JP2026018441A - system - Google Patents

Abstract

A system according to an embodiment aims to efficiently discover detailed needs and broad requirements.
[Solution] A system according to an embodiment includes a character generation unit, an opinion collection unit, a needs analysis unit, and a request analysis unit. The character generation unit creates a group of unique characters using a generation AI. The opinion collection unit collects opinions from the characters created by the character generation unit. The needs analysis unit analyzes the opinions collected by the opinion collection unit to identify specific needs. The request analysis unit analyzes the opinions collected by the needs analysis unit to identify broader requests.
[Selected Figure] Figure 1

Description

The technology disclosed herein relates to a system.

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

Japanese Patent Application Laid-Open No. 2022-180282

Conventional technology has had the challenge of making it difficult to efficiently uncover detailed needs and broad requirements in market research.

The system of this embodiment aims to efficiently discover detailed needs and broad requirements.

The system according to the embodiment comprises a character generation unit, an opinion collection unit, a needs analysis unit, and a requirements analysis unit. The character generation unit uses generation AI to create a group of unique characters. The opinion collection unit collects opinions from the characters created by the character generation unit. The needs analysis unit analyzes the opinions collected by the opinion collection unit to identify specific needs. The requirements analysis unit analyzes the opinions collected by the needs analysis unit to identify broader requirements.

The system according to the embodiment can efficiently identify both specific needs and broad requirements.

1 is a conceptual diagram illustrating an example of the 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. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a second embodiment. FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. FIG. 11 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a third embodiment. FIG. 11 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. FIG. 10 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.

Below, an example of an embodiment of a system relating to the technology disclosed herein will be described with reference to the accompanying drawings.

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

In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, a processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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).

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

In the following embodiments, the coded storage refers to one or more non-volatile storage devices that store various programs, 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) is an interface that includes a communication processor, an antenna, and the like. The communication I/F controls communication between multiple computers. Examples of communication standards that can be applied to the communication I/F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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 A alone, B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and/or B" also applies when three or more things are expressed connected by "and/or."

[First embodiment]
FIG. 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 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and 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 a pointer (e.g., a pen or a finger) to receive user input via the pointer. The microphone 38B detects the user's voice to receive user input via 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 (see Figure 2) 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 by outputting the data in a form that the user can perceive (e.g., audio and/or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact 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.

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.

Figure 2 shows an example of the main functions of the data processing device 12 and 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. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores the specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart device 14 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (prediction results, etc.) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

(Example 1)
The opinion collection system according to an embodiment of the present invention is a system that creates a group of unique characters with different ages, ways of thinking, and preferences, collects opinions from the characters, and discovers detailed needs and broad requirements. This makes it possible to quickly and inexpensively discover detailed needs and broad requirements that are often overlooked in conventional market research, thereby enabling the development of more sophisticated products.

An opinion collection system according to an embodiment includes a character generation unit, an opinion collection unit, a needs analysis unit, and a requirements analysis unit. The character generation unit creates a group of unique characters using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to generate characters with various ages, ways of thinking, and preferences. The generation AI can also use a multimodal generation AI to generate character appearances and personalities. The generation AI can also generate realistic characters based on the character's background information. For example, the text generation AI has learned large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI generates characters based on prompts such as the character's age, occupation, hobbies, and personality. The opinion collection unit collects opinions from the characters created by the character generation unit. For example, the generation AI asks the character questions about a new product concept and collects the responses. The generation AI can also generate realistic opinions and feedback based on the character's personality and background. The generation AI can also collect detailed feedback through dialogue with the character. For example, the generation AI asks open-ended questions to characters to collect their opinions. The needs analysis unit analyzes the opinions collected by the opinion collection unit to discover specific needs. For example, the generation AI identifies common needs shared by characters of a specific age group or occupation. The generation AI can also analyze the collected opinions to extract specific needs and requirements useful for product development. The generation AI can also identify requirements for specific functions or services based on the characters' opinions. For example, the generation AI uses text analysis technology to extract important keywords from the characters' opinions and identify needs based on those keywords. The requirements analysis unit analyzes the opinions collected by the needs analysis unit to discover broader requirements. For example, the generation AI identifies common requirements shared by characters of different age groups or occupations. The generation AI can also analyze the collected opinions to extract broader requirements useful for product development. The generation AI can also identify requirements based on overall user experience and market trends based on the characters' opinions. For example, the generation AI uses topic modeling technology to extract common topics from the characters' opinions and identify requirements based on those keywords. As a result, the opinion collection system according to the embodiment can create a group of unique characters, collect opinions from those characters, and discover detailed needs and broad requests. For example, the generation AI can improve the design and functionality of a product based on feedback obtained from the characters. The generation AI can also propose new product concepts based on opinions obtained from the characters. The generation AI can also develop marketing strategies based on the needs and requests obtained from the characters.

The character generation unit can refer to past market data and trend information to generate more realistic, time-appropriate characters. For example, the character generation unit's generation AI can analyze market data from the past 10 years to learn how trends have changed. For example, it can generate characters that are popular with today's young people based on fashion and technology trends. The character generation unit can also collect trending information from social media and generate characters based on that information. For example, it can set a character's hobbies and interests based on popular topics and hashtags on social media. The character generation unit can also refer to industry reports to generate characters that reflect the latest market trends. For example, it can create characters with specific occupations and lifestyles based on industry reports. In this way, by referencing past market data and trend information, it is possible to generate more realistic, time-appropriate characters.

The character generation unit is able to generate a variety of characters from a global perspective, taking into account different cultural backgrounds and regional characteristics. For example, the character generation unit's generation AI learns data from different cultural backgrounds and generates characters based on that information. For example, it can create characters that reflect traditional Japanese culture or characters that incorporate American pop culture. The character generation unit can also generate characters suitable for specific regions, taking into account regional characteristics. For example, it can create characters that live in cold regions or characters that live in tropical regions. The character generation unit can also generate characters that support multiple languages. For example, it can create characters that speak multiple languages, such as English, Japanese, and Spanish. This allows the generation AI to generate a variety of characters from a global perspective, taking into account different cultural backgrounds and regional characteristics.

The character generation unit can simultaneously generate voice or movement patterns, providing a more realistic character experience. For example, the character generation unit's generation AI can generate the character's voice, enabling dialogue with the user. For example, the character can talk to the user, creating a sense of closer familiarity. The character generation unit can also generate the character's movement patterns and display them as animations. For example, the character can perform movements such as waving, walking, and jumping. The character generation unit can also generate the character's facial expressions to express emotions. For example, the character can show expressions such as smiling, surprised, or sad. This allows the character to simultaneously generate voice and movement patterns, providing a more realistic character experience.

The character generation unit can generate a personalized character by referencing the user's past behavioral history and preferences. For example, the generation AI in the character generation unit analyzes the user's past behavioral history and generates a character based on that data. For example, a character that reflects the user's favorite places or favorite foods is created. The character generation unit can also generate a character based on the user's preferences by referencing them. For example, the character's hobbies and personality are set based on the user's favorite movies and music. The character generation unit can also generate a personalized character by referencing the user's survey results. For example, the character's appearance and personality are set based on the answers the user gives in a survey. In this way, a personalized character can be generated by referencing the user's past behavioral history and preferences.

