and appropriate translation that takes into account the context and emotion of the message input by the user.

"Message sending means" refers to an interface that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Means for automatic translation" refers to a function that automatically translates an input message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the input message and selects the translation that best suits that context.

The "emotion engine" is a system that recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

"Means for adjusting a translation based on emotion" refers to a function for adjusting a translated message based on a user's emotion as recognized by an emotion engine.

A system for implementing the present invention includes a message sending means, a language send button generating means, a means for automatic translation, a means for sending the automatically translated message, a means for selecting an optimal translation based on context, an emotion engine, and a means for adjusting the translation based on emotion.

System configuration

The server uses the following hardware and software:

Hardware: The server uses a computer system with a high-performance processor and sufficient memory. Specifically, Intel Xeon processors and AMD EPYC processors are suitable.

Software: The server uses the Python programming language and the transformers natural language processing library. It also uses the nltk library for sentiment analysis.

Processing flow

1. Message sending means: Provides an interface for users to enter text messages. This is an application that runs on a mobile device such as a smartphone or tablet.

2. Send in language button generator: Generates a button to send a message in the language selected by the user. This button is automatically selected based on the user's settings.

3. Means of automatic translation: Automatically translate messages entered by users into a specified language. This translation is done using a generative AI model.

4. How to send an automatically translated message: Send an automatically translated message to other users.

5. A means to select the best translation based on context: Analyze the context of the message entered by the user and select the translation that best suits that context.

6. Emotion engine: Recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

7. Means to tailor translation based on emotion: Adjust the translated message based on the user's emotion as recognized by the emotion engine.

Specific examples

For example, if a user is watching a movie and a character says, "I'm so happy today!", the emotion engine will recognize the positive emotion and adjust the translation to "I'm so happy today!".

Example of a prompt to input to the generative AI model:

"Translate the following text to Japanese and adjust the translation based on the detected emotion: 'I'm so happy today!'"

In this way, the user's viewing experience can be enriched.

The flow of the specific processing in application example 3 is explained using Figure 22.

Step 1:

The user enters a message on the terminal. The entered message is sent to the server in text format. The input data is the text message entered by the user.

Step 2:

The server analyzes the received messages and performs natural language processing (NLP) to understand the context. For this process, it uses the transformers library. The input data is the text message entered by the user, and the output data is the analysis result including contextual information.

Step 3:

The server uses a generative AI model to generate an optimal translation based on the analysis results. Specifically, it uses a translation model from the transformers library to translate the message into the specified language. The input data is the analysis results including contextual information, and the output data is the translated text message.

Step 4:

The server passes the translated message to an emotion engine to recognize the user's emotion. The emotion engine uses the nltk library. The input data is the translated text message, and the output data is the emotion label (e.g. positive, negative).

Step 5:

The server adjusts the translated message based on the emotion label. For example, for positive emotion it adds "Da yo!" to the translated message, and for negative emotion it adds "Da...". The input data are the emotion label and the translated text message, and the output data is the adjusted translated message.

Step 6:

The server sends the adjusted translation message to the terminal. The terminal displays the received message to the user. The input data is the adjusted translation message, and the output data is the text message displayed to the user.

Step 7:

The user checks the displayed message and replies if necessary. The reply message is sent again through the process from step 1. The input data is the reply message entered by the user, and the output data is the translated and adjusted reply message.

The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input for the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

Another example of generative AI is Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>).

In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the smart glasses 214.

[Third embodiment]

Figure 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

As shown in FIG. 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is performed in a secure state.

Figure 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Figure 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. Data generation model 58 and emotion identification model 59 are used by the identification processing unit 290.

In the headset terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12.

"Example 1"

As one embodiment of the present invention, a "Send in English" button is placed next to the message input field on the message sending screen of a messenger app or SNS. When a user inputs a message and presses the "Send in English" button, the input message is automatically translated into English and the translated message is sent.

"Example 2"

Furthermore, we provide a function that automatically selects the language of the "Send in ____" button from the available languages based on the user's settings. For example, if the user frequently communicates with people who speak French, the "Send in French" button will be automatically generated based on the user's settings.

"Example 3"

The service also provides a function that selects the most appropriate translation based on the context of the message entered by the user. For example, if the user enters "I'm fine," this will be translated as "I'm fine." However, if the user enters "It's fine," this will be translated as "It's fine." In this way, the translation method for the same "fine" changes depending on the context.

The process flow for each example is explained below.

"Example 1"

Step 1: The user opens the message sending screen of a messenger app or SNS.

Step 2: Make sure the "Send in English" button is located next to the message input field.

Step 3: The user enters a message and presses the "Send in English" button.

Step 4: The system will automatically translate the message you entered into English.

Step 5: The system sends the translated message.

"Example 2"

Step 1: The user opens the settings screen of the messenger app or SNS.

Step 2: The user selects the language from the available options for the "Send in" button. Step 3: The user saves the settings and returns to the message sending screen.

Step 4: Make sure there is a "Send in XXX" button in the user's chosen language next to the message input field.

"Example 3"

Step 1: User enters message.

Step 2: The system selects the best translation based on the context of the message entered by the user.

Step 3: The system displays the selected translation to the user.

Step 4: The user presses the "Send in XXX language" button and the system sends the selected translation.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messenger apps and SNS, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, the translation was often inaccurate and did not provide an appropriate translation based on the context, which could impair smooth communication. To solve these problems, a system was needed that would allow users to easily translate and send messages in a specific language.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in specific language" button generating means disposed next to the message sending means, a means for automatically translating the message into a specific language when the "Send in specific language" button is pressed, a means for sending the automatically translated message, a means for inputting the message into a generative AI model as a prompt sentence, a means for the generative AI model to translate the message, and a means for sending the translated message to a destination. This enables a user to easily translate and send a message into a specific language.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that is placed next to the message sending means and generates a button for sending a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

A "generative AI model" is an artificial intelligence model for performing natural language processing and capable of translating input text into other languages.

A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

"Means for sending translated messages" refers to a function for sending messages translated by the automatic translation means to a specified destination.

"Optimal translation based on context" refers to providing the most appropriate translation by taking into account the content and intent of the message entered by the user.

This invention is a system that allows users to easily translate and send messages into a specific language in messenger apps and SNS. A specific embodiment of this system is described below.

First, a user opens the message sending screen of a messenger app or SNS and enters a message in the message input field. For example, the user might enter "Hello, how are you?". Next, the user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in an appropriate format. The server inputs the received message into a generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, it sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

The generative AI model receives the prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" to "Hello, how are you?". The server sends the translated message received from the generative AI model to the device. At this time, the translated message is sent to the device in the appropriate format.

The device then sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend. In this way, a message entered by the user in Japanese is automatically translated into a specific language and sent.

As a concrete example, consider a case where a user wants to send a message to a friend saying "Hello, how are you?" The user enters "Hello, how are you?" in the message input field and presses the "Send in specific language" button. The system translates this message into "Hello, how are you?" and sends it to the friend.

Example of a prompt to input to a generative AI model:

"Please translate 'Hello, how are you?' into English."

This system allows users to easily translate and send messages into a specific language. The hardware used includes the user's device (smartphone, tablet, PC, etc.) and a server. The software used includes messenger apps, SNS applications, and generative AI models (e.g., GPT-4 (registered trademark)).

The flow of the identification process in Example 1 is explained using Figure 11.

Step 1:

The user enters a message in the message input field.

Enter: "Hello, how are you?"

Output: Input message "Hello, how are you?"

Specific actions: The user opens the message sending screen of a messenger app or SNS and types "Hello, how are you?" in the message input field.

Step 2:

The user presses the "Send in specific language" button.

Input: User presses the "Send in specific language" button

Output: Event that the send button was pressed

Specific behavior: The user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

Step 3:

The device sends the entered message to the server.

Input: An event that inputs the message "Hello, how are you?" and presses the send button

Output: Message sent to server: "Hello, how are you?"

Specific operation: The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in the appropriate format.

Step 4:

The server inputs the message into the generation AI model as a prompt.

Input: Message sent to server: "Hello, how are you?"

Output: Prompt sent to the generative AI model: "Please translate 'Hello, how are you?' into English."

Specific operation: The server inputs the received message into the generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, the server sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

Step 5:

A generative AI model translates the message into English.

Input: Prompt text: "Please translate 'Hello, how are you?' into English."

Output: The translated message "Hello, how are you?"

Specific behavior: The generative AI model receives a prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" into "Hello, how are you?".

Step 6:

The server sends the translated message to the device.

Input: translated message "Hello, how are you?"

Output: The translated message "Hello, how are you?" sent to the terminal.

Specific operation: The server sends the translated message received from the generative AI model to the terminal. At this time, the translated message is sent to the terminal in an appropriate format.

Step 7:

Your device will then send the translated message to the recipient.

Input: The translated message sent to the device: "Hello, how are you?"

Output: The message "Hello, how are you?" sent to the destination.

Specific operation: The device sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

With the current trend of globalization, communication with foreign customers has become important in brick-and-mortar stores. However, the language barrier makes it difficult for store staff to communicate smoothly with foreign customers. To solve this problem, real-time language translation is necessary, but current technology is not sufficient.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a voice input means, a means for converting voice acquired by the voice input means into text, a means for translating the text into XXX language, and a means for vocally outputting the translated text. This enables smooth real-time communication between store staff and foreign customers in physical stores.

"Message sending means" refers to an interface that allows a user to input and send text messages.

The "means for generating a send button in XX language" is a function that generates a button for translating and sending a message into a language selected by the user.

"Means for automatic translation" refers to a function for automatically translating an input text message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to the other party.

"Voice input means" is an interface for capturing the user's voice and acquiring it as digital data.

"Means for converting voice to text" refers to a function for converting acquired voice data into text data.

"Means of translating text into XX language" is a function for translating text data into a specified language.

"Means for outputting translated text as audio" refers to a function for playing back translated text as audio.

To implement this invention, the following system configuration and program are required.

First, the server provides a message sending means, which is an interface that allows the user to input and send a text message. Next, the server provides a "Send in XX language" button generating means, which is a function that generates a button for translating and sending a message into a language selected by the user.

When a user presses the "Send in XXX language" button, the server uses an automatic translation means to automatically translate the entered text message into the specified language. This translated message is then sent to the recipient by a means for sending an automatically translated message.

Furthermore, the server provides a voice input means, which is an interface for capturing the user's voice and acquiring it as digital data. The acquired voice data is converted into text data by a voice-to-text conversion means.

The converted text data is translated into a specified language by a means for translating text into a specific language. The translated text is played as audio by a means for outputting the translated text as audio.

To realize this system, the following hardware and software are used:

Hardware: Smart glasses (capable of voice input and output)

Software:

speech_recognition library: convert speech to text

googletrans library: translate text

pyttsx3 library: convert text to speech

As a concrete example, when a store clerk says, "Where is this product located?", the voice is captured by the microphone of the smart glasses. The voice data is converted to text using the speech_recognition library, and the text is translated into English using the googletrans library. The translated text is converted to speech using the pyttsx3 library, and "Where is this product located?" is played from the speaker of the smart glasses.

Example of a prompt to input to a generative AI model:

When a user says "Where is this product located?", convert that speech to text, translate it into English, display "Where is this product located?" and play it aloud.

The flow of the specific processing in application example 1 is explained using Figure 12.

Step 1:

The user speaks into the smart glasses. The microphone in the smart glasses captures the voice and obtains it as voice data. This voice data becomes the input.

Step 2:

The voice data acquired by the device (smart glasses) is converted into text data using the speech_recognition library. The voice data is analyzed and corresponding text data is generated. This text data becomes the output.

Step 3:

Translates text data generated by the device into a specified language (e.g. English) using the googletrans library. Takes text data as input and generates translated text data. This translated text data is the output.

Step 4:

The device converts the translated text data into speech data using the pyttsx3 library. It takes the translated text data as input and generates the corresponding speech data. This speech data becomes the output.

Step 5:

The device then plays the generated voice data through the smart glasses' speakers, allowing the user to listen to the translated audio.

Specifically, when a user says "Where is this product located?", the voice is captured by the microphone in the smart glasses. The voice data is converted into text data saying "Where is this product located?" using the speech_recognition library. The text data is translated into English as "Where is this product located?" using the googletrans library. The translated text data is converted into voice data using the pyttsx3 library, and "Where is this product located?" is played from the speaker in the smart glasses.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messaging apps and SNS, when users wanted to send a message in a different language, they had to translate it manually, which was a time-consuming process. In addition, there was no function to automatically select frequently used languages, so users had to select the language every time, which was inconvenient. Furthermore, the quality of the translation was not consistent, so the translation did not always match the context of the message.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a means for acquiring user setting information, a means for sending a prompt sentence to the generative AI model based on the acquired setting information, a means for generating a "Send in XXX language" button based on a response from the generative AI model, a means for displaying the generated "Send in XXX language" button in a user interface, and a means for sending a message when the user clicks the "Send in XXX language" button. This makes it possible to automatically select a language frequently used by the user and perform an appropriate translation.

"User settings information" refers to the individual language and other customization information that a user sets within the system.

A "generative AI model" is a model designed to perform specific tasks using artificial intelligence. In this case, its role is to generate prompts based on user settings and generate appropriate language selection buttons.

A "prompt sentence" refers to an input sentence that gives specific instructions or asks a question to a generative AI model.

"Send in XXX language button" refers to a button on the interface that allows a user to send a message in a specific language of their choice.

"User interface" refers to the screens and operating means that allow users to interact with the system.

"Means of sending messages" refers to the functionality for sending messages entered by the user in the selected language.

This invention relates to a system for messenger apps and SNS that automatically selects a language that a user frequently uses and performs appropriate translation. A specific embodiment of this system is described below.

Server processing

The server retrieves the user's settings information from a database. Specifically, it uses a database management system such as MySQL (registered trademark) to retrieve information on the languages frequently used by the user. For example, it executes an SQL query that retrieves the corresponding language settings using the user ID as a key.

The server then sends a prompt to a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) based on the retrieved user settings. The prompt includes instructions to generate a "Send in XXX language" button based on the user's frequently used language.

Example of a prompt:

"Based on the user's preferences, select the frequently used language and generate a corresponding submit button. For example, if the user selects French, generate a 'Submit in French' button."

The server that receives the response from the generative AI model generates the data to display in the user interface. Specifically, it generates HTML and JavaScript (registered trademark) code and creates buttons that correspond to the language selected by the user.

Terminal processing

The terminal receives the data sent from the server and reflects it in the user interface. Specifically, it dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React.

User operations

The user selects the languages they use most frequently in the settings screen. For example, if the user selects French, a "Send in French" button will be automatically generated from next time. The user can click this button to send messages in the selected language.

Specific examples

For example, if a user selects "French" in the settings screen, the "Send in French" button will be automatically generated next time. When the user clicks this button, the message will be sent in French.

In this way, it is possible to automatically select the language that the user frequently uses and provide an appropriate translation. This saves the user the trouble of having to manually select the language, allowing for smoother communication.

The flow of the identification process in Example 2 is explained using Figure 13.

