JP2025048872A - system - Google Patents

Abstract

To mitigate solitary that a user may feel when having lost a past partner.SOLUTION: A system according to an embodiment of the present invention comprises a collection unit, a generation unit, and an interaction unit. The collection unit collects data concerning a user's past partner. The generation unit generates a virtual partner corresponding to the past partner on the basis of the data collected by the collection unit. The interaction unit performs interaction with the user by using the virtual partner generated by the generation unit.SELECTED DRAWING: Figure 1

Description

The technology disclosed herein relates to a system.

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

JP 2022-180282 A

Current technology does not adequately provide users with a means to reduce feelings of loneliness when they lose a past partner, and there is room for improvement.

The system according to the embodiment aims to reduce the sense of loneliness felt when a user loses a past partner.

The system according to the embodiment includes a collection unit, a generation unit, and a dialogue unit. The collection unit collects data related to a user's past partners. The generation unit generates virtual partners corresponding to the past partners based on the data collected by the collection unit. The dialogue unit uses the virtual partners generated by the generation unit to engage in dialogue with the user.

The system according to the embodiment can reduce the sense of loneliness when a user loses a past partner.

1 is a conceptual diagram showing an example of a configuration of a data processing system according to a first embodiment. 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. FIG. 11 is a conceptual diagram showing an example of a configuration of a data processing system according to a second embodiment. FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped.

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

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

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

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

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

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

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

[First embodiment]
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, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and/or a LAN (Local Area Network).

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

The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 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 of expression that the user can perceive (e.g., voice and/or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

The 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. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a 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 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also use these models to perform processing similar to that of the specific processing unit 290.

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 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

(Example 1)
A system according to an embodiment of the present invention is a system for reducing a user's sense of loneliness. This system collects data on a user's past partners, generates a virtual partner based on the collected data, and aims to reduce the user's sense of loneliness through a dialogue between the user and the generated virtual partner. For example, data on a user's past partners is collected in the form of text, voice, image, video, etc. The data includes email exchanges with past partners, telephone recordings, photos and videos, etc. This data is collected by a collection unit (which may include AI processing). Next, a virtual partner is generated based on the collected data. The generation unit (which may include AI processing or generation AI processing) analyzes the collected data and reproduces the appearance, voice, and personality of the virtual partner. For example, the appearance is reproduced from photos and videos of the past partner, and the voice is reproduced from telephone recordings. In addition, the personality is reproduced from email exchanges, SNS posts, etc. The generated virtual partner interacts with the user through a dialogue unit (including generation AI processing). The dialogue unit detects the user's emotional state and adjusts the virtual partner's response according to the detected emotional state. For example, if the user feels sad, the virtual partner can offer words of comfort. Furthermore, the system is provided with a learning unit (which may include AI processing or generation AI processing) that continuously improves the dialogue content of the virtual partner based on the user's feedback. This allows the virtual partner to respond more naturally and appropriately through dialogue with the user. This allows the user to obtain emotional support through dialogue with the virtual partner without falling into a lonely state. For example, even if the user loses a person with whom they have been communicating for a long time, the virtual partner can take their place and maintain the user's emotional stability. This allows the system to reduce the user's sense of loneliness.

The system according to the embodiment includes a collection unit, a generation unit, and a dialogue unit. The collection unit collects data related to the user's past partners. The data related to the user's past partners includes, for example, text messages, photos, voice recordings, etc., but is not limited to such examples. The collection unit collects, for example, email exchanges with the past partners. The collection unit can also collect recordings of phone calls with the past partners. Furthermore, the collection unit can collect photos and videos with the past partners. For example, the collection unit collects email exchanges with the past partners in text format. The recordings of phone calls are collected in audio format. The photos and videos are collected in image format or video format. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. The generation unit generates a virtual partner based on the data collected by the collection unit. The generation unit reproduces the appearance from, for example, photos and videos of the past partners. The generation unit can also reproduce the voice from recordings of phone calls of the past partners. Furthermore, the generation unit can also reproduce the personality from the past partner's email exchanges and SNS posts. For example, the generation unit generates a 3D model based on a photo of the past partner and reproduces the appearance. For recording telephone calls, the voice is reproduced using voice synthesis technology. For email exchanges and SNS posts, the personality is reproduced using natural language processing technology. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. The dialogue unit uses the virtual partner generated by the generation unit to have a dialogue with the user. For example, the dialogue unit detects the emotional state of the user and adjusts the response of the virtual partner according to the detected emotional state. For example, when the user feels sad, the dialogue unit causes the virtual partner to speak words of comfort. Furthermore, when the user is relaxed, the dialogue unit can also have a relaxed conversation with the virtual partner. Furthermore, when the user is stressed, the dialogue unit can also cause the virtual partner to speak words that relieve stress. Some or all of the above-described processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. This allows the system according to the embodiment to reduce the user's sense of loneliness.