The opinion collection unit can ask questions in an interactive format to obtain detailed feedback. For example, the generation AI can simulate a dialogue between a character and a user to ask detailed questions. For example, it can ask for specific opinions about the design of a new product. The opinion collection unit can also collect free opinions by having the generation AI ask open-ended questions to the character. For example, it can ask the character, "What do you think about this product?" to obtain detailed feedback. The opinion collection unit can also collect detailed feedback through the generation AI's dialogue with the character. For example, it can ask the character, "Please tell me more about this feature," to collect specific opinions. In this way, more detailed feedback can be obtained by asking questions in an interactive format.

The opinion collection unit can present different scenarios and collect opinions for each scenario. For example, the generation AI presents different scenarios and collects opinions from characters. For example, the generation AI can present multiple usage scenarios for a new product and ask for opinions on each. The opinion collection unit can also have the generation AI ask different questions for each scenario to obtain detailed feedback. For example, the generation AI can present scenarios for home and commercial use and collect opinions based on each scenario. The opinion collection unit can also have the generation AI analyze the opinions for each scenario and identify the needs and requests for each scenario. For example, the generation AI can analyze the opinions of characters based on different scenarios and extract specific needs. This makes it possible to present different scenarios and collect opinions for each scenario.

The opinion collection unit can collect opinions in a variety of formats using audio or video input. For example, the generation AI in the opinion collection unit uses audio input to collect opinions from a character. For example, more natural feedback can be obtained by having the user express their opinion audio. The opinion collection unit can also collect opinions from a character using video input. For example, visual feedback can be obtained by having the user express their opinion via video. The opinion collection unit can also use speech recognition technology to convert audio input into text data and analyze the opinions. For example, opinions expressed by a user via audio can be converted into text data to obtain detailed feedback. The opinion collection unit can also use video analysis technology to analyze video input and collect opinions. For example, opinions expressed by a user via video can be analyzed to obtain specific feedback. This makes it possible to collect opinions in a variety of formats using audio or video input.

The opinion collection unit can refer to the user's past feedback and ask more relevant questions. For example, the generation AI in the opinion collection unit analyzes the user's past feedback and adjusts the questions based on that data. For example, it asks detailed questions based on previous opinions. The opinion collection unit can also refer to the user's past survey results and ask questions based on them. For example, it asks highly relevant questions based on survey results that the user has previously answered. The opinion collection unit can also analyze the user's past reviews and comments and ask questions based on them. For example, it asks specific questions based on reviews and comments that the user has previously posted. This allows it to refer to the user's past feedback and ask more relevant questions.

The needs analysis unit can identify specific needs by referring to past market data and trend information. For example, the generation AI analyzes past market data and compares it with opinions obtained from characters to identify specific needs. For example, needs are extracted based on past consumer behavior data. The needs analysis unit can also identify needs by having the generation AI refer to trend information and use that information to identify needs. For example, specific needs are extracted from character opinions based on trend information on social media. The needs analysis unit can also identify needs that reflect the latest market trends by having the generation AI refer to industry reports. For example, needs for specific functions or services are identified based on industry reports. This makes it possible to refer to past market data and trend information to identify more specific needs.

The needs analysis unit can consider different scenarios and identify needs for each scenario. For example, the generation AI presents different scenarios and the needs analysis unit identifies needs based on each scenario. For example, needs are extracted by considering home and commercial scenarios. The needs analysis unit can also identify different needs for each scenario by the generation AI. For example, it can analyze the opinions of characters based on different scenarios and extract specific needs. The needs analysis unit can also identify needs for each scenario by the generation AI. For example, it can analyze the opinions of characters based on different scenarios and extract specific needs. This makes it possible to consider different scenarios and identify needs for each scenario.

The needs analysis unit can also analyze audio data or video data to identify a wider variety of needs. For example, the generation AI analyzes audio data and identifies needs based on the opinions of the characters. For example, it extracts specific needs stated by the user in the audio. The needs analysis unit can also analyze video data and identify needs based on the opinions of the characters. For example, it extracts specific needs stated by the user in the video. The needs analysis unit can also use speech recognition technology to convert audio data into text data and analyze the needs. For example, it can convert opinions stated by the user in the audio into text data and identify detailed needs. The needs analysis unit can also use video analysis technology to analyze video data and collect needs. For example, it can analyze opinions stated by the user in the video and identify specific needs. In this way, a wider variety of needs can be identified by analyzing audio data and video data as well.

The needs analysis unit can refer to the user's past feedback and identify more relevant needs. For example, the generation AI analyzes the user's past feedback and identifies needs based on that data. For example, specific needs are extracted based on previous opinions. The needs analysis unit can also refer to the user's past survey results and identify needs based on those results. For example, relevant needs are identified based on survey results previously answered by the user. The needs analysis unit can also refer to the user's past reviews and comments and identify needs based on those results. For example, specific needs are extracted based on reviews and comments previously posted by the user. This makes it possible to refer to the user's past feedback and identify more relevant needs.

The requirements analysis unit can identify a wide range of requirements from a global perspective, taking into account different cultural backgrounds or regional characteristics. For example, the generation AI learns data from different cultural backgrounds and identifies a wide range of requirements based on that information. For example, it extracts requirements that reflect traditional Japanese culture or requirements that incorporate American pop culture. The requirements analysis unit can also identify a wide range of requirements appropriate for a specific region, taking into account regional characteristics. For example, it can extract requirements for users living in cold regions or requirements for users living in tropical regions. The requirements analysis unit can also identify multilingual requirements, taking into account different cultural backgrounds and regional characteristics. For example, it can extract requirements in multiple languages, such as English, Japanese, and Spanish. This allows the generation AI to identify a wide range of requirements from a global perspective, taking into account different cultural backgrounds and regional characteristics.

The requirements analysis unit can consider different scenarios and identify a wide range of requirements for each scenario. For example, the generation AI presents different scenarios and the requirements analysis unit identifies a wide range of requirements based on each scenario. For example, the requirements analysis unit extracts requirements by considering home and commercial scenarios. The requirements analysis unit can also allow the generation AI to identify different requirements for each scenario. For example, the unit analyzes the opinions of characters based on different scenarios and extracts specific requirements. The requirements analysis unit can also allow the generation AI to analyze the requirements for each scenario and identify the needs for each scenario. For example, the unit analyzes the opinions of characters based on different scenarios and extracts specific needs. This allows the generation AI to consider different scenarios and identify a wide range of requirements for each scenario.

The request analysis unit can also analyze audio or video data to identify a wider variety of requests. For example, the generation AI analyzes audio data to identify a wider variety of requests based on the character's opinions. For example, it extracts specific requests stated by the user in the audio. The request analysis unit can also analyze video data to identify a wider variety of requests based on the character's opinions. For example, it extracts specific requests stated by the user in the video. The request analysis unit can also use speech recognition technology to convert audio data into text data and analyze the requests. For example, it can convert opinions stated by the user in the audio into text data and identify detailed requests. The request analysis unit can also use video analysis technology to analyze video data and collect requests. For example, it can analyze opinions stated by the user in the video and identify specific requests. In this way, by analyzing audio and video data as well, a wider variety of requests can be identified.