Step 1:

Get user settings information

The server retrieves the user's preference information from a database. As input, a user ID is given. The server uses a database management system such as MySQL (registered trademark) to retrieve information about the user's frequently used languages. Specifically, it executes an SQL query using the user ID as a key to retrieve the corresponding language preference. As output, the user's preference information (e.g., French) is obtained.

Step 2:

Generating and sending prompts

The server sends a prompt to the generative AI model based on the acquired user setting information. The user's setting information is given as input. The prompt includes an instruction to generate a "Send in XX language" button based on the language the user frequently uses. An example of a specific prompt is "Based on the user's settings, please select the language that is frequently used and generate a corresponding send button. For example, if the user selects French, please generate a 'Send in French' button." The output is a response from the generative AI model.

Step 3:

Generate language selection button

The server generates a "Send in XXX language" button based on the response from the generative AI model. The response from the generative AI model is given as input. The server generates HTML and JavaScript (registered trademark) code to create a button that corresponds to the language selected by the user. The output is the data for the generated "Send in XXX language" button.

Step 4:

Display language selection button

The terminal receives the data sent from the server and reflects it in the user interface. As input, it is given the data for the "Send in XX language" button sent from the server. The terminal dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React. As output, it obtains the button displayed in the user interface.

Step 5:

Send a message

The user clicks the generated "Send in French" button. As input, the user's click event is given. When the click event occurs, a message is sent in the selected language. Specifically, a JavaScript® event listener is used to catch the button click event and process the message sending. As output, the message sent in the selected language is obtained.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messenger apps and SNS, when users communicate in different languages, they have to translate manually, which is inefficient. In addition, there was a lack of functionality to automatically learn frequently used languages and send messages in the appropriate language, which made it inconvenient for users.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means. In this invention, the server includes a message sending means, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a means for acquiring user setting information, a means for learning frequently used languages based on the setting information, a means for automatically generating the "Send in XXX language" button based on the learned languages, a means for translating the message in real time, and a means for sending the translated message. This makes it possible to automatically learn languages frequently used by the user and send messages in the appropriate language.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending translated messages to other users.

"Means for acquiring user setting information" refers to a function for acquiring the language and other setting information previously set by the user.

"Means for learning frequently used languages" refers to a function for learning the languages that a user frequently uses based on the user's past message history and settings information.

"Means of real-time translation" refers to a function that translates a message into a specified language in real time as the user types the message.

The system for implementing this invention is composed of a server and a user terminal. The server includes a message sending means, a "send in XX language" button generating means, an automatic translation means, a sending means, a means for acquiring user setting information, a means for learning frequently used languages, and a means for translating in real time.

Program processing explanation

Hardware to be used

Server: Any cloud server (e.g. AWS (registered trademark), Google Cloud)

Client: Smartphone (iOS or ANDROID (registered trademark))

Software to be used

Framework: Flask (Python)

Translation API: Googletrans (Python wrapper for Google Translate API)

Data processing and data calculations

1. How to get user settings information:

The server retrieves the user's pre-selected language and other preferences. This information is used to learn the user's frequently used languages based on their past message history and preferences.

2. Ways to learn frequently used languages:

The server learns which languages the user frequently uses based on the user's past message history and preferences. This allows it to identify the language the user uses most often and automatically generate a button to send messages in that language.

3. How to generate the "Send in ____ language" button:

The server automatically generates a button to send a message in a specific language based on the user's preferences. This button is displayed when the user types a message.

4. Ways to translate in real time:

As users type their messages, the server translates them into the specified language in real time, allowing users to see the translated message instantly.

5. Automatic translation methods:

When a user presses the "Send in XXX language" button, the server automatically translates the message into the specified language. This translation is done using a translation API such as GoogleTrans.

6. Transmission method:

The translated messages are then sent to other users via the server, allowing users who speak different languages to communicate smoothly.

Specific examples

For example, if the user is "user1" and sends the message "Hello, how are you?", the server will translate this message into French and return it as "Bonjour, comment &ccedil;a va?".

Example of a prompt

User ID: user1

Message: Hello, how are you?

When you send this prompt to the server, you will get a response like this:

{

"original_message": "Hello, how are you?",

"translated_message": "Bonjour, comment &ccedil;a va?",

"language": "fr"

}

In this way, a system can be created that automatically selects a language based on the user's settings and then translates and sends the message.

The flow of the specific processing in application example 2 is explained using Figure 14.

Step 1:

The user inputs a message. The user inputs a text message using the smartphone's message sending means. This input message is sent to the server.

Step 2:

The server retrieves the user's preferences. The server retrieves the user's preferences from a database and identifies the user's frequently used languages. This preference information includes languages the user has used in the past and languages that have been preset by the user.

Step 3:

The server learns which languages are used most frequently. Based on the configuration information obtained, the server learns which languages are used most frequently by users. Based on the results of this learning, it generates a "Send in XXX" button for sending messages in a specific language.

Step 4:

The server generates a "Send in XX language" button. Based on the learning results, the server automatically generates a button for sending messages in the language the user frequently uses and displays it on the user's device.

Step 5:

The user presses the "Send in XXX" button. By pressing the generated "Send in XXX" button, the user instructs the message they typed to be translated into a specific language.

Step 6:

The server translates the message in real time. The server translates the message entered by the user into the specified language in real time. This translation uses a translation API such as Googletrans.

Step 7:

The server sends the translated message. The server returns the translated message to the user's device so that the user can review it. The server then sends the translated message to other users.

Step 8:

Other users receive the translated message. Other users receive and display the translated message sent from the server. This allows users who speak different languages to communicate smoothly.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messaging apps and SNS, it was difficult to provide appropriate translations based on the context when users sent messages. In particular, when the same word had different meanings depending on the context, it was difficult to select the appropriate translation.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a message sending means, a "send with translation" button generating means disposed next to the message sending means, a means for automatically translating the message when the "send with translation" button is pressed, a means for sending the automatically translated message, a means for receiving a message input by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to the user. This makes it possible to provide an optimal translation based on the context of the message input by the user.

"Message sending means" refers to a means for sending messages entered by a user to other users.

The "translation and send button generation means" is a means for generating a button that enables a user to translate and send a message.

"Means for automatic translation" refers to a means for automatically translating a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to means for sending translated messages to other users.

"Means for receiving messages entered by users" refers to the means by which the server receives messages entered by users.

"Means for inputting a message into a generative AI model" refers to means for inputting a received message into a generative AI model.

"Means by which a generative AI model generates a context-based translation" refers to the means by which a generative AI model analyzes the context of a message and generates an optimal translation.

"Means for receiving the generated translation results" refers to means for receiving the translation results generated from the generative AI model.

"Means for displaying the translation result to the user" refers to means for displaying the received translation result to the user.

This invention relates to a system that optimally translates a message entered by a user based on the context. This system includes a message sending means, a translation send button generating means, an automatic translation means, a means for sending the automatically translated message, a means for receiving a message entered by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to a user.

Hardware and software used

This system uses a server, a terminal, and a generative AI model. Specifically, the server receives messages, inputs them into the generative AI model, and receives and sends translation results. The terminal inputs messages from users and displays the translation results. For example, OpenAI's GPT-4 (registered trademark) is used as the generative AI model.

Data processing and data calculations

The server receives the message entered by the user on the device and inputs the message into the generative AI model. The generative AI model analyzes the context of the message and generates the optimal translation. The generated translation result is returned to the server, which then sends the result to the device. The device displays the translation result to the user.

Specific examples

As a concrete example, consider the case where a user types "I'm fine." In this case, the server uses a generative AI model to generate the translation "I'm fine." On the other hand, if the user types "It's fine.", the server generates the translation "It's fine."

Example of a prompt

"If the user types 'I'm fine.', translate this as 'I'm fine.'"

"If the user types 'It's fine.', translate this to 'That's fine.'"

In this way, the system can properly translate the user's input message based on the context. The flow of the specific process in Example 3 is explained with reference to FIG. 15.

Step 1:

The user enters a message. The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." This input message becomes the input data for the next processing step.

Step 2:

The terminal sends a message to the server. The terminal sends the message entered by the user to the server using an HTTP request. In this case, the input data is the message entered by the user, and the output data is the message sent to the server.

Step 3:

The server receives the message. The server receives the message sent from the terminal and temporarily stores it in memory. The input data is the message sent from the terminal, and the output data is the message stored on the server.

Step 4:

The server inputs messages into the generative AI model. The server calls an API to input the received messages into the generative AI model. The input data is the message stored on the server, and the output data is the message passed to the generative AI model.

Step 5:

The generative AI model generates a translation based on the context. The generative AI model analyzes the context of the input message and generates the optimal translation. For example, for the message "I'm fine," it generates the translation "I'm fine." The input data is the message passed to the generative AI model, and the output data is the generated translation result.

Step 6:

The server receives the translation results. The server receives the translation results generated from the generative AI model and stores them in memory. The input data is the translation results returned from the generative AI model, and the output data is the translation results stored on the server.

Step 7:

The server sends the translation results to the terminal. The server sends the translation results to the terminal using an HTTP response. The input data is the translation results stored on the server, and the output data is the translation results sent to the terminal.

Step 8:

The terminal displays the translation result to the user. The terminal displays the translation result received from the server to the user. For example, the translation result "I'm fine" is displayed on the terminal screen. The input data is the translation result sent to the terminal, and the output data is the translation result displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messaging apps and social media, accurate translations based on context were often not provided when users communicated in different languages. In addition, in virtual stores, users were not provided with appropriate translations when searching for product information or contacting customer support, resulting in a poor user experience.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in Language" button generating means arranged next to the message sending means, a means for automatically translating the message into a language when the "Send in Language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for providing an optimal translation based on context when a user searches for product information or makes an inquiry to customer support in a virtual store. This allows accurate translations based on context to be provided when users communicate in different languages, improving the user experience in the virtual store.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the message entered by the user and selects the translation that best suits that context.

A "virtual store" is a virtual store that offers products and services over the Internet.

"Means for searching product information" refers to a function that enables users to search for information about products and services offered in the virtual store.

"Means to contact customer support" refers to a feature that allows users to report questions or issues to the virtual store's support team.

To implement this invention, the following system configuration is required. The system includes a message sending means, a language send button generating means, an automatic translation means, a sending means, a means for selecting the optimal translation based on the context, a means for searching for product information in a virtual store, and a means for making an inquiry to customer support.

The server receives the message entered by the user and uses a generative AI model to provide the best translation based on the context. Specifically, it uses Hugging Face's Transformers library to translate from English to Japanese. Once the user enters a message, it is sent to the server, which uses the generative AI model to translate it based on the context.

The terminal provides an interface for the user to input and send a message. The terminal includes a message sending means and a send in language button generating means, and allows the user to send a message in a language selected by the user. When the user presses the "send in language" button, the message is automatically translated and sent to other users via the sending means.

As a concrete example, suppose a user types "Can I return this item?" and presses the "Send in Japanese" button. In this case, the server uses the generative AI model to translate it to "Can I return this item?" and sends the translated message to other users via the sending means.

The same process also applies when users search for product information or contact customer support in the virtual store. For example, if a user types "I need help with my order" to contact the support team, the server translates it to "I need help with my order" and provides the appropriate support.

An example of a prompt to input to the generative AI model could be "Translate the following English sentence to Japanese considering the context: 'I need help with my order.'" Using this prompt, the server can provide the best translation based on the context.

The flow of the specific processing in application example 3 is explained using Figure 16.

Step 1:

The user types a message at the terminal. The user types a text message using the message sending means and presses the send button in the language. The input is the user's text message and the output is the typed message displayed at the terminal.

Step 2:

The terminal sends the entered message to the server. The terminal sends the entered message to the server along with send button information in the language pressed by the user. The input is the user's text message and the selected language, and the output is the message data sent to the server.

Step 3:

The server receives the message and performs a translation based on the context. The server analyzes the received message and uses a generative AI model to perform the optimal translation based on the context. The input is the message data sent to the server, and the output is the translated message. Specifically, the translation is performed using Hugging Face's Transformers library.

Step 4:

The server sends the translated message to the terminal. The server sends the translated message to the terminal and displays it to the user. The input is the translated message and the output is the translated message sent to the terminal.

Step 5:

The terminal displays the translated message and transmits it to other users through the transmission means. The terminal displays the translated message to the user and, after the user has confirmed it, transmits the message to other users through the transmission means. The input is the translated message and the output is the message transmitted to other users.

Step 6:

Checks the message received by other users. Other users check the received message and reply if necessary. The input is the received message and the output is the other users' checked message.

In this way, messages entered by users are optimally translated based on the context and accurately conveyed to other users.

Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

"Example 1"

As one embodiment of the present invention, a message translation system incorporating an emotion engine is provided. In this system, when a user types a message in a messenger app or SNS, the emotion engine recognizes the user's emotion. The emotion engine infers the user's emotion from, for example, the context of the user's message, the use of emojis, typing speed, etc. Then, the translation of the message is adjusted based on that emotion. For example, if the user types "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!".

"Example 2"

In another embodiment of the present invention, a system is provided that includes emotion recognition means for an emotion engine to recognize an emotion of a user, and emotion adjustment means for adjusting the translation of a message based on the recognized emotion. The emotion recognition means infers the emotion of the user from the context of the user's message, the use of emojis, typing speed, etc. The emotion adjustment means adjusts the translation of the message based on the recognized emotion. For example, if the user types "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

"Example 3"

Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. In this system, the emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. For example, if the user inputs "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!". On the other hand, if the user inputs "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

The process flow for each example is explained below.

"Example 1"

Step 1: The user types a message in a messenger app or on a social networking site.

Step 2: The emotion engine infers the user's emotion from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

"Example 2"

Step 1: User enters message.

Step 2: The emotion recognition tool infers the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion adjustment mechanism adjusts the translation of the message based on the recognized emotion.

"Example 3"

Step 1: User enters message.

Step 2: The emotion engine recognizes the user's emotions.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messenger apps and SNS, when users translated and sent messages into other languages, the quality of the translation often lacked emotional expression, and there was a problem that the user's intentions and feelings were not conveyed accurately. In addition, it was inconvenient for users to translate manually, which was time-consuming.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a message sending means, a "send in specific language" button generating means, a means for automatically translating the message into a specific language when the "send in specific language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the emotion of the user, and a means for adjusting the translation based on the result of the emotion recognition means. This makes it possible to send a high-quality translated message that reflects the emotion of the user.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that generates a button that is placed next to the message input field and allows the user to send a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

The "translation adjustment means" is a function that adjusts the expression of a translated message based on the results of the emotion recognition means.

Form for implementing the invention

This invention is a system that places a "Send in specific language" button on the message sending screen of a messenger app or SNS, and when a user inputs a message and presses the "Send in specific language" button, the input message is automatically translated into the specific language and the translated message is sent. It also includes a function that recognizes the user's emotions and adjusts the translation based on those emotions by combining it with an emotion engine.

Hardware and software used

Hardware:

Device: The device on which the user types messages (smartphone, tablet, PC, etc.)

Server: A remote server for message translation and emotion recognition.

Software:

Messenger apps and social media applications

Emotion engine (e.g. EmotionAI)

Translation API (e.g. Google Translate API, DeepL API)

Data processing and data calculations

1. Get message:

The device retrieves the message entered by the user.

2. Emotion recognition:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

3. Message translation:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

4. Sending a translated message:

The device will then send the translated message.