The collection unit collects data on the user's past partners. Data on the user's past partners includes, but is not limited to, for example, text messages, photos, and voice recordings. The collection unit collects, for example, email exchanges with past partners. The collection unit can also collect recordings of phone calls with past partners. Furthermore, the collection unit can collect photos and videos with past partners. For example, the collection unit collects email exchanges with past partners in text format. Phone recordings are collected in audio format. Photos and videos are collected in image format or video format. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. The collection unit has an interface for acquiring data from the user's device or cloud storage, thereby allowing the user to easily provide data on past partners. For example, emails, photos, and videos stored by the user on a smartphone or computer can be automatically detected and sent to the collection unit. The collection unit can also collect data from SNS and messaging apps with the user's permission. This allows the collection unit to comprehensively collect a variety of data about the user's past partners and provide basic data for generating virtual partners. Furthermore, the collection unit has a function to appropriately classify and organize the collected data. For example, text data is analyzed using natural language processing technology to extract important keywords and emotional information. Voice data is converted into text using voice recognition technology, and the content of photos and videos is analyzed using image recognition technology. This allows the collection unit to efficiently process the collected data and provide it in a format that is easy for the generation unit and dialogue unit to use.

The generation unit generates a virtual partner based on the data collected by the collection unit. The generation unit, for example, reproduces the appearance from photos and videos of past partners. The generation unit can also reproduce the voice from recordings of phone calls of past partners. Furthermore, the generation unit can also reproduce the personality from email exchanges and SNS posts of past partners. For example, the generation unit generates a 3D model based on photos of past partners and reproduces the appearance. For recordings of phone calls, voice is reproduced using voice synthesis technology. For email exchanges and SNS posts, personality is reproduced using natural language processing technology. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, generation AI, or may be performed without using generation AI. The generation unit analyzes the characteristics of the user's past partners in detail based on the collected data and builds a model for generating a virtual partner. For example, image recognition technology is used to extract facial features from photos and videos, and a 3D model is generated. Voice synthesis technology is used to analyze voice features from recordings of phone calls and generate natural voice. Using natural language processing technology, the system extracts personality and speech characteristics from emails and SNS posts to recreate the personality of a virtual partner. By combining these technologies, the generation unit can generate a virtual partner that is very similar to the user's past partners. Furthermore, the generation unit has the ability to continuously learn and improve so that the generated virtual partner can adapt to conversations with the user. For example, the generation unit analyzes the conversation history with the user and incorporates feedback to make the virtual partner's responses more natural and appropriate. This allows the generation unit to respond flexibly to the user's needs and emotions, providing a more realistic conversation experience.

The dialogue unit uses the virtual partner generated by the generation unit to dialogue with the user. The dialogue unit detects, for example, the emotional state of the user and adjusts the response of the virtual partner according to the detected emotional state. For example, when the user feels sad, the dialogue unit causes the virtual partner to speak words of comfort. Furthermore, when the user is relaxed, the dialogue unit can also have a relaxed conversation with the virtual partner. Furthermore, when the user is stressed, the dialogue unit can also cause the virtual partner to speak words that reduce stress. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. The dialogue unit can use voice recognition technology or facial expression recognition technology to detect the emotional state of the user. For example, the dialogue unit can analyze changes in the user's tone of voice and speaking style to estimate the emotional state. Furthermore, the user's facial expression is captured by a camera and the emotions are analyzed using facial expression recognition technology. This allows the dialogue unit to grasp the user's emotional state in real time and generate an appropriate response. Furthermore, the dialogue unit can analyze the user's past dialogue history and grasp the user's preferences and interests. This allows the virtual partner to have a conversation that incorporates topics of interest to the user and the user's preferred speaking style. For example, if the user has a particular hobby or interest, the virtual partner can provide information related to that topic and show empathy, resulting in a more intimate conversation. Through conversation with the user, the dialogue unit can reduce the user's sense of loneliness and provide psychological support. This allows the system according to the embodiment to respond flexibly according to the user's emotional state, thereby improving user satisfaction.