The request analysis unit can refer to the user's past feedback and identify broader, more relevant requests. For example, the generation AI analyzes the user's past feedback and identifies broader requests based on that data. For example, specific requests are extracted based on previous opinions. The request analysis unit can also refer to the user's past survey results and identify broader requests based on those results. For example, highly relevant requests are identified based on survey results previously answered by the user. The request analysis unit can also refer to the user's past reviews and comments and identify broader requests based on those results. For example, specific requests are extracted based on reviews and comments previously posted by the user. This makes it possible to refer to the user's past feedback and identify broader, more relevant requests.

The generative AI can automatically propose product designs or functions based on feedback obtained from the character. For example, the generative AI analyzes feedback obtained from the character and proposes product designs based on that data. For example, it can automatically generate designs that reflect user opinions. The generative AI can also propose product functions based on feedback obtained from the character. For example, it can automatically generate new functions that reflect user requests. The generative AI can also propose product improvements based on feedback obtained from the character. For example, it can improve the design or functions of an existing product based on user opinions. This makes it possible to automatically propose product designs and functions based on feedback obtained from the character.

The generation AI can consider different scenarios based on feedback obtained from the characters and propose designs and functions for each scenario. For example, the generation AI can present different scenarios and propose designs based on each scenario. For example, it can propose designs taking into account home and commercial scenarios. The generation AI can also propose different designs for each scenario. For example, it can analyze the character's opinions based on different scenarios and propose specific designs. The generation AI can also propose different functions for each scenario. For example, it can analyze the character's opinions based on different scenarios and propose specific functions. This makes it possible to consider different scenarios based on feedback obtained from the characters and propose designs and functions for each scenario.

Based on feedback obtained from the character, the generative AI can propose designs and functions in a wider variety of formats using audio or video input. For example, the generative AI can collect feedback from the character using audio input and propose designs based on that data. For example, it can reflect specific designs stated by the user in audio. The generative AI can also collect feedback from the character using video input and propose designs based on that data. For example, it can reflect specific designs stated by the user in video. The generative AI can also use voice recognition technology to convert audio input into text data and propose designs. For example, it can convert opinions stated by the user in audio into text data and propose detailed designs. The generative AI can also use video analysis technology to analyze video input and propose designs. For example, it can analyze opinions stated by the user in video and propose specific designs. This allows the generative AI to propose designs and functions in a wider variety of formats using audio or video input based on feedback obtained from the character.

During the product development process, generative AI can refer to past user feedback and suggest more relevant designs and features. For example, generative AI can analyze past user feedback and suggest designs based on that data. For example, it can reflect specific designs based on previous opinions. Generative AI can also refer to past user survey results and suggest designs based on them. For example, it can suggest highly relevant designs based on survey results previously answered by the user. Generative AI can also analyze past user reviews and comments and suggest designs based on them. For example, it can reflect specific designs based on reviews and comments previously posted by the user. This makes it possible to refer to past user feedback and suggest more relevant designs and features during the product development process.

The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows:

The opinion collection system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit collects and analyzes data such as what products the user has purchased in the past, what websites they have visited, and what apps they have used. This allows for an understanding of the user's behavioral patterns and more accurate opinion collection. For example, opinions on similar products can be collected based on reviews of products the user has purchased in the past. Opinions on related products and services can also be collected based on the content of websites the user frequently visits. Furthermore, data on apps used by the user can be analyzed to collect opinions on the app's functions and design. This makes it possible to collect more relevant opinions based on the user's behavioral history.

The opinion collection system can further include a device integration unit that integrates data from different devices. The device integration unit collects and integrates data from multiple devices used by a user, such as smartphones, tablets, and smartwatches. This allows for a more comprehensive understanding of user behavior and opinions. For example, based on smartphone usage history, it can determine what apps a user is using and collect opinions about those apps. It can also collect opinions about the user's health and exercise habits based on smartwatch data. Furthermore, it can determine what content a user is viewing based on tablet usage history and collect opinions about that content. This allows data from different devices to be integrated, allowing for more comprehensive collection of opinions.

The opinion collection system can further include a social network analysis unit that analyzes the user's social network. The social network analysis unit collects and analyzes data such as the types of posts the user makes on social media, the groups the user belongs to, and the friendships the user has. This allows the system to understand the user's social background and interests, and collect more relevant opinions. For example, opinions on topics the user frequently posts about on social media can be collected. It is also possible to collect opinions on related products and services based on the activity of groups the user belongs to. It is also possible to analyze the user's friendships and collect opinions on products and services used by friends. This allows the system to collect more relevant opinions based on the user's social network.

The opinion collection system can further include a purchase history analysis unit that analyzes a user's purchasing history. The purchase history analysis unit collects and analyzes data such as what products a user has purchased in the past and what services they have used. This makes it possible to understand a user's purchasing patterns and collect more relevant opinions. For example, opinions about similar products can be collected based on reviews of products the user has purchased in the past. Opinions about services the user frequently uses can also be collected. Furthermore, opinions about related products and services can be collected based on the user's purchasing history. This makes it possible to collect more relevant opinions based on the user's purchasing history.

The opinion collection system can further include a health data analysis unit that analyzes the user's health data. The health data analysis unit collects and analyzes data such as the user's heart rate, blood pressure, and sleep patterns. This makes it possible to understand the user's health condition and collect health-related opinions. For example, opinions about exercise can be collected based on fluctuations in the user's heart rate. Opinions about sleep can also be collected based on the user's sleep patterns. Furthermore, opinions about health management can be collected based on the user's blood pressure data. This makes it possible to collect more relevant opinions based on the user's health data.

The opinion collection system can further include a hobby and interest analysis unit that analyzes the user's hobbies and interests. The hobby and interest analysis unit collects and analyzes data such as the user's past hobbies and interests. This makes it possible to understand the user's hobbies and interests and collect more relevant opinions. For example, opinions about events and activities that the user has participated in in the past can be collected. Opinions about topics that the user is interested in can also be collected. Furthermore, based on the user's hobbies and interests, opinions about related products and services can also be collected. This makes it possible to collect more relevant opinions based on the user's hobbies and interests.

The processing flow for Example 1 is briefly explained below.