Specific examples

When a user types "Today is the best day ever!" into a messenger app and presses the "Send in specific language" button, the process goes like this:

1. The user types, "Today is the best day ever!".

2. The user presses the "Send in specific language" button.

3. Your device will receive the message "Today is a great day!"

4. The server uses "EmotionAI" to recognize the emotion of joy from the message.

5. The server uses the Google Translate API to translate "Today is the best day ever!" to "Today is the best day ever!".

6. The device sends the message "Today is the best day ever!".

Example of a prompt

"Design a system that translates messages typed by users in a messenger app into a specific language and adjusts the message to the appropriate wording based on emotion. For example, if a user types, 'Today is the best day ever!', the emotion engine should recognize joy and translate the message to, 'Today is the best day ever!'"

In this way, a system is realized that appropriately translates and sends messages entered by users based on emotions.

The flow of the identification process in Example 1 is explained using Figure 17.

Step 1:

The user enters a message into the message input field of a messenger app or social networking site.

Input: User types "Today is the best day ever!"

Specific action: The user types a message using a keyboard or touchscreen.

Output: "Today is the best day ever!" is displayed in the message input field.

Step 2:

The user presses the "Send in specific language" button located next to the message input field.

Input: User clicks the "Submit in specific language" button.

Specific action: The user presses a button using a mouse or touch screen.

Output: An event occurs when the button is pressed.

Step 3:

The device retrieves the message entered by the user.

Input: The event of a button being pressed and the input message "Today is the best day ever!".

Specific operation: The device reads text data from the message input field.

Output: The retrieved message "Today is the best day ever!" is stored in memory.

Step 4:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Input: Retrieved message: "Today is the best day ever!".

What it does: The server uses an emotion engine (e.g. EmotionAI) to analyze the message context, detect emojis, and analyze typing speed.

Output: The emotion engine recognizes the user's emotion as "joy".

Step 5:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

Input: Emotion engine result "Joy" and original message "Today is a great day!".

Specific operation: The server uses a translation API (e.g. Google Translate API) to perform translation that takes emotional expressions into account.

Output: The translated message "Today is the best day ever!".

Step 6:

The device will then send the translated message.

Input: Translated message: "Today is the best day ever!".

Specific operation: The device uses the message sending function to send the translated message.

Output: The sent message "Today is the best day ever!" will appear in the recipient's message inbox.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

When users send messages in different languages on traditional messaging apps and social media, the quality of the translation often does not accurately reflect their emotions, lowering the quality of communication. In addition, because the translation does not take into account the user's emotions, there is a risk of misunderstandings and discomfort.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means. In this invention, the server includes a message sending means in a messenger app or SNS, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion analysis means for analyzing the user's emotions, and a means for adjusting the translation based on the emotion analysis means. This enables a natural translation that takes the user's emotions into account.

"Messenger apps and social networking sites" are software applications that allow users to send and receive text messages, images, videos, etc.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

"Means for generating a send button in XX language" is a function that generates a button that allows a user to send a message in a specific language.

"Means for automatic translation" refers to a function that automatically translates a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to other users.

"Emotion analysis means" refers to a function that analyzes a user's emotions from messages entered by the user and other information.

The "means for adjusting the translation" refers to a function for adjusting the translated message based on the emotional information obtained by the emotional analysis means.

To implement this invention, it is necessary to build a system that takes emotions into account when a user sends a message in a messenger app or on a social networking site. This system includes the following main components:

1. Means of sending messages

It provides an interface for users to type and send messages. This can be a messaging app or social networking application that runs on a device such as a smartphone or computer.

2. How to generate a "Send in XX language" button

Creates a "Send in XXX" button that is placed next to the message sending method. This button allows the user to send a message in a specific language. It is automatically selected from the available languages based on the user's preferences.

3. Means of automatic translation

When a user presses the "Send in XXX language" button, the entered message is automatically translated into the specified language. This function is achieved using a generative AI model. Specifically, a translation model using the Transformers library is used.

4. How to send automatically translated messages

Send the translated message to other users. This feature will also be implemented as part of a messaging app or social networking application.

5. Sentiment analysis methods

Analyze user sentiment from messages entered by users and other information. This function is achieved using a generative AI model. Specifically, a sentiment analysis model using the Transformers library is used.

6. Ways to adjust translations

Adjust the translated message based on the emotional information obtained by the emotion analysis means. For example, if positive emotions are detected, change the translated message to a more positive expression.

Hardware and software used

Hardware: servers (cloud servers or on-premise servers), smartphones, computers

Software: Python, Flask, Transformers library

Specific examples

When a user types "Today is the best day ever!" and presses the "Send in English" button, the sentiment analyzer recognizes the joy and the message is translated and sent as "Today is the best day ever!".

Example of a prompt

"Today is the best day!"

The flow of the specific processing in application example 1 is explained using Figure 18.

Step 1:

The user opens a messenger app or social networking application and types a message. The typed message is saved in text format on the device.

Step 2:

The user presses the "Send in XXX language" button. This action causes the device to send the entered message to the server. The data sent includes the message text and the user's selected language.

Step 3:

The server passes the received message text to a sentiment analyzer, which uses a generative AI model to analyze the sentiment of the message. The input is the message text and the output is a sentiment label (e.g. positive, negative, neutral).

Step 4:

The server passes the message text to the translation means based on the emotion label obtained from the emotion analysis means. The translation means translates the message into the specified language using a generative AI model. The input is the message text and the emotion label, and the output is the translated message text.

Step 5:

The server adjusts the translated message text based on the emotion label. For example, if a positive emotion is detected, it changes the translated message to a more positive expression. The input is the translated message text and the emotion label, and the output is the adjusted message text.

Step 6:

The server sends the adjusted message text to the terminal. The terminal displays the received message and sends it to other users. The input is the adjusted message text, and the output is the displayed and sent message.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

In conventional messaging apps and social media, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, because the translation was done without taking into account the user's feelings, there was a risk that unintended nuances would be conveyed. This led to a problem of a decline in the quality of communication.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the user's emotion, and an emotion adjustment means for adjusting the translation of the message based on the recognized emotion. This makes it possible to automatically select a language frequently used by the user and provide an appropriate translation according to the emotion.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

The "means for generating a send button in XX language" is a function that automatically selects an appropriate language from available languages based on the user's settings, and generates a button for sending a message in that language.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

"Emotion adjustment means" is a function that adjusts the translation of a message based on the recognized emotions of the user.

This invention is a system that reduces the effort required for users to send messages in different languages and provides appropriate translations according to emotions. A specific embodiment of this system is described below.

Hardware and software used

Server: Responsible for data processing and storage. Specifically, it uses cloud services (e.g. AWS (registered trademark), Google Cloud Platform).

Device: The device used by the user. This includes smartphones, tablets, PCs, etc.

Generative AI model: A model for performing natural language processing. For example, OpenAI's GPT-3 or GPT-4 (registered trademark) are used.

Emotion engine: An engine for recognizing user emotions. For example, using IBM Watson's emotion analysis API.

System processing flow

1. User language settings

Users select the language they frequently use in the application settings screen.

The device sends the selected language information to the server.

The server stores the received language information in a database.

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

2. Create a language selection button

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

3. Enter your message

The user enters text into the message input field.

The device sends the entered message to the server in real time.

What it does: When a user types "Today is the worst day...", the text is instantly sent to the server.

4. Emotion Recognition

The server sends the received message to the emotion engine.

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

The server receives the results from the emotion engine and stores the emotion information.

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

5. Translation adjustments

The server sends a translation request to the generative AI model based on the recognized emotion.

The generative AI model generates appropriate translations based on emotions.

The server sends the generated translation to the device.

Specific operation: The generative AI model generates the translation "Today is the worst day..." and the server sends it to the device.

6. Sending a message

The user presses the "Send in French" button.

The device sends the translated message to the server.

The server receives the message and sends it to the specified recipient.

Specific operation: When the user presses the "Send in French" button, the device sends the message "Aujourd'hui est le pire jour..." to the server, which then sends it to the recipient.

Example of a prompt

"Please explain the function that allows users to set their frequently used language and automatically generate the submit button in that language on subsequent visits."

"Please explain the functionality that recognizes user emotions and adjusts the translation of the message based on the recognized emotion."

To improve user convenience, the system automatically selects frequently used languages and provides appropriate translations according to sentiment.

The flow of the identification process in Example 2 is explained using Figure 19.

Step 1:

Users select the language they frequently use in the application settings screen.

Input: The language selected by the user in the settings screen (e.g. French)

Output: Selected language information

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

Step 2:

The device sends the selected language information to the server.

Enter: Selected language information

Output: Language information sent to the server

Specific operation: The device sends the user's selected language information to the server.

Step 3:

The server stores the received language information in a database.

Input: Language information sent to the server

Output: Language information stored in the database

Specific operation: The server stores the language information it receives in the database.

Step 4:

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Input: Language information stored in the database

Output: Submit button information in generated language

Specific behavior: The server retrieves language information from the database and generates information for the "Submit in French" button.

Step 5:

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Input: Submit button information for generated language

Output: A submit button displayed in the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

Step 6:

The user enters text into the message input field.

Input: A message typed by the user (e.g., "Today is the worst day...")

Output: The message entered

Specific action: User types, "Today is the worst day..."

Step 7:

The device sends the entered message to the server in real time.

Input: Message entered

Output: Message sent to server

Specific operation: The device sends the entered message to the server.

Step 8:

The server sends the received message to the emotion engine.

Input: Message sent to server

Output: Message sent to emotion engine

Specific operation: The server sends the received message to the emotion engine.

Step 9:

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

Input: Message sent to emotion engine

Output: Inferred emotion information (e.g. sadness)

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

Step 10:

The server receives the results from the emotion engine and stores the emotion information.

Input: Inferred emotion information

Output: Stored emotion information

Specific operation: The server receives emotion information from the emotion engine and stores it in the database.

Step 11:

The server sends a translation request to the generative AI model based on the recognized emotion.

Input: Stored emotion information, user message

Output: Translation request sent to generative AI model

Specific operation: The server sends emotion information and the user's message to the generative AI model.

Step 12:

The generative AI model generates appropriate translations based on emotions.

Input: Translation request sent to generative AI model

Output: The generated translation (e.g. "Today is the worst day...")

Specific behavior: The generative AI model generates the translation "Today is the worst day..."

Step 13:

The server sends the generated translation to the device.

Input: Generated translation

Output: Translation sent to device

Specific operation: The server sends the generated translation to the device.

Step 14:

The user presses the "Send in French" button.

Input: User operation

Output: Send button press information

Specific action: The user presses the "Send in French" button.

Step 15:

The device sends the translated message to the server.

Input: Send button press information, generated translation

Output: The translated message sent to the server

Specific action: The device sends the message "Aujourd'hui est le pire jour..." to the server.

Step 16:

The server receives the message and sends it to the specified recipient.

Input: Translation message sent to server

Output: Message sent to recipient

Specific operation: The server sends the translated message to the recipient.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

Existing messenger apps and SNS lack the ability to automatically select the language frequently used by the user or adjust the translation of messages based on the user's emotions, limiting the user experience. There is also a demand for more natural and appropriate communication by recognizing the user's emotions and adjusting the translation based on them. Furthermore, content distribution services also face the challenge of improving the viewing experience by adjusting subtitles and audio translations based on the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means.

In this invention, the server includes a message sending means for a messenger app or SNS, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing a user's emotion, an emotion adjustment means for adjusting the translation of the message based on the recognized emotion, a language selection means for automatically selecting a language based on the user's settings and past usage history, and a translation adjustment means for adjusting the translation of subtitles and audio based on the user's emotion. This makes it possible to automatically select a language frequently used by the user and adjust the translation of messages and content based on the user's emotion.

"Message sending means" refers to an interface that allows users to input and send messages.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings and usage history.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" refers to technology for recognizing emotions from user input, facial expressions, voice, etc.

"Emotion adjustment means" is a function that adjusts the translation or display of a message based on the recognized emotion.

"Language selection means" is a function that automatically selects the most appropriate language based on the user's settings and past usage history.

"Translation adjustment means" is a function that adjusts the translation of subtitles and audio based on the user's emotions.

The following system configuration is described as a form for implementing this invention.

System configuration

This system includes a means for sending messages in messenger apps and SNS, a means for generating send buttons in a certain language, an automatic translation means, an emotion recognition means, an emotion adjustment means, a language selection means, and a translation adjustment means.

Method of sending message

An interface that allows users to input and send messages. It is implemented as an application on a smartphone or PC.

How to generate a send button in XX language

This function automatically generates buttons for sending messages in a specific language based on the user's settings and usage history. It automatically selects the language the user frequently uses and displays it as a button.

Automatic translation methods

This function automatically translates messages entered by users into a specified language. It is implemented using a translation API such as Google Translator.

Emotion recognition means

This is a technology for recognizing emotions from user input, facial expressions, voice, etc. It uses software such as OpenCV and EmotionRecognizer to analyze data from the camera and microphone.

Methods of emotion regulation

This feature adjusts the translation and display of messages based on the recognized emotion. For example, if the user has a sad expression, the translated message will be adjusted accordingly.

Language selection method

This function automatically selects the most suitable language based on the user's settings and past usage history. Content from the next time onwards will also be automatically selected based on the user's viewing history and settings information.

Translation adjustment methods

This feature adjusts subtitle and audio translations based on the user's emotions. For example, if the user looks sad, the subtitle translation will be adjusted accordingly.

Program processing explanation

The server captures data from the camera and microphone and recognizes the user's emotions using OpenCV and EmotionRecognizer. Based on the recognized emotions, it translates the message using a translation API such as Google Translator and displays the message adjusted by the emotion adjustment means. Based on the user's settings and past usage history, the language selection means automatically selects the most suitable language.

Specific examples

If a user frequently speaks French, the application will automatically provide content in French. And if the user has a sad expression, the subtitle translation will adjust accordingly.

Example of a prompt

Develop a smartphone application that automatically selects the language that the user frequently uses and uses an emotion engine to recognize the user's emotions and adjust the translation accordingly. For example, if the user frequently uses French, the application automatically provides content in French. Also, if the user has a sad expression, the subtitle translation will be adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

The flow of the specific processing in application example 2 is explained using Figure 20.

Step 1:

The server captures the user's video and audio data from the device through the camera and microphone. The input is the user's video and audio data, and the output is the captured raw data. This data is used in subsequent processing steps.

Step 2:

The server analyzes the captured video and audio data using OpenCV and EmotionRecognizer to recognize the user's emotions. The input is the captured raw data, and the output is the recognized emotional information. Specifically, it analyzes the user's facial expressions and tone of voice, and classifies emotions into "happiness," "sadness," "anger," etc.

Step 3:

The server uses a language selection means to automatically select the most appropriate language based on the user's settings and past usage history. The input is the user's settings information and usage history, and the output is the selected language information. Specifically, the language that the user frequently uses is obtained from the database and applied to the next and subsequent content.

Step 4:

The user enters a message and presses the send button. The input is the message entered by the user, and the output is the event information that the send button has been pressed. Specifically, this includes the action of the user entering a message into a text box and pressing the "Send in XX language" button.