The collection unit can collect data about past partners in the form of text, audio, images, or videos. For example, the collection unit collects email exchanges with past partners in text format. The collection unit can also collect recordings of phone calls with past partners in audio format. The collection unit can also collect photos and videos with past partners in image format or video format. For example, the collection unit collects email exchanges with past partners in text format. Recordings of phone calls are collected in audio format. Photos and videos are collected in image format or video format. This improves the accuracy of reproducing virtual partners by collecting data in various formats. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The generation unit can reproduce the appearance, voice, and personality of the virtual partner based on the data collected by the collection unit. The generation unit reproduces the appearance from, for example, photos and videos of the past partner. The generation unit can also reproduce the voice from recordings of phone calls of the past partner. Furthermore, the generation unit can reproduce the personality from email exchanges and SNS posts of the past partner. For example, the generation unit generates a 3D model based on photos of the past partner to reproduce the appearance. For recordings of phone calls, voice synthesis technology is used to reproduce the voice. For email exchanges and SNS posts, natural language processing technology is used to reproduce the personality. As a result, by reproducing the appearance, voice, and personality of the virtual partner, the dialogue with the user becomes more natural. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The learning unit can continuously improve the dialogue content of the virtual partner based on the user's feedback. The learning unit continuously improves the dialogue content of the virtual partner based on, for example, the user's feedback. For example, when the user provides positive feedback on the dialogue content, the learning unit strengthens the dialogue content. In addition, when the user provides negative feedback on the dialogue content, the learning unit can also improve the dialogue content. Furthermore, the learning unit can analyze the user's feedback and extract a pattern of the dialogue content to improve it. For example, the learning unit extracts a pattern of the dialogue content based on the user's feedback and improves the dialogue content. In this way, the dialogue content is continuously improved by reflecting the user's feedback. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI.

The collection unit can analyze the user's relationship with past partners and select an appropriate data collection method. The collection unit, for example, analyzes the user's relationship with past partners and selects the optimal data collection method. For example, the collection unit preferentially collects data of partners with whom the user has frequently contacted in the past. In addition, if the user has a deep relationship with a specific partner, the collection unit can also collect detailed data about the partner. Furthermore, the collection unit can also focus on collecting data of partners with whom the user has shared important events in the past. For example, the collection unit preferentially collects data of partners with whom the user has frequently contacted in the past. In the case where the user has a deep relationship with a specific partner, detailed data about the partner is collected. Data of partners with whom the user has shared important events in the past is collected with focus. This allows for more accurate virtual partners to be generated by collecting data based on relationships. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The collection unit can perform filtering based on the user's current living situation and areas of interest when collecting data. For example, the collection unit performs filtering based on the user's current living situation and areas of interest when collecting data. For example, the collection unit preferentially collects data related to topics in which the user is currently interested. The collection unit can also filter and collect highly relevant data according to the user's current living situation. Furthermore, the collection unit can also preferentially collect information that the user needs in the current living situation. For example, the collection unit preferentially collects data related to topics in which the user is currently interested. The collection unit filters and collects highly relevant data according to the user's current living situation. The collection unit preferentially collects information that the user needs in the current living situation. This makes it possible to collect data according to the user's current situation. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

When collecting data, the collection unit can prioritize collecting highly relevant data in consideration of the geographical location information of the user. For example, when collecting data, the collection unit prioritizes collecting highly relevant data in consideration of the geographical location information of the user. For example, the collection unit prioritizes collecting data related to the location where the user is currently located. The collection unit can also collect data related to places the user has visited in the past. Furthermore, the collection unit can also collect data related to places the user plans to visit in the future. For example, the collection unit prioritizes collecting data related to the location where the user is currently located. Collects data related to places the user has visited in the past. Collects data related to places the user plans to visit in the future. This makes it possible to collect data based on geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The collection unit can analyze the user's social media activity and collect related data when collecting data. For example, the collection unit analyzes the user's social media activity and collects related data when collecting data. For example, the collection unit collects data related to topics that the user frequently mentions on social media. The collection unit can also collect data related to photos and videos that the user shared on social media. Furthermore, the collection unit can collect data related to accounts that the user follows on social media. For example, the collection unit collects data related to topics that the user frequently mentions on social media. Collects data related to photos and videos that the user shared on social media. Collects data related to accounts that the user follows on social media. This makes it possible to collect data based on social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The generation unit can reproduce the personality of the virtual partner by analyzing the behavioral patterns of the past partner at the time of generation. For example, the generation unit reproduces the personality of the virtual partner by analyzing the behavioral patterns of the past partner at the time of generation. For example, the generation unit reproduces the personality of the virtual partner based on the behavior frequently performed by the past partner. The generation unit can also extract and reproduce personality characteristics from the emails and SNS posts of the past partner. Furthermore, the generation unit can reproduce the speaking style and catchphrases from the voice data of the past partner. For example, the generation unit reproduces the personality of the virtual partner based on the behavior frequently performed by the past partner. The personality characteristics are extracted and reproduced from the emails and SNS posts of the past partner. The speaking style and catchphrases are reproduced from the voice data of the past partner. This makes it possible to reproduce the personality based on the past behavioral patterns. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The generation unit can generate a virtual partner reflecting the hobbies and interests of the past partner at the time of generation. The generation unit generates a virtual partner reflecting the hobbies and interests of the past partner at the time of generation, for example. The generation unit reproduces the hobbies of the virtual partner based on the hobbies that the past partner had. The generation unit can also reproduce the interests of the virtual partner based on topics that the past partner was interested in. Furthermore, the generation unit can also reproduce the interests of the virtual partner based on themes that the past partner frequently talked about. For example, the generation unit reproduces the hobbies of the virtual partner based on the hobbies that the past partner had. The virtual partner's interests are reproduced based on topics that the past partner was interested in. The virtual partner's interests are reproduced based on themes that the past partner frequently talked about. This makes it possible to generate a virtual partner based on past hobbies and interests. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI.