Step 1: The character generation unit uses generation AI to create a group of unique characters. For example, the generation AI uses text generation AI (e.g., LLM) to generate characters with various ages, ways of thinking, and preferences. The generation AI can also use multimodal generation AI to generate character appearances and personalities. The generation AI can also generate realistic characters based on the character's background information. For example, the text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI generates characters based on prompts such as the character's age, occupation, hobbies, and personality.
Step 2: The opinion collection unit collects opinions from the character created by the character generation unit. For example, the generation AI asks the character questions about a new product concept and collects the responses. The generation AI can also generate realistic opinions and feedback based on the character's personality and background. The generation AI can also collect detailed feedback through dialogue with the character. For example, the generation AI can ask the character open-ended questions to collect free opinions.
Step 3: The needs analysis unit analyzes the opinions collected by the opinion collection unit to identify specific needs. For example, the generation AI can identify needs common to characters of a particular age group or occupation. The generation AI can also analyze the collected opinions to extract specific needs and requirements that will be useful for product development. The generation AI can also identify requirements for specific functions or services based on the characters' opinions. For example, the generation AI can use text analysis technology to extract important keywords from the characters' opinions and use them to identify needs.
Step 4: The requirements analysis unit analyzes the opinions collected by the needs analysis unit to discover broader requirements. For example, the generation AI can identify common requirements shared by characters of different age groups and occupations. The generation AI can also analyze the collected opinions and extract broader requirements that are useful for product development. Based on the characters' opinions, the generation AI can also identify requirements based on overall user experience and market trends. For example, the generation AI can use topic modeling technology to extract common topics from the characters' opinions and use them to identify requirements.

(Example 2)
The opinion collection system according to an embodiment of the present invention is a system that creates a group of unique characters with different ages, ways of thinking, and preferences, collects opinions from the characters, and discovers detailed needs and broad requirements. This makes it possible to quickly and inexpensively discover detailed needs and broad requirements that are often overlooked in conventional market research, thereby enabling the development of more sophisticated products.

An opinion collection system according to an embodiment includes a character generation unit, an opinion collection unit, a needs analysis unit, and a requirements analysis unit. The character generation unit creates a group of unique characters using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to generate characters with various ages, ways of thinking, and preferences. The generation AI can also use a multimodal generation AI to generate character appearances and personalities. The generation AI can also generate realistic characters based on the character's background information. For example, the text generation AI has learned large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI generates characters based on prompts such as the character's age, occupation, hobbies, and personality. The opinion collection unit collects opinions from the characters created by the character generation unit. For example, the generation AI asks the character questions about a new product concept and collects the responses. The generation AI can also generate realistic opinions and feedback based on the character's personality and background. The generation AI can also collect detailed feedback through dialogue with the character. For example, the generation AI asks open-ended questions to characters to collect their opinions. The needs analysis unit analyzes the opinions collected by the opinion collection unit to discover specific needs. For example, the generation AI identifies common needs shared by characters of a specific age group or occupation. The generation AI can also analyze the collected opinions to extract specific needs and requirements useful for product development. The generation AI can also identify requirements for specific functions or services based on the characters' opinions. For example, the generation AI uses text analysis technology to extract important keywords from the characters' opinions and identify needs based on those keywords. The requirements analysis unit analyzes the opinions collected by the needs analysis unit to discover broader requirements. For example, the generation AI identifies common requirements shared by characters of different age groups or occupations. The generation AI can also analyze the collected opinions to extract broader requirements useful for product development. The generation AI can also identify requirements based on overall user experience and market trends based on the characters' opinions. For example, the generation AI uses topic modeling technology to extract common topics from the characters' opinions and identify requirements based on those keywords. As a result, the opinion collection system according to the embodiment can create a group of unique characters, collect opinions from those characters, and discover detailed needs and broad requests. For example, the generation AI can improve the design and functionality of a product based on feedback obtained from the characters. The generation AI can also propose new product concepts based on opinions obtained from the characters. The generation AI can also develop marketing strategies based on the needs and requests obtained from the characters.

The character generation unit can refer to past market data and trend information to generate more realistic, time-appropriate characters. For example, the character generation unit's generation AI might analyze market data from the past 10 years to learn how trends have changed. For example, it might generate characters that are popular with today's young people based on fashion and technology trends. The character generation unit can also generate characters based on social media trend information collected by the generation AI. For example, it might set a character's hobbies and interests based on popular topics and hashtags on social media. The character generation unit can also refer to industry reports to generate characters that reflect the latest market trends. For example, it might create a character with a specific occupation or lifestyle based on an industry report. In this way, by referencing past market data and trend information, it is possible to generate more realistic, time-appropriate characters.

The character generation unit can analyze the user's emotional state in real time and generate a character that corresponds to the user's emotions. For example, the character generation unit's generation AI analyzes the user's facial expressions and voice to grasp their emotional state in real time. For example, if the user is smiling, it generates a positive character. The character generation unit can also analyze the user's emotional state by collecting the user's biometric data (heart rate and electrodermal activity) with sensors. For example, it can determine whether the user is relaxed based on heart rate fluctuations and generate a character accordingly. The character generation unit can also estimate the user's emotional state by analyzing the user's text input with the generation AI. For example, if the user uses a lot of positive words, it will generate a positive character. This allows the character generation unit to analyze the user's emotional state in real time and generate a character that corresponds to their emotions.

The character generation unit is able to generate a variety of characters from a global perspective, taking into account different cultural backgrounds and regional characteristics. For example, the character generation unit's generation AI learns data from different cultural backgrounds and generates characters based on that information. For example, it can create characters that reflect traditional Japanese culture or characters that incorporate American pop culture. The character generation unit can also generate characters suitable for specific regions, taking into account regional characteristics. For example, it can create characters that live in cold regions or characters that live in tropical regions. The character generation unit can also generate characters that support multiple languages. For example, it can create characters that speak multiple languages, such as English, Japanese, and Spanish. This allows the generation AI to generate a variety of characters from a global perspective, taking into account different cultural backgrounds and regional characteristics.

The character generation unit can simultaneously generate voice or movement patterns, providing a more realistic character experience. For example, the character generation unit's generation AI can generate the character's voice, enabling dialogue with the user. For example, the character can talk to the user, creating a sense of closer familiarity. The character generation unit can also generate the character's movement patterns and display them as animations. For example, the character can perform movements such as waving, walking, and jumping. The character generation unit can also generate the character's facial expressions to express emotions. For example, the character can show expressions such as smiling, surprised, or sad. This allows the character to simultaneously generate voice and movement patterns, providing a more realistic character experience.

The character generation unit can generate a personalized character by referencing the user's past behavioral history and preferences. For example, the generation AI in the character generation unit analyzes the user's past behavioral history and generates a character based on that data. For example, a character that reflects the user's favorite places or favorite foods is created. The character generation unit can also generate a character based on the user's preferences by referencing them. For example, the character's hobbies and personality are set based on the user's favorite movies and music. The character generation unit can also generate a personalized character by referencing the user's survey results. For example, the character's appearance and personality are set based on the answers the user gives in a survey. In this way, a personalized character can be generated by referencing the user's past behavioral history and preferences.

The character generation unit can use the emotion estimation function to analyze the emotions the user has when creating a character, and generate a character that elicits positive emotions. The character generation unit, for example, uses the emotion estimation function to analyze the emotions the user has when creating a character in real time. For example, if the user is smiling, a positive character is generated. The character generation unit can also use the emotion estimation function to generate a character that matches the user's emotional state. For example, if the user is relaxed, a character that can relax is generated. The character generation unit can also use the emotion estimation function to generate a character that makes the user feel positive. For example, if the user is feeling stressed, a character that can relax is generated. In this way, the emotion estimation function can be used to generate a character that elicits positive emotions from the user.