Step 5:

When the send button is pressed, the server uses a translation API such as Google Translator to automatically translate the entered message into the selected language. The input is the message entered by the user and the selected language information, and the output is the translated message. Specifically, the message and target language are sent to the API and the translation result is received.

Step 6:

The server adjusts the translated message based on the recognized emotion with an emotion adjustment means. The input is the translated message and the recognized emotion information, and the output is the adjusted message. Specifically, if the user is expressing a sad emotion, the translated message is adjusted to be more negative accordingly.

Step 7:

The server sends the adjusted message through the message sending means. The input is the adjusted message and the output is the sent message. Specifically, the server sends the adjusted message to the recipient and displays a notification of the completion of the sending on the user's interface.

Step 8:

The server adjusts the subtitle and audio translations in the content delivery service based on the user's emotions. The input is the user's emotional information and content data, and the output is the adjusted subtitles and audio. Specifically, if the user has a sad expression, the subtitle translation is adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

Conventional message translation systems perform simple translations without considering the context or emotions of the message entered by the user, which often results in inappropriate translations. In addition, there is a problem that the quality of communication declines because the translation cannot reflect the user's emotions. This creates an issue in that it becomes difficult to convey the exact meaning and emotions intended by the user.

The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "send in translation language" button generating means located next to the message sending means, a means for automatically translating the message into the translation language when the "send in translation language" button is pressed, a means for sending the automatically translated message, a context analysis means for selecting an optimal translation based on the context of a message input by a user, and an emotion analysis means for recognizing the user's emotion and adjusting the translation based on that emotion. This makes it possible to provide an optimal translation of a user's input message based on the context and emotion.

"Message sending means" is a function for sending messages entered by a user to other users.

The "means for generating a send button in a translated language" is a function for generating a button for sending a message in a translated language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified translation language.

"Context analysis means" is a function that analyzes the context of the message entered by the user and selects the most appropriate translation based on that context.

"Sentiment analysis means" is a function that recognizes the emotion of the message entered by the user and adjusts the translation based on that emotion.

"Transmission means" is a function for sending translated messages to other users.

"User settings" are settings that users make to customize system behavior, translation languages, etc.

"Translation language" is the language the user uses to translate the message.

Form for implementing the invention

This invention is a system that provides an optimal translation of a message entered by a user based on the context and emotion. A specific embodiment of this system is described below.

System configuration

The system mainly consists of the following components:

1. Means of sending messages

2. How to generate a send button in a translated language

3. Automatic translation methods

4. Contextual analysis methods

5. Sentiment analysis methods

6. Transmission method

Hardware and software used

The server uses the following hardware and software to receive, parse, translate, and send messages:

Server hardware: A server with a powerful processor and sufficient memory

Software: Python, NLTK library, Google Natural Language API

The device uses the following hardware and software to allow users to enter messages and display translation results:

Device hardware: smartphones, tablets, PCs, etc.

Software: Messenger apps, SNS apps

System operation

The user inputs a message into an input field on the terminal. For example, the user inputs "I'm fine." The terminal sends this message to the server. The server sends the received message to the context analysis means, which analyzes the context of the message. The context analysis means analyzes the context using, for example, Python's NLTK library, and translates the message "I'm fine." into "I'm fine."

The server then sends the translation to the sentiment analyzer, which uses Google's Natural Language API to analyze the sentiment of the message. For example, if the user types "Today is the best day ever!" and the sentiment analyzer recognizes joy, the translation is adjusted to "Today is the best day ever!".

Finally, the server sends the adjusted translation result to the terminal, and the terminal displays the translation result to the user. The user can check the translation result on the terminal screen.

Specific examples

As a concrete example, consider the case where a user types "I'm fine" into a terminal. This message is sent to the server, where the context analysis means translates it as "I'm fine." If the user then types "Today is the best day ever!", the emotion analysis means will recognize the joy, and the server will translate it as "Today is the best day ever!".

Example of a prompt:

If a user types "I'm fine," choose the appropriate translation based on the context and analyze the sentiment using sentiment analysis tools.

If a user types "Today is a great day!", use sentiment analysis to recognize the sentiment and choose the appropriate translation.

This system supports more natural and appropriate communication by providing an optimal translation of the user's input message based on the context and emotion. The flow of the specific process in Example 3 is explained with reference to FIG. 21.

Step 1:

The user types a message.

The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." The entered message is passed to the terminal's message sending means.

Step 2:

The device sends the message to the server.

The terminal sends the message entered by the user to the server. At this time, the message is sent as an HTTP request. The input is the user's message, and the output is an HTTP request to the server.

Step 3:

The server receives the message and sends it to the context analysis means.

The server sends the received message to the contextual analyzer, which analyzes the context using, for example, Python's NLTK library. The input is the user's message and the output is the data to the contextual analyzer.

Step 4:

The contextual analysis means analyzes the context of the message and selects the appropriate translation.

The contextual analysis means analyzes the context of the message and selects the appropriate translation. For example, the message "I'm fine." is translated as "I'm fine." The input is the user's message and the output is the translation result.

Step 5:

The server sends the translation results to the sentiment analysis means.

The server transmits the translation results obtained from the context analysis means to the sentiment analysis means. The sentiment analysis means analyzes sentiment using, for example, Google's (registered trademark) Natural Language API. The input is the translation result, and the output is data to the sentiment analysis means.

Step 6:

Sentiment analysis tools analyze the sentiment of the message and adjust the translation.

The sentiment analyzer analyzes the sentiment of the message and adjusts the translation. For example, if the message "Today is the best day ever!" is recognized as expressing joy, the translation is adjusted to "Today is the best day ever!". The input is the translation and the output is the adjusted translation.

Step 7:

The server sends the final translation results to the device.

The server sends the final translation result obtained from the sentiment analysis means to the terminal. At this time, the translation result is sent as an HTTP response. The input is the adjusted translation result, and the output is the HTTP response to the terminal.

Step 8:

The device displays the translation results to the user.

The terminal displays the translation results received from the server to the user. The user can check the translation results on the terminal screen. The input is the translation result from the server, and the output is what is displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

Conventional message translation systems perform translation without considering the context or emotion of the message entered by the user, resulting in unnatural translations or failure to accurately convey the user's intent. In addition, since translations cannot reflect emotion, it is difficult to properly convey the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in language" button generating means located next to the message sending means, a means for automatically translating the message into a language when the "Send in language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for recognizing the user's emotion using an emotion engine and adjusting the translation based on that emotion. This enables a natural and appropriate translation that takes into account the context and emotion of the message input by the user.

"Message sending means" refers to an interface that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Means for automatic translation" refers to a function that automatically translates an input message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the input message and selects the translation that best suits that context.

The "emotion engine" is a system that recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

"Means for adjusting a translation based on emotion" refers to a function for adjusting a translated message based on a user's emotion as recognized by an emotion engine.

A system for implementing the present invention includes a message sending means, a language send button generating means, a means for automatic translation, a means for sending the automatically translated message, a means for selecting an optimal translation based on context, an emotion engine, and a means for adjusting the translation based on emotion.

System configuration

The server uses the following hardware and software:

Hardware: The server uses a computer system with a high-performance processor and sufficient memory. Specifically, Intel Xeon processors and AMD EPYC processors are suitable.

Software: The server uses the Python programming language and the transformers natural language processing library. It also uses the nltk library for sentiment analysis.

Processing flow

1. Message sending means: Provides an interface for users to enter text messages. This is an application that runs on a mobile device such as a smartphone or tablet.

2. Send in language button generator: Generates a button to send a message in the language selected by the user. This button is automatically selected based on the user's settings.

3. Means of automatic translation: Automatically translate messages entered by users into a specified language. This translation is done using a generative AI model.

4. How to send an automatically translated message: Send an automatically translated message to other users.

5. A means to select the best translation based on context: Analyze the context of the message entered by the user and select the translation that best suits that context.

6. Emotion engine: Recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

7. Means to tailor translation based on emotion: Adjust the translated message based on the user's emotion as recognized by the emotion engine.

Specific examples

For example, if a user is watching a movie and a character says, "I'm so happy today!", the emotion engine will recognize the positive emotion and adjust the translation to "I'm so happy today!".

Example of a prompt to input to the generative AI model:

"Translate the following text to Japanese and adjust the translation based on the detected emotion: 'I'm so happy today!'"

In this way, the user's viewing experience can be enriched.

The flow of the specific processing in application example 3 is explained using Figure 22.

Step 1:

The user enters a message on the terminal. The entered message is sent to the server in text format. The input data is the text message entered by the user.

Step 2:

The server analyzes the received messages and performs natural language processing (NLP) to understand the context. For this process, it uses the transformers library. The input data is the text message entered by the user, and the output data is the analysis result including contextual information.

Step 3:

The server uses a generative AI model to generate an optimal translation based on the analysis results. Specifically, it uses a translation model from the transformers library to translate the message into the specified language. The input data is the analysis results including contextual information, and the output data is the translated text message.

Step 4:

The server passes the translated message to an emotion engine to recognize the user's emotion. The emotion engine uses the nltk library. The input data is the translated text message, and the output data is the emotion label (e.g. positive, negative).

Step 5:

The server adjusts the translated message based on the emotion label. For example, for positive emotion it adds "Da yo!" to the translated message, and for negative emotion it adds "Da...". The input data are the emotion label and the translated text message, and the output data is the adjusted translated message.

Step 6:

The server sends the adjusted translation message to the terminal. The terminal displays the received message to the user. The input data is the adjusted translation message, and the output data is the text message displayed to the user.

Step 7:

The user checks the displayed message and replies if necessary. The reply message is sent again through the process from step 1. The input data is the reply message entered by the user, and the output data is the translated and adjusted reply message.

The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input for the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

Another example of generative AI is Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>).

In the above embodiment, an example was given in which the specific processing was performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the headset-type terminal 314.

[Fourth embodiment]

Figure 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

As shown in FIG. 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

The data processing device 12 includes a computer 22, a database 24, and a communication I/F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I/Fs 44 and 26 is performed in a secure state.

The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and legs. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

Storage 32 stores a data generation model 58 and an emotion identification model 59. Data generation model 58 and emotion identification model 59 are used by the identification processing unit 290.

In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

Next, we will explain the specific processing performed by the specific processing unit 290 of the data processing device 12.

"Example 1"

As one embodiment of the present invention, a "Send in English" button is placed next to the message input field on the message sending screen of a messenger app or SNS. When a user inputs a message and presses the "Send in English" button, the input message is automatically translated into English and the translated message is sent.

"Example 2"

Furthermore, we provide a function that automatically selects the language of the "Send in ____" button from the available languages based on the user's settings. For example, if the user frequently communicates with people who speak French, the "Send in French" button will be automatically generated based on the user's settings.

"Example 3"

The service also provides a function that selects the most appropriate translation based on the context of the message entered by the user. For example, if the user enters "I'm fine," this will be translated as "I'm fine." However, if the user enters "It's fine," this will be translated as "It's fine." In this way, the translation method for the same "fine" changes depending on the context.

The process flow for each example is explained below.

"Example 1"

Step 1: The user opens the message sending screen of a messenger app or SNS.

Step 2: Make sure the "Send in English" button is located next to the message input field.

Step 3: The user enters a message and presses the "Send in English" button.

Step 4: The system will automatically translate the message you entered into English.

Step 5: The system sends the translated message.

"Example 2"

Step 1: The user opens the settings screen of the messenger app or SNS.

Step 2: The user selects the language from the available options for the "Send in" button. Step 3: The user saves the settings and returns to the message sending screen.

Step 4: Make sure there is a "Send in XXX" button in the user's chosen language next to the message input field.

"Example 3"

Step 1: User enters message.

Step 2: The system selects the best translation based on the context of the message entered by the user.

Step 3: The system displays the selected translation to the user.

Step 4: The user presses the "Send in XXX language" button and the system sends the selected translation.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, the accuracy of the translation and the lack of appropriate translation based on the context were often poor, which could impair smooth communication. To solve these problems, a system was needed that would allow users to easily translate and send messages in a specific language.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in specific language" button generating means disposed next to the message sending means, a means for automatically translating the message into a specific language when the "Send in specific language" button is pressed, a means for sending the automatically translated message, a means for inputting the message into a generative AI model as a prompt sentence, a means for the generative AI model to translate the message, and a means for sending the translated message to a destination. This enables a user to easily translate and send a message into a specific language.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that is placed next to the message sending means and generates a button for sending a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

A "generative AI model" is an artificial intelligence model for performing natural language processing and capable of translating input text into other languages.

A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

"Means for sending translated messages" refers to a function for sending messages translated by the automatic translation means to a specified destination.

"Optimal translation based on context" refers to providing the most appropriate translation by taking into account the content and intent of the message entered by the user.

This invention is a system that allows users to easily translate and send messages into a specific language in messenger apps and SNS. A specific embodiment of this system is described below.

First, a user opens the message sending screen of a messenger app or SNS and enters a message in the message input field. For example, the user might enter "Hello, how are you?". Next, the user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in an appropriate format. The server inputs the received message into a generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, it sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

The generative AI model receives the prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" to "Hello, how are you?". The server sends the translated message received from the generative AI model to the device. At this time, the translated message is sent to the device in the appropriate format.

The device then sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend. In this way, a message entered by the user in Japanese is automatically translated into a specific language and sent.

As a concrete example, consider a case where a user wants to send a message to a friend saying "Hello, how are you?" The user enters "Hello, how are you?" in the message input field and presses the "Send in specific language" button. The system translates this message into "Hello, how are you?" and sends it to the friend.

Example of a prompt to input to a generative AI model:

"Please translate 'Hello, how are you?' into English."

This system allows users to easily translate and send messages into a specific language. The hardware used includes the user's device (smartphone, tablet, PC, etc.) and a server. The software used includes messenger apps, SNS applications, and generative AI models (e.g., GPT-4 (registered trademark)).

The flow of the identification process in Example 1 is explained using Figure 11.

Step 1:

The user enters a message in the message input field.

Enter: "Hello, how are you?"

Output: Input message "Hello, how are you?"

Specific actions: The user opens the message sending screen of a messenger app or SNS and types "Hello, how are you?" in the message input field.

Step 2:

The user presses the "Send in specific language" button.

Input: User presses the "Send in specific language" button

Output: Event that the send button was pressed

Specific behavior: The user presses the "Send in specific language" button located next to the message input field. This action starts the process of translating the entered message into the specific language.

Step 3:

The device sends the entered message to the server.

Input: An event that inputs the message "Hello, how are you?" and presses the send button

Output: Message sent to server: "Hello, how are you?"

Specific operation: The terminal sends the message entered by the user to the server. At this time, the message is sent to the server in the appropriate format.

Step 4:

The server inputs the message into the generation AI model as a prompt.

Input: Message sent to server: "Hello, how are you?"

Output: Prompt sent to the generative AI model: "Please translate 'Hello, how are you?' into English."

Specific operation: The server inputs the received message into the generative AI model (e.g., GPT-4 (registered trademark)) as a prompt sentence. Specifically, the server sends the prompt sentence "Please translate 'Hello, how are you?' into English" to the generative AI model.

Step 5:

A generative AI model translates the message into English.

Input: Prompt text: "Please translate 'Hello, how are you?' into English."