The generation unit can generate a virtual partner reflecting the lifestyle habits of the past partner at the time of generation. The generation unit generates a virtual partner reflecting the lifestyle habits of the past partner at the time of generation, for example. The generation unit reproduces the lifestyle habits of the virtual partner based on the lifestyle habits of the past partner, for example. The generation unit can also reproduce the behavior of the virtual partner based on the daily routine of the past partner. Furthermore, the generation unit can also reproduce the behavior of the virtual partner based on a specific habit of the past partner. For example, the generation unit reproduces the lifestyle habits of the virtual partner based on the lifestyle habits of the past partner. The behavior of the virtual partner is reproduced based on the daily routine of the past partner. The behavior of the virtual partner is reproduced based on a specific habit of the past partner. This makes it possible to generate a virtual partner based on past lifestyle habits. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can generate an appropriate response by referring to the user's past dialogue history during dialogue. For example, the dialogue unit generates an appropriate response by referring to the user's past dialogue history during dialogue. For example, the dialogue unit generates an optimal response based on the content of dialogues the user has had in the past. The dialogue unit can also extract a preferred response pattern from the user's past dialogue history and respond. Furthermore, the dialogue unit can generate an optimal response based on the content of dialogues that the user has preferred in the past. For example, the dialogue unit generates an optimal response based on the content of dialogues the user has had in the past. A preferred response pattern is extracted from the user's past dialogue history and responded. An optimal response is generated based on the content of dialogues that the user has preferred in the past. This makes it possible to generate an optimal response based on the past dialogue history. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can customize the dialogue content based on the user's current living situation during the dialogue. For example, the dialogue unit customizes the dialogue content based on the user's current living situation during the dialogue. For example, the dialogue unit customizes the dialogue content based on information the user needs in the current living situation. The dialogue unit can also provide highly relevant dialogue content according to the user's current living situation. Furthermore, the dialogue unit can customize the dialogue content based on topics in which the user is interested in the current living situation. For example, the dialogue unit customizes the dialogue content based on information the user needs in the current living situation. Provides highly relevant dialogue content according to the user's current living situation. Customizes the dialogue content based on topics in which the user is interested in the current living situation. This makes it possible to customize the dialogue content according to the current living situation. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can provide highly relevant dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit can provide highly relevant dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit can provide dialogue content based on information related to the location where the user is currently located, for example. The dialogue unit can also provide dialogue content based on information related to locations where the user has visited in the past. The dialogue unit can also provide dialogue content based on information related to locations where the user plans to visit in the future. For example, the dialogue unit provides dialogue content based on information related to the location where the user is currently located. The dialogue unit provides dialogue content based on information related to locations where the user has visited in the past. The dialogue unit provides dialogue content based on information related to locations where the user plans to visit in the future. This makes it possible to provide dialogue content based on geographical location information. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can customize the dialogue content by analyzing the user's social media activity during the dialogue. For example, the dialogue unit customizes the dialogue content by analyzing the user's social media activity during the dialogue. The dialogue unit, for example, provides dialogue content related to topics that the user frequently mentions on social media. The dialogue unit can also provide dialogue content related to photos and videos that the user has shared on social media. Furthermore, the dialogue unit can also provide dialogue content related to accounts that the user follows on social media. For example, the dialogue unit provides dialogue content related to topics that the user frequently mentions on social media. Provides dialogue content related to photos and videos that the user has shared on social media. Provides dialogue content related to accounts that the user follows on social media. This makes it possible to customize the dialogue content based on social media activity. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. The learning unit selects an optimal learning algorithm based on past learning data, for example. The learning unit can also optimize the algorithm by extracting effective learning patterns from past learning data. Furthermore, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit optimizes the algorithm by extracting effective learning patterns from past learning data. The learning unit analyzes past learning data and adjusts the parameters of the learning algorithm. This makes it possible to optimize the learning algorithm based on past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The learning unit can weight the learning data based on the user's dialogue history during learning. For example, the learning unit weights the learning data based on the user's dialogue history during learning. The learning unit weights the learning data based on, for example, the dialogue content of the user's past. The learning unit can also weight important dialogue content from the user's dialogue history. Furthermore, the learning unit can weight the learning data based on dialogue content that the user liked in the past. For example, the learning unit weights the learning data based on the dialogue content of the user's past. From the user's dialogue history, weights important dialogue content. The learning unit weights the learning data based on dialogue content that the user liked in the past. This makes it possible to weight the learning data based on the dialogue history. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