The opinion collection unit can ask questions in an interactive format to obtain detailed feedback. For example, the generation AI can simulate a dialogue between a character and a user to ask detailed questions. For example, it can ask for specific opinions about the design of a new product. The opinion collection unit can also collect free opinions by having the generation AI ask open-ended questions to the character. For example, it can ask the character, "What do you think about this product?" to obtain detailed feedback. The opinion collection unit can also collect detailed feedback through the generation AI's dialogue with the character. For example, it can ask the character, "Please tell me more about this feature," to collect specific opinions. In this way, more detailed feedback can be obtained by asking questions in an interactive format.

The opinion collection unit can analyze the user's emotional state in real time and ask questions that correspond to their emotions. For example, the generation AI in the opinion collection unit analyzes the user's emotional state in real time and adjusts the questions based on the results. For example, if the user is relaxed, it will ask more detailed questions. The opinion collection unit can also analyze the user's facial expressions and voice to grasp their emotional state. For example, if the user is smiling, it will ask positive questions. The opinion collection unit can also collect the user's biometric data (heart rate and electrodermal activity) using sensors to analyze their emotional state. For example, it can determine whether the user is relaxed based on fluctuations in heart rate and ask questions accordingly. This allows the generation AI to analyze the user's emotional state in real time and ask questions that correspond to their emotions.

The opinion collection unit can present different scenarios and collect opinions for each scenario. For example, the generation AI presents different scenarios and collects opinions from the characters. For example, the generation AI can present multiple usage scenarios for a new product and ask for opinions on each. The opinion collection unit can also have the generation AI ask different questions for each scenario to obtain detailed feedback. For example, the generation AI can present scenarios for home and commercial use and collect opinions based on each scenario. The opinion collection unit can also have the generation AI analyze the opinions for each scenario and identify the needs and requests for each scenario. For example, the generation AI can analyze the opinions of the characters based on different scenarios and extract specific needs. This makes it possible to present different scenarios and collect opinions for each scenario.

The opinion collection unit can collect opinions in a variety of formats using audio or video input. For example, the generation AI in the opinion collection unit uses audio input to collect opinions from a character. For example, more natural feedback can be obtained by having the user express their opinion audio. The opinion collection unit can also collect opinions from a character using video input. For example, visual feedback can be obtained by having the user express their opinion via video. The opinion collection unit can also use voice recognition technology to convert audio input into text data and analyze the opinions. For example, opinions expressed by a user via audio can be converted into text data to obtain detailed feedback. The opinion collection unit can also use video analysis technology to analyze video input and collect opinions. For example, opinions expressed by a user via video can be analyzed to obtain specific feedback. This makes it possible to collect opinions in a variety of formats using audio or video input.

The opinion collection unit can refer to the user's past feedback and ask more relevant questions. For example, the generation AI in the opinion collection unit analyzes the user's past feedback and adjusts the questions based on that data. For example, it asks detailed questions based on previous opinions. The opinion collection unit can also refer to the user's past survey results and ask questions based on them. For example, it asks highly relevant questions based on survey results that the user has previously answered. The opinion collection unit can also analyze the user's past reviews and comments and ask questions based on them. For example, it asks specific questions based on reviews and comments that the user has previously posted. This allows it to refer to the user's past feedback and ask more relevant questions.

The opinion collection unit can use the emotion estimation function to analyze the user's emotions when collecting opinions from the character and ask questions that elicit positive emotions. The opinion collection unit, for example, uses the emotion estimation function to analyze the user's emotions in real time and adjust the questions based on the results. For example, if the user is relaxed, it asks detailed questions. The opinion collection unit can also use the emotion estimation function to ask questions that correspond to the user's emotional state. For example, if the user is smiling, it asks positive questions. The opinion collection unit can also use the emotion estimation function to ask questions that will make the user feel positive. For example, if the user is feeling stressed, it asks questions that will help them relax. In this way, the emotion estimation function can be used to ask questions that elicit positive emotions from the user.

The needs analysis unit can identify specific needs by referring to past market data and trend information. For example, the generation AI analyzes past market data and compares it with opinions obtained from characters to identify specific needs. For example, needs are extracted based on past consumer behavior data. The needs analysis unit can also identify needs by having the generation AI refer to trend information and use that information to identify needs. For example, specific needs are extracted from character opinions based on trend information on social media. The needs analysis unit can also identify needs that reflect the latest market trends by having the generation AI refer to industry reports. For example, needs for specific functions or services are identified based on industry reports. This makes it possible to refer to past market data and trend information to identify more specific needs.

The needs analysis unit can analyze the user's emotional state in real time and identify needs based on emotions. For example, the generation AI in the needs analysis unit analyzes the user's emotional state in real time and identifies needs based on the results. For example, if the user is excited, positive needs are extracted. The needs analysis unit can also analyze the user's facial expressions and voice to grasp the emotional state. For example, if the user is smiling, positive needs are identified. The needs analysis unit can also analyze the user's emotional state by collecting the user's biometric data (heart rate and electrodermal activity) with sensors. For example, the generation AI can determine whether the user is relaxed based on fluctuations in heart rate and identify needs based on that. This makes it possible to analyze the user's emotional state in real time and identify emotional needs.

The needs analysis unit can consider different scenarios and identify needs for each scenario. For example, the generation AI presents different scenarios and the needs analysis unit identifies needs based on each scenario. For example, needs are extracted by considering home and commercial scenarios. The needs analysis unit can also identify different needs for each scenario by the generation AI. For example, it can analyze the opinions of characters based on different scenarios and extract specific needs. The needs analysis unit can also identify needs for each scenario by the generation AI. For example, it can analyze the opinions of characters based on different scenarios and extract specific needs. This makes it possible to consider different scenarios and identify needs for each scenario.

The needs analysis unit can also analyze audio data or video data to identify a wider variety of needs. For example, the generation AI analyzes audio data and identifies needs based on the opinions of the characters. For example, it extracts specific needs stated by the user in the audio. The needs analysis unit can also analyze video data and identify needs based on the opinions of the characters. For example, it extracts specific needs stated by the user in the video. The needs analysis unit can also use speech recognition technology to convert audio data into text data and analyze the needs. For example, it can convert opinions stated by the user in the audio into text data and identify detailed needs. The needs analysis unit can also use video analysis technology to analyze video data and collect needs. For example, it can analyze opinions stated by the user in the video and identify specific needs. In this way, a wider variety of needs can be identified by analyzing audio data and video data as well.

The needs analysis unit can refer to the user's past feedback and identify more relevant needs. For example, the generation AI analyzes the user's past feedback and identifies needs based on that data. For example, specific needs are extracted based on previous opinions. The needs analysis unit can also refer to the user's past survey results and identify needs based on those results. For example, relevant needs are identified based on survey results previously answered by the user. The needs analysis unit can also refer to the user's past reviews and comments and identify needs based on those results. For example, specific needs are extracted based on reviews and comments previously posted by the user. This makes it possible to refer to the user's past feedback and identify more relevant needs.