Output: The translated message "Hello, how are you?"

Specific behavior: The generative AI model receives a prompt and translates the message into a specific language. For example, it translates "Hello, how are you?" into "Hello, how are you?".

Step 6:

The server sends the translated message to the device.

Input: translated message "Hello, how are you?"

Output: The translated message "Hello, how are you?" sent to the terminal.

Specific operation: The server sends the translated message received from the generative AI model to the terminal. At this time, the translated message is sent to the terminal in an appropriate format.

Step 7:

Your device will then send the translated message to the recipient.

Input: The translated message sent to the device: "Hello, how are you?"

Output: The message "Hello, how are you?" sent to the destination.

Specific operation: The device sends the translated message received from the server to the destination. For example, the message "Hello, how are you?" is sent to a friend.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

With the current trend of globalization, communication with foreign customers has become important in brick-and-mortar stores. However, the language barrier makes it difficult for store staff to communicate smoothly with foreign customers. To solve this problem, real-time language translation is necessary, but current technology is not sufficient.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a voice input means, a means for converting voice acquired by the voice input means into text, a means for translating the text into XXX language, and a means for vocally outputting the translated text. This enables smooth real-time communication between store staff and foreign customers in physical stores.

"Message sending means" refers to an interface that allows a user to input and send text messages.

The "means for generating a send button in XX language" is a function that generates a button for translating and sending a message into a language selected by the user.

"Means for automatic translation" refers to a function for automatically translating an input text message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to the other party.

"Voice input means" is an interface for capturing the user's voice and acquiring it as digital data.

"Means for converting voice to text" refers to a function for converting acquired voice data into text data.

"Means of translating text into XX language" is a function for translating text data into a specified language.

"Means for outputting translated text as audio" refers to a function for playing back translated text as audio.

To implement this invention, the following system configuration and program are required.

First, the server provides a message sending means, which is an interface that allows the user to input and send a text message. Next, the server provides a "Send in XX language" button generating means, which is a function that generates a button for translating and sending a message into a language selected by the user.

When a user presses the "Send in XXX language" button, the server uses an automatic translation means to automatically translate the entered text message into the specified language. This translated message is then sent to the recipient by a means for sending an automatically translated message.

Furthermore, the server provides a voice input means, which is an interface for capturing the user's voice and acquiring it as digital data. The acquired voice data is converted into text data by a voice-to-text conversion means.

The converted text data is translated into a specified language by a means for translating text into a specific language. The translated text is played as audio by a means for outputting the translated text as audio.

To realize this system, the following hardware and software are used:

Hardware: Smart glasses (capable of voice input and output)

Software:

speech_recognition library: convert speech to text

googletrans library: translate text

pyttsx3 library: convert text to speech

As a concrete example, when a store clerk says, "Where is this product located?", the voice is captured by the microphone of the smart glasses. The voice data is converted to text using the speech_recognition library, and the text is translated into English using the googletrans library. The translated text is converted to speech using the pyttsx3 library, and "Where is this product located?" is played from the speaker of the smart glasses.

Example of a prompt to input to a generative AI model:

When a user says "Where is this product located?", convert that speech to text, translate it into English, display "Where is this product located?" and play it aloud.

The flow of the specific processing in application example 1 is explained using Figure 12.

Step 1:

The user speaks into the smart glasses. The microphone in the smart glasses captures the voice and obtains it as voice data. This voice data becomes the input.

Step 2:

The voice data acquired by the device (smart glasses) is converted into text data using the speech_recognition library. The voice data is analyzed and corresponding text data is generated. This text data becomes the output.

Step 3:

Translates text data generated by the device into a specified language (e.g. English) using the googletrans library. Takes text data as input and generates translated text data. This translated text data is the output.

Step 4:

The device converts the translated text data into speech data using the pyttsx3 library. It takes the translated text data as input and generates the corresponding speech data. This speech data becomes the output.

Step 5:

The device then plays the generated voice data through the smart glasses' speakers, allowing the user to listen to the translated audio.

Specifically, when a user says "Where is this product located?", the voice is captured by the microphone in the smart glasses. The voice data is converted into text data saying "Where is this product located?" using the speech_recognition library. The text data is translated into English as "Where is this product located?" using the googletrans library. The translated text data is converted into voice data using the pyttsx3 library, and "Where is this product located?" is played from the speaker in the smart glasses.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messaging apps and SNS, when users wanted to send a message in a different language, they had to translate it manually, which was a time-consuming process. In addition, there was no function to automatically select frequently used languages, so users had to select the language every time, which was inconvenient. Furthermore, the quality of the translation was not consistent, so the translation did not always match the context of the message.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a means for acquiring user setting information, a means for sending a prompt sentence to the generative AI model based on the acquired setting information, a means for generating a "Send in XXX language" button based on a response from the generative AI model, a means for displaying the generated "Send in XXX language" button in a user interface, and a means for sending a message when the user clicks the "Send in XXX language" button. This makes it possible to automatically select a language frequently used by the user and perform an appropriate translation.

"User settings information" refers to the individual language and other customization information that a user sets within the system.

A "generative AI model" is a model designed to perform specific tasks using artificial intelligence. In this case, its role is to generate prompts based on user settings and generate appropriate language selection buttons.

A "prompt sentence" refers to an input sentence that gives specific instructions or asks a question to a generative AI model.

"Send in XXX language button" refers to a button on the interface that allows a user to send a message in a specific language of their choice.

"User interface" refers to the screens and operating means that allow users to interact with the system.

"Means of sending messages" refers to the functionality for sending messages entered by the user in the selected language.

This invention relates to a system for messenger apps and SNS that automatically selects a language frequently used by a user and performs appropriate translation. A specific embodiment of this system is described below.

Server processing

The server retrieves the user's settings information from a database. Specifically, it uses a database management system such as MySQL (registered trademark) to retrieve information on the languages frequently used by the user. For example, it executes an SQL query that retrieves the corresponding language settings using the user ID as a key.

The server then sends a prompt to a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) based on the retrieved user settings. The prompt includes instructions to generate a "Send in XXX language" button based on the user's frequently used language.

Example of a prompt:

"Based on the user's preferences, select the frequently used language and generate a corresponding submit button. For example, if the user selects French, generate a 'Submit in French' button."

The server that receives the response from the generative AI model generates the data to display in the user interface. Specifically, it generates HTML and JavaScript (registered trademark) code and creates buttons that correspond to the language selected by the user.

Terminal processing

The terminal receives the data sent from the server and reflects it in the user interface. Specifically, it dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React.

User operations

The user selects the languages they use most frequently in the settings screen. For example, if the user selects French, a "Send in French" button will be automatically generated from next time. The user can click this button to send messages in the selected language.

Specific examples

For example, if a user selects "French" in the settings screen, the "Send in French" button will be automatically generated next time. When the user clicks this button, the message will be sent in French.

In this way, it is possible to automatically select the language that the user frequently uses and provide an appropriate translation. This saves the user the trouble of having to manually select the language, allowing for smoother communication.

The flow of the identification process in Example 2 is explained using Figure 13.

Step 1:

Get user settings information

The server retrieves the user's preference information from a database. As input, a user ID is given. The server uses a database management system such as MySQL (registered trademark) to retrieve information about the user's frequently used languages. Specifically, it executes an SQL query using the user ID as a key to retrieve the corresponding language preference. As output, the user's preference information (e.g., French) is obtained.

Step 2:

Generating and sending prompts

The server sends a prompt to the generative AI model based on the acquired user setting information. The user's setting information is given as input. The prompt includes an instruction to generate a "Send in XX language" button based on the language the user frequently uses. An example of a specific prompt is "Based on the user's settings, please select the language that is frequently used and generate a corresponding send button. For example, if the user selects French, please generate a 'Send in French' button." The output is a response from the generative AI model.

Step 3:

Generate language selection button

The server generates a "Send in XXX language" button based on the response from the generative AI model. The response from the generative AI model is given as input. The server generates HTML and JavaScript (registered trademark) code to create a button that corresponds to the language selected by the user. The output is the data for the generated "Send in XXX language" button.

Step 4:

Display language selection button

The terminal receives the data sent from the server and reflects it in the user interface. As input, it is given the data for the "Send in XX language" button sent from the server. The terminal dynamically generates and displays the "Send in French" button using front-end technologies such as JavaScript (registered trademark) and React. As output, it obtains the button displayed in the user interface.

Step 5:

Send a message

The user clicks the generated "Send in French" button. As input, the user's click event is given. When the click event occurs, a message is sent in the selected language. Specifically, a JavaScript® event listener is used to catch the button click event and process the message sending. As output, the message sent in the selected language is obtained.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users communicate in different languages, they have to translate manually, which is inefficient. In addition, there was a lack of functionality to automatically learn frequently used languages and send messages in the appropriate language, which made it inconvenient for users.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means. In this invention, the server includes a message sending means, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, a means for acquiring user setting information, a means for learning frequently used languages based on the setting information, a means for automatically generating the "Send in XXX language" button based on the learned languages, a means for translating the message in real time, and a means for sending the translated message. This makes it possible to automatically learn languages frequently used by the user and send messages in the appropriate language.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending translated messages to other users.

"Means for acquiring user setting information" refers to a function for acquiring the language and other setting information previously set by the user.

"Means for learning frequently used languages" refers to a function for learning the languages that a user frequently uses based on the user's past message history and settings information.

"Means of real-time translation" refers to a function that translates a message into a specified language in real time as the user types the message.

The system for implementing this invention is composed of a server and a user terminal. The server includes a message sending means, a "send in XX language" button generating means, an automatic translation means, a sending means, a means for acquiring user setting information, a means for learning frequently used languages, and a means for translating in real time.

Program processing explanation

Hardware to be used

Server: Any cloud server (e.g. AWS (registered trademark), Google Cloud)

Client: Smartphone (iOS or ANDROID (registered trademark))

Software to be used

Framework: Flask (Python)

Translation API: Googletrans (Python wrapper for Google Translate API)

Data processing and data calculations

1. How to get user settings information:

The server retrieves the user's pre-selected language and other preferences. This information is used to learn the user's frequently used languages based on their past message history and preferences.

2. Ways to learn frequently used languages:

The server learns which languages the user frequently uses based on the user's past message history and preferences. This allows it to identify the language the user uses most often and automatically generate a button to send messages in that language.

3. How to generate the "Send in ____ language" button:

The server automatically generates a button to send a message in a specific language based on the user's preferences. This button is displayed when the user types a message.

4. Ways to translate in real time:

As users type their messages, the server translates them into the specified language in real time, allowing users to see the translated message instantly.

5. Automatic translation methods:

When a user presses the "Send in XXX language" button, the server automatically translates the message into the specified language. This translation is done using a translation API such as GoogleTrans.

6. Transmission method:

The translated messages are then sent to other users via the server, allowing users who speak different languages to communicate smoothly.

Specific examples

For example, if the user is "user1" and sends the message "Hello, how are you?", the server will translate this message into French and return it as "Bonjour, comment &ccedil;a va?".

Example of a prompt

User ID: user1

Message: Hello, how are you?

When you send this prompt to the server, you will get a response like this:

{

"original_message": "Hello, how are you?",

"translated_message": "Bonjour, comment &ccedil;a va?",

"language": "fr"

}

In this way, a system can be created that automatically selects a language based on the user's settings and then translates and sends the message.

The flow of the specific processing in application example 2 is explained using Figure 14.

Step 1:

The user inputs a message. The user inputs a text message using the smartphone's message sending means. This input message is sent to the server.

Step 2:

The server retrieves the user's preferences. The server retrieves the user's preferences from a database and identifies the user's frequently used languages. This preference information includes languages the user has used in the past and languages that have been preset by the user.

Step 3:

The server learns which languages are used most frequently. Based on the configuration information obtained, the server learns which languages are used most frequently by users. Based on the results of this learning, it generates a "Send in XXX" button for sending messages in a specific language.

Step 4:

The server generates a "Send in XX language" button. Based on the learning results, the server automatically generates a button for sending messages in the language the user frequently uses and displays it on the user's device.

Step 5:

The user presses the "Send in XXX" button. By pressing the generated "Send in XXX" button, the user instructs the message they typed to be translated into a specific language.

Step 6:

The server translates the message in real time. The server translates the message entered by the user into the specified language in real time. This translation uses a translation API such as Googletrans.

Step 7:

The server sends the translated message. The server returns the translated message to the user's device so that the user can review it. The server then sends the translated message to other users.

Step 8:

Other users receive the translated message. Other users receive and display the translated message sent from the server. This allows users who speak different languages to communicate smoothly.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messaging apps and SNS, it was difficult to provide appropriate translations based on the context when users sent messages. In particular, when the same word had different meanings depending on the context, it was difficult to select the appropriate translation.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a message sending means, a "send with translation" button generating means disposed next to the message sending means, a means for automatically translating the message when the "send with translation" button is pressed, a means for sending the automatically translated message, a means for receiving a message input by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to the user. This makes it possible to provide an optimal translation based on the context of the message input by the user.

"Message sending means" refers to a means for sending messages entered by a user to other users.

The "translation and send button generation means" is a means for generating a button that enables a user to translate and send a message.

"Means for automatic translation" refers to a means for automatically translating a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to means for sending translated messages to other users.

"Means for receiving messages entered by users" refers to the means by which the server receives messages entered by users.

"Means for inputting a message into a generative AI model" refers to means for inputting a received message into a generative AI model.

"Means by which a generative AI model generates a context-based translation" refers to the means by which a generative AI model analyzes the context of a message and generates an optimal translation.

"Means for receiving the generated translation results" refers to means for receiving the translation results generated from the generative AI model.

"Means for displaying the translation result to the user" refers to means for displaying the received translation result to the user.

This invention relates to a system that optimally translates a message entered by a user based on the context. This system includes a message sending means, a translation send button generating means, an automatic translation means, a means for sending the automatically translated message, a means for receiving a message entered by a user, a means for inputting a message to a generative AI model, a means for the generative AI model to generate a translation based on the context, a means for receiving the generated translation result, and a means for displaying the translation result to a user.

Hardware and software used

This system uses a server, a terminal, and a generative AI model. Specifically, the server receives messages, inputs them into the generative AI model, and receives and sends translation results. The terminal inputs messages from users and displays the translation results. For example, OpenAI's GPT-4 (registered trademark) is used as the generative AI model.

Data processing and data calculations

The server receives the message entered by the user on the device and inputs the message into the generative AI model. The generative AI model analyzes the context of the message and generates the optimal translation. The generated translation result is returned to the server, which then sends the result to the device. The device displays the translation result to the user.

Specific examples

As a concrete example, consider the case where a user types "I'm fine." In this case, the server uses a generative AI model to generate the translation "I'm fine." On the other hand, if the user types "It's fine.", the server generates the translation "It's fine."

Example of a prompt

"If the user types 'I'm fine.', translate this as 'I'm fine.'"

"If the user types 'It's fine.', translate this to 'That's fine.'"

In this way, the system can properly translate the user's input message based on the context. The flow of the specific process in Example 3 is explained with reference to FIG. 15.

Step 1:

The user enters a message. The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." This input message becomes the input data for the next processing step.