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

The system can also customize the virtual partner's dialogue content based on the user's current life situation to reduce the user's sense of loneliness. For example, if the user is facing a particular problem in his or her current life situation, the virtual partner can provide advice on that problem. If the user has started a new hobby, the virtual partner can provide information related to that hobby. Furthermore, if the user is planning to travel, the virtual partner can provide information and advice on travel destinations. This allows for more personalized support by providing dialogue content that is appropriate for the user's current life situation.

The system can also analyze the user's past interaction history and optimize the content of the virtual partner's interaction. For example, the virtual partner can revisit topics that the user liked in the past. It can also adjust the content of the interaction to avoid topics that the user avoided in the past. It can also provide new information related to topics that the user was particularly interested in in the past. This makes it possible to have personalized interactions based on the user's past interaction history.

The system can also customize the dialogue of the virtual partner by taking into account the user's current geographic location. For example, it can provide information related to the location where the user is currently located, or it can reminisce about places the user has visited in the past, or it can provide information and advice about places the user plans to visit in the future. This allows for personalized dialogue based on geographic location.

The system can also analyze the user's social media activity and customize the dialogue content for the virtual partner. For example, the system can provide dialogue content related to topics the user frequently mentions on social media. It can also provide dialogue content related to photos and videos the user has shared on social media. It can also provide dialogue content related to accounts the user follows on social media. This allows for personalized dialogue based on social media activity.

The system can also analyze the behavioral patterns of the user's past partners and recreate the virtual partner's personality. For example, it can recreate a virtual partner's personality based on the actions that the past partner frequently engaged in. It can also extract and recreate personality traits from the past partner's emails and social media posts. It can also recreate the speaking style and catchphrases from the past partner's voice data. This makes it possible to recreate personalities based on past behavioral patterns, providing a more natural dialogue.

The processing flow of Example 1 is briefly explained below.

Step 1: The collection unit collects data on the user's past partners. Data on the user's past partners includes, for example, text messages, photos, and voice recordings. The collection unit can collect email correspondence with past partners, telephone recordings, photos, and videos. These data are collected in text, audio, image, and video formats. The processing in the collection unit may be performed using AI.
Step 2: The generation unit generates a virtual partner based on the data collected by the collection unit. The generation unit recreates the appearance from photos and videos of past partners, the voice from phone recordings, and the personality from email exchanges and SNS posts. These processes are performed using 3D model generation, voice synthesis technology, and natural language processing technology. The processing in the generation unit may also be performed using generation AI.
Step 3: The dialogue unit uses the virtual partner generated by the generation unit to dialogue with the user. The dialogue unit detects the user's emotional state and adjusts the response of the virtual partner according to the detected emotional state. For example, if the user feels sad, the virtual partner will offer comforting words, if the user is relaxed, the virtual partner will engage in a relaxing conversation, and if the user is stressed, the virtual partner will offer words to relieve stress. The processing in the dialogue unit may be performed using a generation AI.