The needs analysis unit can use the emotion estimation function to analyze opinions obtained from the character and identify needs based on positive emotions. The needs analysis unit, for example, uses the emotion estimation function to analyze the character's opinions in real time and identify needs based on the results. For example, if the user is relaxed, it extracts relaxation-related needs. The needs analysis unit can also use the emotion estimation function to identify needs based on the character's emotional state. For example, if the user is smiling, it identifies positive needs. The needs analysis unit can also use the emotion estimation function to identify needs that will make the character's emotions positive. For example, if the user is feeling stressed, it identifies needs that will help them relax. In this way, it is possible to use the emotion estimation function to identify needs based on positive emotions.

The requirements analysis unit can identify a wide range of requirements from a global perspective, taking into account different cultural backgrounds or regional characteristics. For example, the generation AI learns data from different cultural backgrounds and identifies a wide range of requirements based on that information. For example, it extracts requirements that reflect traditional Japanese culture or requirements that incorporate American pop culture. The requirements analysis unit can also identify a wide range of requirements appropriate for a specific region, taking into account regional characteristics. For example, it can extract requirements for users living in cold regions or requirements for users living in tropical regions. The requirements analysis unit can also identify multilingual requirements, taking into account different cultural backgrounds and regional characteristics. For example, it can extract requirements in multiple languages, such as English, Japanese, and Spanish. This allows the generation AI to identify a wide range of requirements from a global perspective, taking into account different cultural backgrounds and regional characteristics.

The request analysis unit can analyze the user's emotional state in real time and identify a wide range of emotional requests. For example, the generation AI analyzes the user's emotional state in real time and identifies a wide range of emotional requests based on the results. For example, if the user is excited, a positive request is extracted. The generation AI can also analyze the user's facial expressions and voice to grasp the emotional state. For example, if the user is smiling, a positive request is identified. The generation AI can also collect the user's biometric data (heart rate and electrodermal activity) using sensors to analyze the emotional state. For example, the generation AI can determine whether the user is relaxed based on heart rate fluctuations and identify a wide range of emotional requests based on that. This makes it possible to analyze the user's emotional state in real time and identify a wide range of emotional requests.

The requirements analysis unit can consider different scenarios and identify a wide range of requirements for each scenario. For example, the generation AI presents different scenarios and the requirements analysis unit identifies a wide range of requirements based on each scenario. For example, the requirements analysis unit extracts requirements by considering home and commercial scenarios. The requirements analysis unit can also allow the generation AI to identify different requirements for each scenario. For example, the unit analyzes the opinions of characters based on different scenarios and extracts specific requirements. The requirements analysis unit can also allow the generation AI to analyze the requirements for each scenario and identify the needs for each scenario. For example, the unit analyzes the opinions of characters based on different scenarios and extracts specific needs. This allows the generation AI to consider different scenarios and identify a wide range of requirements for each scenario.

The request analysis unit can also analyze audio data or video data to identify a wider variety of requests. For example, the generation AI analyzes audio data to identify a wider variety of requests based on the opinions of the characters. For example, it extracts specific requests stated by the user in the audio. The request analysis unit can also analyze video data to identify a wider variety of requests based on the opinions of the characters. For example, it extracts specific requests stated by the user in the video. The request analysis unit can also use speech recognition technology to convert audio data into text data and analyze the requests. For example, it can convert opinions stated by the user in the audio into text data and identify detailed requests. The request analysis unit can also use video analysis technology to analyze video data and collect requests. For example, it can analyze opinions stated by the user in the video and identify specific requests. In this way, by analyzing audio data and video data as well, a wider variety of requests can be identified.

The request analysis unit can refer to the user's past feedback and identify broader, more relevant requests. For example, the generation AI analyzes the user's past feedback and identifies broader requests based on that data. For example, specific requests are extracted based on previous opinions. The request analysis unit can also refer to the user's past survey results and identify broader requests based on those results. For example, highly relevant requests are identified based on survey results previously answered by the user. The request analysis unit can also refer to the user's past reviews and comments and identify broader requests based on those results. For example, specific requests are extracted based on reviews and comments previously posted by the user. This makes it possible to refer to the user's past feedback and identify broader, more relevant requests.

The request analysis unit can use the emotion estimation function to analyze opinions obtained from the character and identify a wide range of requests based on positive emotions. The request analysis unit can, for example, use the emotion estimation function to analyze the character's opinions in real time and identify a wide range of requests based on the results. For example, if the user is relaxed, it extracts requests related to relaxation. The request analysis unit can also use the emotion estimation function to identify a wide range of requests based on the character's emotional state. For example, if the user is smiling, it identifies positive requests. The request analysis unit can also use the emotion estimation function to identify requests that will make the character's emotions positive. For example, if the user is feeling stressed, it identifies requests that will help them relax. In this way, the emotion estimation function can be used to identify a wide range of requests based on positive emotions.

The generative AI can automatically propose product designs or functions based on feedback obtained from the character. For example, the generative AI analyzes feedback obtained from the character and proposes product designs based on that data. For example, it can automatically generate designs that reflect user opinions. The generative AI can also propose product functions based on feedback obtained from the character. For example, it can automatically generate new functions that reflect user requests. The generative AI can also propose product improvements based on feedback obtained from the character. For example, it can improve the design or functions of an existing product based on user opinions. This makes it possible to automatically propose product designs and functions based on feedback obtained from the character.

During the product development process, generative AI can analyze a user's emotional state in real time and suggest designs and features based on their emotions. For example, generative AI can analyze a user's emotional state in real time and suggest designs based on the results. For example, if a user is relaxed, it can suggest a design that helps them relax. Generative AI can also suggest product features based on a user's emotional state. For example, if a user is excited, it can suggest positive features. Generative AI can also analyze a user's emotional state in real time and suggest product improvements based on the results. For example, if a user is feeling stressed, it can suggest a feature that helps them relax. This makes it possible to analyze a user's emotional state in real time and suggest designs and features based on their emotions during the product development process.

The generation AI can consider different scenarios based on feedback obtained from the characters and propose designs and functions for each scenario. For example, the generation AI can present different scenarios and propose designs based on each scenario. For example, it can propose designs taking into account home and commercial scenarios. The generation AI can also propose different designs for each scenario. For example, it can analyze the character's opinions based on different scenarios and propose specific designs. The generation AI can also propose different functions for each scenario. For example, it can analyze the character's opinions based on different scenarios and propose specific functions. This makes it possible to consider different scenarios based on feedback obtained from the characters and propose designs and functions for each scenario.

Based on feedback obtained from the character, the generative AI can propose designs and functions in a wider variety of formats using audio or video input. For example, the generative AI can collect feedback from the character using audio input and propose designs based on that data. For example, it can reflect specific designs stated by the user in audio. The generative AI can also collect feedback from the character using video input and propose designs based on that data. For example, it can reflect specific designs stated by the user in video. The generative AI can also use voice recognition technology to convert audio input into text data and propose designs. For example, it can convert opinions stated by the user in audio into text data and propose detailed designs. The generative AI can also use video analysis technology to analyze video input and propose designs. For example, it can analyze opinions stated by the user in video and propose specific designs. This allows the generative AI to propose designs and functions in a wider variety of formats using audio or video input based on feedback obtained from the character.