Step 2:

The terminal sends a message to the server. The terminal sends the message entered by the user to the server using an HTTP request. In this case, the input data is the message entered by the user, and the output data is the message sent to the server.

Step 3:

The server receives the message. The server receives the message sent from the terminal and temporarily stores it in memory. The input data is the message sent from the terminal, and the output data is the message stored on the server.

Step 4:

The server inputs messages into the generative AI model. The server calls an API to input the received messages into the generative AI model. The input data is the message stored on the server, and the output data is the message passed to the generative AI model.

Step 5:

The generative AI model generates a translation based on the context. The generative AI model analyzes the context of the input message and generates the optimal translation. For example, for the message "I'm fine," it generates the translation "I'm fine." The input data is the message passed to the generative AI model, and the output data is the generated translation result.

Step 6:

The server receives the translation results. The server receives the translation results generated from the generative AI model and stores them in memory. The input data is the translation results returned from the generative AI model, and the output data is the translation results stored on the server.

Step 7:

The server sends the translation results to the terminal. The server sends the translation results to the terminal using an HTTP response. The input data is the translation results stored on the server, and the output data is the translation results sent to the terminal.

Step 8:

The terminal displays the translation result to the user. The terminal displays the translation result received from the server to the user. For example, the translation result "I'm fine" is displayed on the terminal screen. The input data is the translation result sent to the terminal, and the output data is the translation result displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messaging apps and social media, accurate translations based on context were often not provided when users communicated in different languages. In addition, in virtual stores, users were not provided with appropriate translations when searching for product information or contacting customer support, resulting in a poor user experience.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in Language" button generating means arranged next to the message sending means, a means for automatically translating the message into a language when the "Send in Language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for providing an optimal translation based on context when a user searches for product information or makes an inquiry to customer support in a virtual store. This allows accurate translations based on context to be provided when users communicate in different languages, improving the user experience in the virtual store.

"Message sending means" is a function that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Transmission means" is a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the message entered by the user and selects the translation that best suits that context.

A "virtual store" is a virtual store that offers products and services over the Internet.

"Means for searching product information" refers to a function that enables users to search for information about products and services offered in the virtual store.

"Means to contact customer support" refers to a feature that allows users to report questions or issues to the virtual store's support team.

To implement this invention, the following system configuration is required. The system includes a message sending means, a language send button generating means, an automatic translation means, a sending means, a means for selecting the optimal translation based on the context, a means for searching for product information in a virtual store, and a means for making an inquiry to customer support.

The server receives the message entered by the user and uses a generative AI model to provide the best translation based on the context. Specifically, it uses Hugging Face's Transformers library to translate from English to Japanese. Once the user enters a message, it is sent to the server, which uses the generative AI model to translate it based on the context.

The terminal provides an interface for the user to input and send a message. The terminal includes a message sending means and a send in language button generating means, and allows the user to send a message in a language selected by the user. When the user presses the "send in language" button, the message is automatically translated and sent to other users via the sending means.

As a concrete example, suppose a user types "Can I return this item?" and presses the "Send in Japanese" button. In this case, the server uses the generative AI model to translate it to "Can I return this item?" and sends the translated message to other users via the sending means.

The same process also applies when users search for product information or contact customer support in the virtual store. For example, if a user types "I need help with my order" to contact the support team, the server translates it to "I need help with my order" and provides the appropriate support.

An example of a prompt to input to the generative AI model could be "Translate the following English sentence to Japanese considering the context: 'I need help with my order.'" Using this prompt, the server can provide the best translation based on the context.

The flow of the specific processing in application example 3 is explained using Figure 16.

Step 1:

The user types a message at the terminal. The user types a text message using the message sending means and presses the send button in the language. The input is the user's text message and the output is the typed message displayed at the terminal.

Step 2:

The terminal sends the entered message to the server. The terminal sends the entered message to the server along with send button information in the language pressed by the user. The input is the user's text message and the selected language, and the output is the message data sent to the server.

Step 3:

The server receives the message and performs a translation based on the context. The server analyzes the received message and uses a generative AI model to perform the optimal translation based on the context. The input is the message data sent to the server, and the output is the translated message. Specifically, the translation is performed using Hugging Face's Transformers library.

Step 4:

The server sends the translated message to the terminal. The server sends the translated message to the terminal and displays it to the user. The input is the translated message and the output is the translated message sent to the terminal.

Step 5:

The terminal displays the translated message and transmits it to other users through the transmission means. The terminal displays the translated message to the user and, after the user has confirmed it, transmits the message to other users through the transmission means. The input is the translated message and the output is the message transmitted to other users.

Step 6:

Checks the message received by other users. Other users check the received message and reply if necessary. The input is the received message and the output is the other users' checked message.

In this way, messages entered by users are optimally translated based on the context and accurately conveyed to other users.

Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

"Example 1"

As one embodiment of the present invention, a message translation system incorporating an emotion engine is provided. In this system, when a user types a message in a messenger app or SNS, the emotion engine recognizes the user's emotion. The emotion engine infers the user's emotion from, for example, the context of the user's message, the use of emojis, typing speed, etc. Then, the translation of the message is adjusted based on that emotion. For example, if the user types "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!".

"Example 2"

In another embodiment of the present invention, a system is provided that includes emotion recognition means for an emotion engine to recognize an emotion of a user, and emotion adjustment means for adjusting the translation of a message based on the recognized emotion. The emotion recognition means infers the emotion of the user from the context of the user's message, the use of emojis, typing speed, etc. The emotion adjustment means adjusts the translation of the message based on the recognized emotion. For example, if the user types "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

"Example 3"

Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. In this system, the emotion engine recognizes a user's emotion and adjusts the translation of a message based on the emotion. For example, if the user inputs "Today is the best day ever!" and the emotion engine recognizes joy, the message is translated into a more positive expression, "Today is the best day ever!". On the other hand, if the user inputs "Today is the worst day..." and the emotion engine recognizes sadness, the message is translated into a more negative expression, "Today is the worst day...".

The process flow for each example is explained below.

"Example 1"

Step 1: The user types a message in a messenger app or on a social networking site.

Step 2: The emotion engine infers the user's emotion from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

"Example 2"

Step 1: User enters message.

Step 2: The emotion recognition tool infers the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Step 3: The emotion adjustment mechanism adjusts the translation of the message based on the recognized emotion.

"Example 3"

Step 1: User enters message.

Step 2: The emotion engine recognizes the user's emotions.

Step 3: The emotion engine adjusts the translation of the message based on the emotion it recognizes.

(Example 1)

Next, a first embodiment of the first embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messenger apps and SNS, when users translated and sent messages into other languages, the quality of the translation often lacked emotional expression, and there was a problem that the user's intentions and feelings were not conveyed accurately. In addition, it was inconvenient for users to translate manually, which was time-consuming.

The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a message sending means, a "send in specific language" button generating means, a means for automatically translating the message into a specific language when the "send in specific language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the emotion of the user, and a means for adjusting the translation based on the result of the emotion recognition means. This makes it possible to send a high-quality translated message that reflects the emotion of the user.

"Message sending means" is a function that provides an interface for users to input and send messages.

The "means for generating a send button in a specific language" is a function that generates a button that is placed next to the message input field and allows the user to send a message in a specific language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specific language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

The "translation adjustment means" is a function that adjusts the expression of a translated message based on the results of the emotion recognition means.

Form for implementing the invention

This invention is a system that places a "Send in specific language" button on the message sending screen of a messenger app or SNS, and when a user inputs a message and presses the "Send in specific language" button, the input message is automatically translated into the specific language and the translated message is sent. It also includes a function that recognizes the user's emotions and adjusts the translation based on those emotions by combining it with an emotion engine.

Hardware and software used

Hardware:

Device: The device on which the user types messages (smartphone, tablet, PC, etc.)

Server: A remote server for message translation and emotion recognition.

Software:

Messenger apps and social media applications

Emotion engine (e.g. EmotionAI)

Translation API (e.g. Google Translate API, DeepL API)

Data processing and data calculations

1. Get message:

The device retrieves the message entered by the user.

2. Emotion recognition:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

3. Message translation:

The server translates the message into a specific language containing the appropriate emotional expression based on the results of the emotion engine.

4. Sending a translated message:

The device will then send the translated message.

Specific examples

When a user types "Today is the best day ever!" into a messenger app and presses the "Send in specific language" button, the process goes like this:

1. The user types, "Today is the best day ever!".

2. The user presses the "Send in specific language" button.

3. Your device will receive the message "Today is a great day!"

4. The server uses "EmotionAI" to recognize the emotion of joy from the message.

5. The server uses the Google Translate API to translate "Today is the best day ever!" to "Today is the best day ever!".

6. The device sends the message "Today is the best day ever!".

Example of a prompt

"Design a system that translates messages typed by users in a messenger app into a specific language and adjusts the message to the appropriate wording based on emotion. For example, if a user types, 'Today is the best day ever!', the emotion engine should recognize joy and translate the message to, 'Today is the best day ever!'"

In this way, a system is realized that appropriately translates and sends messages entered by users based on emotions.

The flow of the identification process in Example 1 is explained using Figure 17.

Step 1:

The user enters a message into the message input field of a messenger app or social networking site.

Input: User types "Today is the best day ever!"

Specific action: The user types a message using a keyboard or touchscreen.

Output: "Today is the best day ever!" is displayed in the message input field.

Step 2:

The user presses the "Send in specific language" button located next to the message input field.

Input: User clicks the "Submit in specific language" button.

Specific action: The user presses a button using a mouse or touch screen.

Output: An event occurs when the button is pressed.

Step 3:

The device retrieves the message entered by the user.

Input: The event of a button being pressed and the input message "Today is the best day ever!".

Specific operation: The device reads text data from the message input field.

Output: The retrieved message "Today is the best day ever!" is stored in memory.

Step 4:

The server uses an emotion engine to infer the user's emotions from the context of their message, their use of emojis, their typing speed, etc.

Input: Retrieved message: "Today is the best day ever!".

What it does: The server uses an emotion engine (e.g. EmotionAI) to analyze the message context, detect emojis, and analyze typing speed.

Output: The emotion engine recognizes the user's emotion as "joy".

Step 5:

The server translates the message into a specific language with the appropriate emotional expression based on the results of the emotion engine.

Input: Emotion engine result "Joy" and original message "Today is a great day!".

Specific operation: The server uses a translation API (e.g. Google Translate API) to perform translation that takes emotional expressions into account.

Output: The translated message "Today is the best day ever!".

Step 6:

The device will then send the translated message.

Input: Translated message: "Today is the best day ever!".

Specific operation: The device uses the message sending function to send the translated message.

Output: The sent message "Today is the best day ever!" will appear in the recipient's message inbox.

(Application example 1)

Next, application example 1 of embodiment example 1 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

When users send messages in different languages on traditional messaging apps and social media, the quality of the translation often does not accurately reflect their emotions, lowering the quality of communication. In addition, because the translation does not take into account the user's emotions, there is a risk of misunderstandings and discomfort.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 1 is realized by the following means. In this invention, the server includes a message sending means in a messenger app or SNS, a "Send in XXX language" button generating means arranged next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion analysis means for analyzing the user's emotions, and a means for adjusting the translation based on the emotion analysis means. This enables a natural translation that takes the user's emotions into account.

"Messenger apps and social networking sites" are software applications that allow users to send and receive text messages, images, videos, etc.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

"Means for generating a send button in XX language" is a function that generates a button that allows a user to send a message in a specific language.

"Means for automatic translation" refers to a function that automatically translates a message entered by a user into a specified language.

"Means for sending automatically translated messages" refers to a function for sending translated messages to other users.

"Emotion analysis means" refers to a function that analyzes a user's emotions from messages entered by the user and other information.

The "means for adjusting the translation" refers to a function for adjusting the translated message based on the emotional information obtained by the emotional analysis means.

To implement this invention, it is necessary to build a system that takes emotions into account when a user sends a message in a messenger app or on a social networking site. This system includes the following main components:

1. Means of sending messages

It provides an interface for users to type and send messages. This can be a messaging app or social networking application that runs on a device such as a smartphone or computer.

2. How to generate a "Send in XX language" button

Creates a "Send in XXX" button that is placed next to the message sending method. This button allows the user to send a message in a specific language. It is automatically selected from the available languages based on the user's preferences.

3. Means of automatic translation

When a user presses the "Send in XXX language" button, the entered message is automatically translated into the specified language. This function is achieved using a generative AI model. Specifically, a translation model using the Transformers library is used.

4. How to send automatically translated messages

Send the translated message to other users. This feature will also be implemented as part of a messaging app or social networking application.

5. Sentiment analysis methods

Analyze user sentiment from messages entered by users and other information. This function is achieved using a generative AI model. Specifically, a sentiment analysis model using the Transformers library is used.

6. Ways to adjust translations

Adjust the translated message based on the emotional information obtained by the emotion analysis means. For example, if positive emotions are detected, change the translated message to a more positive expression.

Hardware and software used

Hardware: servers (cloud servers or on-premise servers), smartphones, computers

Software: Python, Flask, Transformers library

Specific examples

When a user types "Today is the best day ever!" and presses the "Send in English" button, the sentiment analyzer recognizes the joy and the message is translated and sent as "Today is the best day ever!".

Example of a prompt

"Today is the best day!"

The flow of the specific processing in application example 1 is explained using Figure 18.

Step 1:

The user opens a messenger app or social networking application and types a message. The typed message is saved in text format on the device.

Step 2:

The user presses the "Send in XXX language" button. This action causes the device to send the entered message to the server. The data sent includes the message text and the user's selected language.

Step 3:

The server passes the received message text to a sentiment analyzer, which uses a generative AI model to analyze the sentiment of the message. The input is the message text and the output is a sentiment label (e.g. positive, negative, neutral).

Step 4:

The server passes the message text to the translation means based on the emotion label obtained from the emotion analysis means. The translation means translates the message into the specified language using a generative AI model. The input is the message text and the emotion label, and the output is the translated message text.

Step 5:

The server adjusts the translated message text based on the emotion label. For example, if a positive emotion is detected, it changes the translated message to a more positive expression. The input is the translated message text and the emotion label, and the output is the adjusted message text.

Step 6:

The server sends the adjusted message text to the terminal. The terminal displays the received message and sends it to other users. The input is the adjusted message text, and the output is the displayed and sent message.

(Example 2)

Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

In conventional messaging apps and social media, when users wanted to send messages in a different language, they had to translate them manually, which was a time-consuming process. In addition, because the translation was done without taking into account the user's feelings, there was a risk that unintended nuances would be conveyed. This led to a problem of a decline in the quality of communication.

The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "Send in XXX language" button generating means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing the user's emotion, and an emotion adjustment means for adjusting the translation of the message based on the recognized emotion. This makes it possible to automatically select a language frequently used by the user and provide an appropriate translation according to the emotion.

"Message sending means" is a function that allows a user to send a message entered by the user to other users.

The "means for generating a send button in XX language" is a function that automatically selects an appropriate language from available languages based on the user's settings, and generates a button for sending a message in that language.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" is a function that infers a user's emotions from the context of the message entered by the user, the use of emojis, typing speed, etc.

"Emotion adjustment means" is a function that adjusts the translation of a message based on the recognized emotions of the user.