During the product development process, generative AI can refer to past user feedback and suggest more relevant designs and features. For example, generative AI can analyze past user feedback and suggest designs based on that data. For example, it can reflect specific designs based on previous opinions. Generative AI can also refer to past user survey results and suggest designs based on them. For example, it can suggest highly relevant designs based on survey results previously answered by the user. Generative AI can also analyze past user reviews and comments and suggest designs based on them. For example, it can reflect specific designs based on reviews and comments previously posted by the user. This makes it possible to refer to past user feedback and suggest more relevant designs and features during the product development process.

The generative AI can use the emotion estimation function to suggest designs and features based on positive emotions, based on feedback obtained from the character. For example, the generative AI can use the emotion estimation function to analyze the character's feedback in real time and suggest designs based on the results. For example, if the user is relaxed, it will suggest a relaxing design. The generative AI can also use the emotion estimation function to suggest product features based on the character's emotional state. For example, if the user is excited, it will suggest a positive feature. The generative AI can also use the emotion estimation function to suggest designs and features that will make the character's emotions positive. For example, if the user is feeling stressed, it will suggest a relaxing design or feature. In this way, the emotion estimation function can be used to suggest designs and features based on positive emotions, based on feedback obtained from the character.

The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows:

The opinion collection system can further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit collects and analyzes data such as what products the user has purchased in the past, what websites they have visited, and what apps they have used. This allows for an understanding of the user's behavioral patterns and more accurate opinion collection. For example, opinions on similar products can be collected based on reviews of products the user has purchased in the past. Opinions on related products and services can also be collected based on the content of websites the user frequently visits. Furthermore, data on apps used by the user can be analyzed to collect opinions on the app's functions and design. This makes it possible to collect more relevant opinions based on the user's behavioral history.

The opinion collection system can further include an emotion analysis unit that estimates the user's emotions and collects opinions based on the estimated emotions. The emotion analysis unit, for example, analyzes the user's facial expressions and voice to grasp their emotional state in real time. This makes it possible to ask questions that correspond to their emotions, such as asking detailed questions if the user is relaxed and simple questions if the user is feeling stressed. For example, if the user is smiling, positive questions can be asked, and if the user looks anxious, questions that will help them relax can be asked. The order and content of questions can also be adjusted depending on the user's emotional state. This makes it possible to collect opinions more effectively based on the user's emotions.

The opinion collection system can further include a device integration unit that integrates data from different devices. The device integration unit collects and integrates data from multiple devices used by a user, such as smartphones, tablets, and smartwatches. This allows for a more comprehensive understanding of user behavior and opinions. For example, based on smartphone usage history, it can determine what apps a user is using and collect opinions about those apps. It can also collect opinions about the user's health and exercise habits based on smartwatch data. Furthermore, it can determine what content a user is viewing based on tablet usage history and collect opinions about that content. This allows data from different devices to be integrated, allowing for more comprehensive collection of opinions.

The opinion collection system can further include a social network analysis unit that analyzes the user's social network. The social network analysis unit collects and analyzes data such as the types of posts the user makes on social media, the groups the user belongs to, and the friendships the user has. This allows the system to understand the user's social background and interests, and collect more relevant opinions. For example, opinions on topics the user frequently posts about on social media can be collected. It is also possible to collect opinions on related products and services based on the activity of groups the user belongs to. It is also possible to analyze the user's friendships and collect opinions on products and services used by friends. This allows the system to collect more relevant opinions based on the user's social network.

The opinion collection system can further include an emotion feedback unit that estimates the user's emotions and collects opinions based on the estimated emotions. The emotion feedback unit, for example, analyzes the user's facial expressions and voice to grasp the user's emotional state in real time. This makes it possible to collect feedback according to the user's emotions, such as requesting detailed feedback if the user has positive emotions and simple feedback if the user has negative emotions. For example, positive feedback is requested if the user is smiling, and relaxing feedback is requested if the user looks anxious. The content and format of the feedback can also be adjusted according to the user's emotional state. This makes it possible to collect feedback more effectively based on the user's emotions.

The opinion collection system can further include a purchase history analysis unit that analyzes a user's purchasing history. The purchase history analysis unit collects and analyzes data such as what products a user has purchased in the past and what services they have used. This makes it possible to understand a user's purchasing patterns and collect more relevant opinions. For example, opinions about similar products can be collected based on reviews of products the user has purchased in the past. Opinions about services the user frequently uses can also be collected. Furthermore, opinions about related products and services can be collected based on the user's purchasing history. This makes it possible to collect more relevant opinions based on the user's purchasing history.

The opinion collection system can further include an emotional interaction unit that estimates the user's emotions and collects opinions based on the estimated emotions. The emotional interaction unit, for example, analyzes the user's facial expressions and voice to grasp the user's emotional state in real time. This makes it possible to perform interactions according to the user's emotions, such as asking detailed questions if the user is relaxed and simple questions if the user is feeling stressed. For example, positive questions can be asked if the user is smiling, and questions that will help the user relax if the user looks anxious. The content and format of the interaction can also be adjusted according to the user's emotional state. This makes it possible to collect opinions more effectively based on the user's emotions.

The opinion collection system can further include a health data analysis unit that analyzes the user's health data. The health data analysis unit collects and analyzes data such as the user's heart rate, blood pressure, and sleep patterns. This makes it possible to understand the user's health condition and collect health-related opinions. For example, opinions about exercise can be collected based on fluctuations in the user's heart rate. Opinions about sleep can also be collected based on the user's sleep patterns. Furthermore, opinions about health management can be collected based on the user's blood pressure data. This makes it possible to collect more relevant opinions based on the user's health data.

The opinion collection system can further include an emotion monitoring unit that estimates the user's emotions and collects opinions based on the estimated emotions. The emotion monitoring unit, for example, analyzes the user's facial expressions and voice to grasp the user's emotional state in real time. This makes it possible to collect feedback according to the user's emotions, such as requesting detailed feedback if the user has positive emotions and simple feedback if the user has negative emotions. For example, positive feedback is requested if the user is smiling, and relaxing feedback is requested if the user looks anxious. The content and format of the feedback can also be adjusted depending on the user's emotional state. This makes it possible to collect feedback more effectively based on the user's emotions.

The opinion collection system can further include a hobby and interest analysis unit that analyzes the user's hobbies and interests. The hobby and interest analysis unit collects and analyzes data such as the user's past hobbies and interests. This makes it possible to understand the user's hobbies and interests and collect more relevant opinions. For example, opinions about events and activities that the user has participated in in the past can be collected. Opinions about topics that the user is interested in can also be collected. Furthermore, based on the user's hobbies and interests, opinions about related products and services can also be collected. This makes it possible to collect more relevant opinions based on the user's hobbies and interests.

The processing flow for Example 2 is briefly explained below.