This invention is a system that reduces the effort required for users to send messages in different languages and provides appropriate translations according to emotions. A specific embodiment of this system is described below.

Hardware and software used

Server: Responsible for data processing and storage. Specifically, it uses cloud services (e.g. AWS (registered trademark), Google Cloud Platform).

Device: The device used by the user. This includes smartphones, tablets, PCs, etc.

Generative AI model: A model for performing natural language processing. For example, OpenAI's GPT-3 or GPT-4 (registered trademark) are used.

Emotion engine: An engine for recognizing user emotions. For example, using IBM Watson's emotion analysis API.

System processing flow

1. User language settings

Users select the language they frequently use in the application settings screen.

The device sends the selected language information to the server.

The server stores the received language information in a database.

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

2. Create a language selection button

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

3. Enter your message

The user enters text into the message input field.

The device sends the entered message to the server in real time.

What it does: When a user types "Today is the worst day...", the text is instantly sent to the server.

4. Emotion Recognition

The server sends the received message to the emotion engine.

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

The server receives the results from the emotion engine and stores the emotion information.

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

5. Translation adjustments

The server sends a translation request to the generative AI model based on the recognized emotion.

The generative AI model generates appropriate translations based on emotions.

The server sends the generated translation to the device.

Specific operation: The generative AI model generates the translation "Today is the worst day..." and the server sends it to the device.

6. Sending a message

The user presses the "Send in French" button.

The device sends the translated message to the server.

The server receives the message and sends it to the specified recipient.

Specific operation: When the user presses the "Send in French" button, the device sends the message "Aujourd'hui est le pire jour..." to the server, which then sends it to the recipient.

Example of a prompt

"Please explain the function that allows users to set their frequently used language and automatically generate the submit button in that language on subsequent visits."

"Please explain the functionality that recognizes user emotions and adjusts the translation of the message based on the recognized emotion."

To improve user convenience, the system automatically selects frequently used languages and provides appropriate translations according to sentiment.

The flow of the identification process in Example 2 is explained using Figure 19.

Step 1:

Users select the language they frequently use in the application settings screen.

Input: The language selected by the user in the settings screen (e.g. French)

Output: Selected language information

Specific operation: When the user selects "French" on the settings screen and presses the save button, the device sends that information to the server.

Step 2:

The device sends the selected language information to the server.

Enter: Selected language information

Output: Language information sent to the server

Specific operation: The device sends the user's selected language information to the server.

Step 3:

The server stores the received language information in a database.

Input: Language information sent to the server

Output: Language information stored in the database

Specific operation: The server stores the language information it receives in the database.

Step 4:

The server will generate a submit button in the appropriate language the next time the user accesses the site based on the user's language setting information.

Input: Language information stored in the database

Output: Submit button information in generated language

Specific behavior: The server retrieves language information from the database and generates information for the "Submit in French" button.

Step 5:

Based on the information the device receives from the server, it displays a "Send in French" button on the user interface.

Input: Submit button information for generated language

Output: A submit button displayed in the user interface.

Specific behavior: When the user restarts the app, the device retrieves information about the "Send in French" button from the server and displays it on the screen.

Step 6:

The user enters text into the message input field.

Input: A message typed by the user (e.g., "Today is the worst day...")

Output: The message entered

Specific action: User types, "Today is the worst day..."

Step 7:

The device sends the entered message to the server in real time.

Input: Message entered

Output: Message sent to server

Specific operation: The device sends the entered message to the server.

Step 8:

The server sends the received message to the emotion engine.

Input: Message sent to server

Output: Message sent to emotion engine

Specific operation: The server sends the received message to the emotion engine.

Step 9:

The emotion engine infers a user's emotions from the context of the message, use of emojis, typing speed, and more.

Input: Message sent to emotion engine

Output: Inferred emotion information (e.g. sadness)

Specific behavior: The emotion engine recognizes "sadness" from the message "Today is the worst day..."

Step 10:

The server receives the results from the emotion engine and stores the emotion information.

Input: Inferred emotion information

Output: Stored emotion information

Specific operation: The server receives emotion information from the emotion engine and stores it in the database.

Step 11:

The server sends a translation request to the generative AI model based on the recognized emotion.

Input: Stored emotion information, user message

Output: Translation request sent to generative AI model

Specific operation: The server sends emotion information and the user's message to the generative AI model.

Step 12:

The generative AI model generates appropriate translations based on emotions.

Input: Translation request sent to generative AI model

Output: Generated translation (e.g. "Today is the worst day...")

Specific behavior: The generative AI model generates the translation "Today is the worst day..."

Step 13:

The server sends the generated translation to the device.

Input: Generated translation

Output: Translation sent to device

Specific operation: The server sends the generated translation to the device.

Step 14:

The user presses the "Send in French" button.

Input: User operation

Output: Send button press information

Specific action: The user presses the "Send in French" button.

Step 15:

The device sends the translated message to the server.

Input: Send button press information, generated translation

Output: The translated message sent to the server

Specific action: The device sends the message "Aujourd'hui est le pire jour..." to the server.

Step 16:

The server receives the message and sends it to the specified recipient.

Input: Translation message sent to server

Output: Message sent to recipient

Specific operation: The server sends the translated message to the recipient.

(Application example 2)

Next, application example 2 of embodiment example 2 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

Existing messenger apps and SNS lack the ability to automatically select the language frequently used by the user or adjust the translation of messages based on the user's emotions, limiting the user experience. There is also a demand for more natural and appropriate communication by recognizing the user's emotions and adjusting the translation based on them. Furthermore, content distribution services also face the challenge of improving the viewing experience by adjusting subtitles and audio translations based on the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 2 is realized by the following means.

In this invention, the server includes a message sending means for a messenger app or SNS, a "Send in XXX language" button generating means placed next to the message sending means, a means for automatically translating the message into XXX language when the "Send in XXX language" button is pressed, a means for sending the automatically translated message, an emotion recognition means for recognizing a user's emotion, an emotion adjustment means for adjusting the translation of the message based on the recognized emotion, a language selection means for automatically selecting a language based on the user's settings and past usage history, and a translation adjustment means for adjusting the translation of subtitles and audio based on the user's emotion. This makes it possible to automatically select a language frequently used by the user and adjust the translation of messages and content based on the user's emotion.

"Message sending means" refers to an interface that allows users to input and send messages.

The "means for generating a send button in a specific language" is a function that automatically generates a button for sending a message in a specific language based on the user's settings and usage history.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified language.

"Emotion recognition means" refers to technology for recognizing emotions from user input, facial expressions, voice, etc.

"Emotion adjustment means" is a function that adjusts the translation or display of a message based on the recognized emotion.

"Language selection means" is a function that automatically selects the most appropriate language based on the user's settings and past usage history.

"Translation adjustment means" is a function that adjusts the translation of subtitles and audio based on the user's emotions.

The following system configuration is described as a form for implementing this invention.

System configuration

This system includes a means for sending messages in messenger apps and SNS, a means for generating send buttons in a certain language, an automatic translation means, an emotion recognition means, an emotion adjustment means, a language selection means, and a translation adjustment means.

Method of sending message

An interface that allows users to input and send messages. It is implemented as an application on a smartphone or PC.

How to generate a send button in XX language

This function automatically generates buttons for sending messages in a specific language based on the user's settings and usage history. It automatically selects the language the user frequently uses and displays it as a button.

Automatic translation methods

This function automatically translates messages entered by users into a specified language. It is implemented using a translation API such as Google Translator.

Emotion recognition means

This is a technology for recognizing emotions from user input, facial expressions, voice, etc. It uses software such as OpenCV and EmotionRecognizer to analyze data from the camera and microphone.

Methods of emotion regulation

This feature adjusts the translation and display of messages based on the recognized emotion. For example, if the user has a sad expression, the translated message will be adjusted accordingly.

Language selection method

This function automatically selects the most suitable language based on the user's settings and past usage history. Content from the next time onwards will also be automatically selected based on the user's viewing history and settings information.

Translation adjustment methods

This feature adjusts subtitle and audio translations based on the user's emotions. For example, if the user looks sad, the subtitle translation will be adjusted accordingly.

Program processing explanation

The server captures data from the camera and microphone and recognizes the user's emotions using OpenCV and EmotionRecognizer. Based on the recognized emotions, it translates the message using a translation API such as Google Translator and displays the message adjusted by the emotion adjustment means. Based on the user's settings and past usage history, the language selection means automatically selects the most suitable language.

Specific examples

If a user frequently speaks French, the application will automatically provide content in French. And if the user has a sad expression, the subtitle translation will adjust accordingly.

Example of a prompt

Develop a smartphone application that automatically selects the language that the user frequently uses and uses an emotion engine to recognize the user's emotions and adjust the translation accordingly. For example, if the user frequently uses French, the application automatically provides content in French. Also, if the user has a sad expression, the subtitle translation will be adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

The flow of the specific processing in application example 2 is explained using Figure 20.

Step 1:

The server captures the user's video and audio data from the device through the camera and microphone. The input is the user's video and audio data, and the output is the captured raw data. This data is used in subsequent processing steps.

Step 2:

The server analyzes the captured video and audio data using OpenCV and EmotionRecognizer to recognize the user's emotions. The input is the captured raw data, and the output is the recognized emotional information. Specifically, it analyzes the user's facial expressions and tone of voice, and classifies emotions into "happiness," "sadness," "anger," etc.

Step 3:

The server uses a language selection means to automatically select the most appropriate language based on the user's settings and past usage history. The input is the user's settings information and usage history, and the output is the selected language information. Specifically, the language that the user frequently uses is obtained from the database and applied to the next and subsequent content.

Step 4:

The user enters a message and presses the send button. The input is the message entered by the user, and the output is the event information that the send button has been pressed. Specifically, this includes the action of the user entering a message into a text box and pressing the "Send in XX language" button.

Step 5:

When the send button is pressed, the server uses a translation API such as Google Translator to automatically translate the entered message into the selected language. The input is the message entered by the user and the selected language information, and the output is the translated message. Specifically, the message and target language are sent to the API and the translation result is received.

Step 6:

The server adjusts the translated message based on the recognized emotion with an emotion adjustment means. The input is the translated message and the recognized emotion information, and the output is the adjusted message. Specifically, if the user is expressing a sad emotion, the translated message is adjusted to be more negative accordingly.

Step 7:

The server sends the adjusted message through the message sending means. The input is the adjusted message and the output is the sent message. Specifically, the server sends the adjusted message to the recipient and displays a notification of the completion of the sending on the user's interface.

Step 8:

The server adjusts the subtitle and audio translations in the content delivery service based on the user's emotions. The input is the user's emotional information and content data, and the output is the adjusted subtitles and audio. Specifically, if the user has a sad expression, the subtitle translation is adjusted accordingly.

In this way, a system can be created that provides optimal content based on the user's preferences and emotions.

(Example 3)

Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

Conventional message translation systems perform simple translations without considering the context or emotions of the message entered by the user, which often results in inappropriate translations. In addition, there is a problem that the quality of communication declines because the translation cannot reflect the user's emotions. This creates an issue in that it becomes difficult to convey the exact meaning and emotions intended by the user.

The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

In this invention, the server includes a message sending means, a "send in translation language" button generating means located next to the message sending means, a means for automatically translating the message into the translation language when the "send in translation language" button is pressed, a means for sending the automatically translated message, a context analysis means for selecting an optimal translation based on the context of a message input by a user, and an emotion analysis means for recognizing the user's emotion and adjusting the translation based on that emotion. This makes it possible to provide an optimal translation of a user's input message based on the context and emotion.

"Message sending means" is a function for sending messages entered by a user to other users.

The "means for generating a send button in a translated language" is a function for generating a button for sending a message in a translated language selected by the user.

"Automatic translation means" is a function that automatically translates a message entered by a user into a specified translation language.

"Context analysis means" is a function that analyzes the context of the message entered by the user and selects the most appropriate translation based on that context.

"Sentiment analysis means" is a function that recognizes the emotion of the message entered by the user and adjusts the translation based on that emotion.

"Transmission means" is a function for sending translated messages to other users.

"User settings" are settings that users make to customize system behavior, translation languages, etc.

"Translation language" is the language the user uses to translate the message.

Form for implementing the invention

This invention is a system that provides an optimal translation of a message entered by a user based on the context and emotion. A specific embodiment of this system is described below.

System configuration

The system mainly consists of the following components:

1. Means of sending messages

2. How to generate a send button in a translated language

3. Automatic translation methods

4. Contextual analysis methods

5. Sentiment analysis methods

6. Transmission method

Hardware and software used

The server uses the following hardware and software to receive, parse, translate, and send messages:

Server hardware: A server with a powerful processor and sufficient memory

Software: Python, NLTK library, Google Natural Language API

The device uses the following hardware and software to allow users to enter messages and display translation results:

Device hardware: smartphones, tablets, PCs, etc.

Software: Messenger apps, SNS apps

System operation

The user inputs a message into an input field on the terminal. For example, the user inputs "I'm fine." The terminal sends this message to the server. The server sends the received message to the context analysis means, which analyzes the context of the message. The context analysis means analyzes the context using, for example, Python's NLTK library, and translates the message "I'm fine." into "I'm fine."

The server then sends the translation to the sentiment analyzer, which uses Google's Natural Language API to analyze the sentiment of the message. For example, if the user types "Today is the best day ever!" and the sentiment analyzer recognizes joy, the translation is adjusted to "Today is the best day ever!".

Finally, the server sends the adjusted translation result to the terminal, and the terminal displays the translation result to the user. The user can check the translation result on the terminal screen.

Specific examples

As a concrete example, consider the case where a user types "I'm fine" into a terminal. This message is sent to the server, where the context analysis means translates it as "I'm fine." If the user then types "Today is the best day ever!", the emotion analysis means will recognize the joy, and the server will translate it as "Today is the best day ever!".

Example of a prompt:

If a user types "I'm fine," choose the appropriate translation based on the context and analyze the sentiment using sentiment analysis tools.

If a user types "Today is a great day!", use sentiment analysis to recognize the sentiment and choose the appropriate translation.

This system supports more natural and appropriate communication by providing an optimal translation of the user's input message based on the context and emotion. The flow of the specific process in Example 3 is explained with reference to FIG. 21.

Step 1:

The user types a message.

The user enters a message into the input field of the terminal. For example, the user enters "I'm fine." The entered message is passed to the terminal's message sending means.

Step 2:

The device sends the message to the server.

The terminal sends the message entered by the user to the server. At this time, the message is sent as an HTTP request. The input is the user's message, and the output is an HTTP request to the server.

Step 3:

The server receives the message and sends it to the context analysis means.

The server sends the received message to the contextual analyzer, which analyzes the context using, for example, Python's NLTK library. The input is the user's message and the output is the data to the contextual analyzer.

Step 4:

The contextual analysis means analyzes the context of the message and selects the appropriate translation.

The contextual analysis means analyzes the context of the message and selects the appropriate translation. For example, the message "I'm fine." is translated as "I'm fine." The input is the user's message and the output is the translation result.

Step 5:

The server sends the translation results to the sentiment analysis means.

The server transmits the translation results obtained from the context analysis means to the sentiment analysis means. The sentiment analysis means analyzes sentiment using, for example, Google's (registered trademark) Natural Language API. The input is the translation result, and the output is data to the sentiment analysis means.