Step 1: The character generation unit uses generation AI to create a group of unique characters. For example, the generation AI uses text generation AI (e.g., LLM) to generate characters with various ages, ways of thinking, and preferences. The generation AI can also use multimodal generation AI to generate character appearances and personalities. The generation AI can also generate realistic characters based on the character's background information. For example, the text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI generates characters based on prompts such as the character's age, occupation, hobbies, and personality.
Step 2: The opinion collection unit collects opinions from the character created by the character generation unit. For example, the generation AI asks the character questions about a new product concept and collects the responses. The generation AI can also generate realistic opinions and feedback based on the character's personality and background. The generation AI can also collect detailed feedback through dialogue with the character. For example, the generation AI can ask the character open-ended questions to collect free opinions.
Step 3: The needs analysis unit analyzes the opinions collected by the opinion collection unit to identify specific needs. For example, the generation AI can identify needs common to characters of a particular age group or occupation. The generation AI can also analyze the collected opinions to extract specific needs and requirements that will be useful for product development. The generation AI can also identify requirements for specific functions or services based on the characters' opinions. For example, the generation AI can use text analysis technology to extract important keywords from the characters' opinions and use them to identify needs.
Step 4: The requirements analysis unit analyzes the opinions collected by the needs analysis unit to discover broader requirements. For example, the generation AI can identify common requirements shared by characters of different age groups and occupations. The generation AI can also analyze the collected opinions and extract broader requirements that are useful for product development. Based on the characters' opinions, the generation AI can also identify requirements based on overall user experience and market trends. For example, the generation AI can use topic modeling technology to extract common topics from the characters' opinions and use them to identify requirements.

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 38B acquires audio indicating the user input regarding the results 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 what is known as generative AI (artificial intelligence). An example of a 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 containing an instruction is input to the data generation model 58, and inference data such as voice data representing speech, text data representing text, and image data representing an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AI other than the generation AI. Examples of AI other than the generation AI include linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes, and can perform a variety of processes, but are not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generation AI, may be replaced with rule-based processing.

Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, etc., and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

Second Embodiment
FIG. 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 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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 and/or a LAN.

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, RAM 48, and storage 50. The processor 46, RAM 48, and 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 other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with 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 images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy 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 carried out in a secure manner.

Figure 4 shows an example of the main functions of the data processing device 12 and smart glasses 214. As shown in Figure 4, 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 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. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 210 according to the second embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. Processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

[Third embodiment]
FIG. 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 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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 and/or a LAN.

The headset 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, RAM 48, and storage 50. The processor 46, RAM 48, and 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 other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with 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 images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy 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 carried out in a secure manner.

Figure 6 shows an example of the main functions of the data processing device 12 and headset terminal 314. As shown in Figure 6, 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 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. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In the headset type terminal 314, the specific processing is performed by the processor 46. A specific program 60 is stored in the storage 50. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. Processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[Fourth embodiment]
FIG. 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 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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 and/or a LAN.

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, RAM 48, and storage 50. The processor 46, RAM 48, and 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 other information from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with 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 image sensor or CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy 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 carried out in a secure manner.

The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. 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, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

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. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

In robot 414, specific processing is performed by processor 46. Specific program 60 is stored in storage 50. Processor 46 reads specific program 60 from storage 50 and executes the read specific program 60 on RAM 48. The specific processing is realized by processor 46 operating as control unit 46A in accordance with specific program 60 executed on RAM 48. Note that robot 414 may have a data generation model and emotion identification model similar to data generation model 58 and emotion identification model 59.

Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt and outputs the inference results in the form of data such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12, etc., includes multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform a variety of processes, but is not limited to these examples. The AI may also be an AI agent. When the processing of each of the above-mentioned parts is performed by AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. The processing performed by AI, including the generative AI, may be replaced with rule-based processing.

The data processing system 410 according to the fourth embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. Processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

The emotion identification model 59, which serves as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see Figure 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

Figure 9 shows an emotion map 400 on which multiple emotions are mapped. In emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both emotions and mental states. Emotions that are generally generated from reactions that occur in the brain are arranged on the left side of the concentric circles. Emotions that are generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, 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, emotion map 400 maps multiple emotions based on the structure by which emotions are generated, with emotions that tend to occur simultaneously being mapped close together.

These emotions are distributed in the 3 o'clock direction on 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 in 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) the emotion becomes.

Here, human emotions are based on various balances such as posture and blood sugar levels, and when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery life, and when these balances deviate from the ideal, it indicates discomfort, and when they approach the ideal, it indicates pleasure. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and emotional brain physiological signal analysis systems, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions belonging to an area called "reaction," where sensation is dominant. The right half of the emotion map is lined with emotions belonging to an area called "situation," where situational awareness is dominant.

The emotion map defines two emotions that encourage learning. One 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 experiences positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input into 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 pieces of training 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 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, such as "relieved," "calm," and "reassuring," have similar emotion values.

In the above embodiment, an example was given in which a specific process is performed by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may also be performed by multiple computers, including computer 22.

In the above embodiment, an example was 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 USB (Universal Serial Bus) 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.

Alternatively, the specific processing program 56 may 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 on the computer 22 in response to a request from the data processing device 12.

It is not necessary to store the entire 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 the entire specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

The following types of processors can be used as hardware resources for executing specific processes. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Other 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 for executing specific processes. All processors have built-in or connected memory, and all use the memory to execute specific processes.

The hardware resource that executes the specific processing 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 (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific processing 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 using a combination of one or more CPUs and software, and this processor functions as a hardware resource that executes specific processing. Second, there is a configuration in which a processor is used to realize the functions of an entire system, including multiple hardware resources that execute specific processing, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, specific processing is realized using one or more of the various processors listed above as hardware resources.

More specifically, the hardware structure of these various processors can be an electrical circuit that combines circuit elements such as semiconductor devices. Furthermore, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps can be added, or the processing order can be rearranged, all within the scope of the spirit of the invention.

Furthermore, in the above examples, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. Furthermore, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are only examples, and they may be combined, or other devices may be used. Furthermore, in the above examples, the first and second embodiments have been described separately, but these may also be combined.

The above-described written content 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 substitutions may be made to the above-described written content and illustrations, as long as they do not deviate from the spirit of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described written content and illustrations omit explanations of common technical 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 mentioned in this specification are incorporated herein by reference to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (8)

A character generation section that uses generative AI to create a unique group of characters;
an opinion collection unit that collects opinions from the characters created by the character creation unit;
a needs analysis unit that analyzes the opinions collected by the opinion collection unit to find out specific needs;
a requirements analysis unit that analyzes the opinions collected by the needs analysis unit to find out a wide range of requirements. The character generation unit
The system according to claim 1, wherein the system analyzes the user's emotional state in real time and generates a character according to the user's emotions. The opinion collection unit
The system according to claim 1, characterized in that it analyzes the user's emotional state in real time and asks questions according to the emotion. The needs analysis unit
10. The system of claim 1, further comprising: analyzing a user's emotional state in real time to identify emotion-based needs. The request analysis unit
10. The system of claim 1, further comprising: analyzing a user's emotional state in real time to identify broad emotional needs. The character generation unit
The system of claim 1, further comprising: simultaneously generating voice or movement patterns to provide a more realistic character experience. The opinion collection unit
10. The system of claim 1, wherein voice or video input is used to gather opinions in a more diverse format. The needs analysis unit
10. The system of claim 1, further analyzing audio or video data to identify more diverse needs.