Step 6:

Sentiment analysis tools analyze the sentiment of the message and adjust the translation.

The sentiment analyzer analyzes the sentiment of the message and adjusts the translation. For example, if the message "Today is the best day ever!" is recognized as expressing joy, the translation is adjusted to "Today is the best day ever!". The input is the translation and the output is the adjusted translation.

Step 7:

The server sends the final translation results to the device.

The server sends the final translation result obtained from the sentiment analysis means to the terminal. At this time, the translation result is sent as an HTTP response. The input is the adjusted translation result, and the output is the HTTP response to the terminal.

Step 8:

The device displays the translation results to the user.

The terminal displays the translation results received from the server to the user. The user can check the translation results on the terminal screen. The input is the translation result from the server, and the output is what is displayed to the user.

(Application example 3)

Next, application example 3 of embodiment example 3 will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

Conventional message translation systems perform translation without considering the context or emotion of the message entered by the user, resulting in unnatural translations or failure to accurately convey the user's intent. In addition, since translations cannot reflect emotion, it is difficult to properly convey the user's emotions.

The specific processing by the specific processing unit 290 of the data processing device 12 in application example 3 is realized by the following means. In this invention, the server includes a message sending means, a "Send in language" button generating means located next to the message sending means, a means for automatically translating the message into a language when the "Send in language" button is pressed, a means for sending the automatically translated message, a means for selecting an optimal translation based on the context of a message input by a user, and a means for recognizing the user's emotion using an emotion engine and adjusting the translation based on that emotion. This enables a natural and appropriate translation that takes into account the context and emotion of the message input by the user.

"Message sending means" refers to an interface that allows users to input text messages and send them to other users.

The "send in language button generation means" is a function that generates a button for sending a message in the language selected by the user.

"Means for automatic translation" refers to a function that automatically translates an input message into a specified language.

"Means for sending automatically translated messages" refers to a function for sending automatically translated messages to other users.

"Means for selecting the best translation based on context" refers to a function that analyzes the context of the input message and selects the translation that best suits that context.

The "emotion engine" is a system that recognizes emotions from the message entered by the user and adjusts the translation based on those emotions.

"Means for adjusting a translation based on emotion" refers to a function for adjusting a translated message based on a user's emotion as recognized by an emotion engine.

A system for implementing the present invention includes a message sending means, a language send button generating means, a means for automatic translation, a means for sending the automatically translated message, a means for selecting an optimal translation based on context, an emotion engine, and a means for adjusting the translation based on emotion.

System configuration

The server uses the following hardware and software:

Hardware: The server uses a computer system with a high-performance processor and sufficient memory. Specifically, Intel Xeon processors and AMD EPYC processors are suitable.

Software: The server uses the Python programming language and the transformers natural language processing library. It also uses the nltk library for sentiment analysis.

Processing flow

1. Message sending means: Provides an interface for users to enter text messages. This is an application that runs on a mobile device such as a smartphone or tablet.

2. Send in language button generator: Generates a button to send a message in the language selected by the user. This button is automatically selected based on the user's settings.

3. Means of automatic translation: Automatically translate messages entered by users into a specified language. This translation is done using a generative AI model.

4. How to send an automatically translated message: Send an automatically translated message to other users.

5. A means to select the best translation based on context: Analyze the context of the message entered by the user and select the translation that best suits that context.

6. Emotion engine: Recognizes emotions from the user's input message and adjusts the translation based on those emotions.

7. Means to tailor translation based on emotion: Adjust the translated message based on the user's emotion as recognized by the emotion engine.

Specific examples

For example, if a user is watching a movie and a character says, "I'm so happy today!", the emotion engine will recognize the positive emotion and adjust the translation to "I'm so happy today!".

Example of a prompt to input to the generative AI model:

"Translate the following text to Japanese and adjust the translation based on the detected emotion: 'I'm so happy today!'"

In this way, the user's viewing experience can be enriched.

The flow of the specific processing in application example 3 is explained using Figure 22.

Step 1:

The user enters a message on the terminal. The entered message is sent to the server in text format. The input data is the text message entered by the user.

Step 2:

The server analyzes the received messages and performs natural language processing (NLP) to understand the context. For this processing, it uses the transformers library. The input data is the text message entered by the user, and the output data is the analysis result including contextual information.

Step 3:

The server uses a generative AI model to generate an optimal translation based on the analysis results. Specifically, it uses a translation model from the transformers library to translate the message into the specified language. The input data is the analysis results including contextual information, and the output data is the translated text message.

Step 4:

The server passes the translated message to an emotion engine to recognize the user's emotion. The emotion engine uses the nltk library. The input data is the translated text message, and the output data is the emotion label (e.g. positive, negative).

Step 5:

The server adjusts the translated message based on the emotion label. For example, for positive emotion it adds "Da yo!" to the translated message, and for negative emotion it adds "Da...". The input data are the emotion label and the translated text message, and the output data is the adjusted translated message.

Step 6:

The server sends the adjusted translation message to the terminal. The terminal displays the received message to the user. The input data is the adjusted translation message, and the output data is the text message displayed to the user.

Step 7:

The user checks the displayed message and replies if necessary. The reply message is sent again through the process from step 1. The input data is the reply message entered by the user, and the output data is the translated and adjusted reply message.

The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating the user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization.

Another example of generative AI is Gemini (Internet search <URL: https://gemini.google.com/?hl=ja>).

In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology disclosed herein is not limited to this, and the specific processing may also be performed by the robot 414.

The emotion identification model 59, which serves as an emotion engine, may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. Emotions that represent states and actions arising from mental states are arranged on the outer sides of the concentric circles. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

These emotions are distributed in the three o'clock direction of emotion map 400, and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness takes precedence over internal sensations, resulting in a sense of calm.

The inside of emotion map 400 represents what is going on inside the mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible (expressed in behavior) your emotions become.

Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery power, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions that belong to an area called "reaction" where sensation is dominant. The right half of the emotion map is lined with emotions that belong to an area called "situation" where situation recognition is dominant.

The emotion map defines two emotions that encourage learning. The first is the negative emotion around the middle of "repentance" or "reflection" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input to a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Figure 10. Figure 10 shows an example in which multiple emotions, "peace of mind," "calm," and "reassuring," have similar emotion values.

In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

In the above embodiment, an example has been described in which the specific processing program 56 is stored in the storage 32, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

The specific processing program 56 may also be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed in the computer 22 in response to a request from the data processing device 12.

It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

The various processors listed below can be used as hardware resources for executing specific processes. Examples of processors include a CPU, which is a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically to execute specific processes. All of these processors have built-in or connected memory, and all of these processors execute specific processes by using the memory.

The hardware resource that executes the specific process may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific process may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured by combining one or more CPUs with software, and this processor functions as a hardware resource that executes a specific process. Secondly, there is a configuration in which a processor is used that realizes the functions of the entire system, including multiple hardware resources that execute a specific process, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the various processors mentioned above as hardware resources.

More specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processing described above is merely an example. It goes without saying that unnecessary steps can be deleted, new steps can be added, and the processing order can be changed without departing from the spirit of the invention.

The above description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above explanation of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. Also, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

All publications, patent applications, and technical standards described in this specification are incorporated by reference into this specification to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

The following is further disclosed regarding the above embodiment.

(Claim 1)
A system including a message sending means in a messenger app or SNS, a "Send in XX language" button generating means placed next to the message sending means, a means for automatically translating the message into XX language when the "Send in XX language" button is pressed, and a means for sending the automatically translated message.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

(Claim 4)
2. The system of claim 1, wherein the automatic translation means further incorporates an emotion engine that recognizes an emotion of a user and adjusts the translation of the message based on the emotion recognized by the emotion engine.

(Claim 5)
5. The system of claim 4, wherein the emotion engine includes emotion recognition means for recognizing an emotion of a user, and emotion adjustment means for adjusting the translation of a message based on the emotion recognized by the emotion recognition means.

(Claim 6)
6. The system of claim 5, wherein the emotion adjustment means adjusts the translation of the message to a more positive expression if the recognized emotion is happiness and to a more negative expression if the recognized emotion is sadness.

"Example 1"
(Claim 1)
A message sending means;
a "send in specific language" button generating means disposed next to the message sending means;
means for automatically translating the message into a specific language when the "send in specific language" button is pressed;
means for transmitting the automatically translated message;
A means for inputting the message as a prompt sentence to a generative AI model;
means for said generative AI model to translate messages;
The system includes means for transmitting the translated message to a destination.

(Claim 2)
2. The system of claim 1, wherein the "submit in specific language" button generating means automatically selects the specific language from available languages based on a user setting.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Application example 1"
(Claim 1)
A message sending means;
A "send in XX language" button generating means disposed next to the message sending means;
A means for automatically translating the message into a certain language when the "Send in XX language" button is pressed;
means for transmitting the automatically translated message;
A voice input means;
A means for converting the voice acquired by the voice input means into text;
A means for translating the text into a certain language;
The system further includes a means for audibly outputting the translated text.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Example 2"
(Claim 1)
A means for obtaining user configuration information;
A means for sending a prompt sentence to the generative AI model based on the acquired configuration information;
A means for generating a "Submit in ____ language" button based on a response from the generative AI model;
A means for displaying the generated "Send in XXX language" button on a user interface;
A system that includes a means for sending a message when a user clicks a "Send in XXX language" button.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
The system of claim 1 , wherein the generative AI model generates a prompt sentence based on user setting information and generates an optimal language selection button.

"Application Example 2"
(Claim 1)
A message sending means;
A "send in XX language" button generating means disposed next to the message sending means;
A means for automatically translating the message into a certain language when the "Send in XX language" button is pressed;
means for transmitting the automatically translated message;
A means for obtaining user configuration information;
A means for learning frequently used languages based on the setting information;
A means for automatically generating a "Send in XXX language" button based on the learned language;
means for translating said message in real time;
The system includes a means for transmitting the translated message.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Example 3"
(Claim 1)
A message sending means;
a "send with translation" button generating means disposed next to the message sending means;
means for automatically translating the message when the "send with translation" button is pressed;
means for transmitting the automatically translated message;
means for receiving a message entered by a user;
A means of inputting messages into the generative AI model; and
A means by which the generative AI model generates a contextual translation; and
A means for receiving the generated translation result;
The system further includes a means for displaying the translation result to a user.

(Claim 2)
2. The system of claim 1, wherein the "send with translation" button generating means automatically selects a translation from available languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a message input by a user and based on the context of the message.

"Application example 3"
(Claim 1)
A message sending means;
a "send in language" button generating means disposed next to the message sending means;
means for automatically translating the message into a language when the "send in language" button is pressed;
means for transmitting the automatically translated message;
and
A means to provide optimal translations based on context when users search for product information or contact customer support in virtual stores;
A system including:

(Claim 2)
2. The system of claim 1, wherein the "submit in language" button generating means automatically selects a language from available languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Example 1 of combining emotion engines"
(Claim 1)
A message sending means;
a "send in specific language" button generating means disposed next to the message sending means;
means for automatically translating the message into a specific language when the "send in specific language" button is pressed;
means for transmitting the automatically translated message;
An emotion recognition means for recognizing an emotion of a user;
The system includes means for adjusting the translation based on results of the emotion recognition means.

(Claim 2)
2. The system of claim 1, wherein the "submit in specific language" button generating means automatically selects the specific language from available languages based on a user setting.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a message input by a user and based on the context of the message.

"Application example 1 when combining emotion engines"
(Claim 1)
A means for sending messages in a messenger app or SNS;
A "send in XX language" button generating means disposed next to the message sending means;
A means for automatically translating the message into a certain language when the "Send in XX language" button is pressed;
means for transmitting the automatically translated message;
A sentiment analysis means for analyzing a user's sentiment;
The system includes means for adjusting the translation based on the sentiment analysis means.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Example 2 of combining emotion engines"
(Claim 1)
A message sending means;
A "send in XX language" button generating means disposed next to the message sending means;
A means for automatically translating the message into a certain language when the "Send in XX language" button is pressed;
means for transmitting the automatically translated message;
An emotion recognition means for recognizing an emotion of a user;
The system includes an emotion adjustment means for adjusting the translation of the message based on the recognized emotion.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Application example 2 when combining emotion engines"
(Claim 1)
A means for sending messages in a messenger app or SNS;
A "send in XX language" button generating means disposed next to the message sending means;
A means for automatically translating the message into a certain language when the "Send in XX language" button is pressed;
means for transmitting the automatically translated message;
An emotion recognition means for recognizing an emotion of a user;
an emotion adjustment means for adjusting the translation of the message based on the recognized emotion;
A language selection means for automatically selecting a language based on a user's settings and past usage history;
The system includes a translation adjustment means for adjusting subtitle or audio translations based on user sentiment.

(Claim 2)
The system of claim 1 , wherein the "Send in XXX language" button generating means automatically selects XXX from selectable languages based on a user's settings.

(Claim 3)
2. The system of claim 1, wherein the automatic translation means selects an optimal translation based on a user-entered message and on the context of the message.

"Example 3 when combining emotion engines"
(Claim 1)
A message sending means;
a "send in translated language" button generating means disposed next to the message sending means;
means for automatically translating the message into the translation language when the "send in translation language" button is pressed;
means for transmitting the automatically translated message;
a context analysis means for selecting an optimal translation based on the context of a message input by a user;
a sentiment analysis means for recognizing a user's sentiment and adjusting the translation based on the sentiment;
A system including:

(Claim 2)
2. The system of claim 1, wherein the "send in translated language" button generating means automatically selects the translated language from among the available languages based on a user setting.

(Claim 3)
2. The system of claim 1, wherein said context analysis means selects an optimal translation based on a user-entered message and on the context of the message.

(Claim 4)
The system of claim 1 , wherein the sentiment analysis means recognizes a user's sentiment and adjusts the translation based on the sentiment.

"Application example 3 when combining emotion engines"
(Claim 1)
A message sending means;
a "send in language" button generating means disposed next to the message sending means;
means for automatically translating the message into a language when the "send in language" button is pressed;
means for transmitting the automatically translated message;
means for selecting an optimal translation based on the context of a message entered by a user;
a means for recognizing a user's emotion using an emotion engine and adjusting the translation based on the emotion;
A system including:

(Claim 2)
2. The system of claim 1, wherein the "submit in language" button generating means automatically selects a language from available languages based on a user's settings.

(Claim 3)
The system of claim 1 , wherein the emotion engine recognizes an emotion of a user and adjusts the translation of the message based on the emotion.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (3)

A means for generating a button for sending a message in a particular language;
a means for inputting the input message as a prompt sentence to a generative AI model when the button is pressed;
A means for translating an input message by the generative AI model;
means for transmitting the translated message to a destination;
A system including: 10. The system of claim 1, wherein the means for generating the button automatically selects a particular language from available languages based on a user preference. A means for generating a button for sending a message in a particular language;
means for translating an input message when the button is pressed;
means for transmitting the translated message to a destination;
A means for obtaining user configuration information;
A means for learning frequently used languages based on the setting information;
Including,
The system, wherein the means for generating buttons generates the buttons based on a learned language.

Images