(Example 2)
A system according to an embodiment of the present invention is a system for reducing a user's sense of loneliness. This system collects data on a user's past partners, generates a virtual partner based on the collected data, and aims to reduce the user's sense of loneliness through a dialogue between the user and the generated virtual partner. For example, data on a user's past partners is collected in the form of text, voice, image, video, etc. The data includes email exchanges with past partners, telephone recordings, photos and videos, etc. This data is collected by a collection unit (which may include AI processing). Next, a virtual partner is generated based on the collected data. The generation unit (which may include AI processing or generation AI processing) analyzes the collected data and reproduces the appearance, voice, and personality of the virtual partner. For example, the appearance is reproduced from photos and videos of the past partner, and the voice is reproduced from telephone recordings. In addition, the personality is reproduced from email exchanges, SNS posts, etc. The generated virtual partner interacts with the user through a dialogue unit (including generation AI processing). The dialogue unit detects the user's emotional state and adjusts the virtual partner's response according to the detected emotional state. For example, if the user feels sad, the virtual partner can offer words of comfort. Furthermore, the system is provided with a learning unit (which may include AI processing or generation AI processing) that continuously improves the dialogue content of the virtual partner based on the user's feedback. This allows the virtual partner to respond more naturally and appropriately through dialogue with the user. This allows the user to obtain emotional support through dialogue with the virtual partner without falling into a lonely state. For example, even if the user loses a person with whom they have been communicating for a long time, the virtual partner can take their place and maintain the user's emotional stability. This allows the system to reduce the user's sense of loneliness.

The system according to the embodiment includes a collection unit, a generation unit, and a dialogue unit. The collection unit collects data related to the user's past partners. The data related to the user's past partners includes, for example, text messages, photos, voice recordings, etc., but is not limited to such examples. The collection unit collects, for example, email exchanges with the past partners. The collection unit can also collect recordings of phone calls with the past partners. Furthermore, the collection unit can collect photos and videos with the past partners. For example, the collection unit collects email exchanges with the past partners in text format. The recordings of phone calls are collected in audio format. The photos and videos are collected in image format or video format. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. The generation unit generates a virtual partner based on the data collected by the collection unit. The generation unit reproduces the appearance from, for example, photos and videos of the past partners. The generation unit can also reproduce the voice from recordings of phone calls of the past partners. Furthermore, the generation unit can also reproduce the personality from the past partner's email exchanges and SNS posts. For example, the generation unit generates a 3D model based on a photo of the past partner and reproduces the appearance. For recording telephone calls, the voice is reproduced using voice synthesis technology. For email exchanges and SNS posts, the personality is reproduced using natural language processing technology. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. The dialogue unit uses the virtual partner generated by the generation unit to have a dialogue with the user. For example, the dialogue unit detects the emotional state of the user and adjusts the response of the virtual partner according to the detected emotional state. For example, when the user feels sad, the dialogue unit causes the virtual partner to speak words of comfort. Furthermore, when the user is relaxed, the dialogue unit can also have a relaxed conversation with the virtual partner. Furthermore, when the user is stressed, the dialogue unit can also cause the virtual partner to speak words that relieve stress. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. This allows the system according to the embodiment to reduce the user's sense of loneliness.

The collection unit collects data on the user's past partners. Data on the user's past partners includes, but is not limited to, for example, text messages, photos, and voice recordings. The collection unit collects, for example, email exchanges with past partners. The collection unit can also collect recordings of phone calls with past partners. Furthermore, the collection unit can collect photos and videos with past partners. For example, the collection unit collects email exchanges with past partners in text format. Phone recordings are collected in audio format. Photos and videos are collected in image format or video format. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. The collection unit has an interface for acquiring data from the user's device or cloud storage, thereby allowing the user to easily provide data on past partners. For example, emails, photos, and videos stored by the user on a smartphone or computer can be automatically detected and sent to the collection unit. The collection unit can also collect data from SNS and messaging apps with the user's permission. This allows the collection unit to comprehensively collect a variety of data about the user's past partners and provide basic data for generating virtual partners. Furthermore, the collection unit has a function to appropriately classify and organize the collected data. For example, text data is analyzed using natural language processing technology to extract important keywords and emotional information. Voice data is converted into text using voice recognition technology, and the content of photos and videos is analyzed using image recognition technology. This allows the collection unit to efficiently process the collected data and provide it in a format that is easy for the generation unit and dialogue unit to use.

The generation unit generates a virtual partner based on the data collected by the collection unit. For example, the generation unit reproduces the appearance from photos and videos of past partners. The generation unit can also reproduce the voice from recordings of phone calls of past partners. Furthermore, the generation unit can also reproduce the personality from email exchanges and SNS posts of past partners. For example, the generation unit generates a 3D model based on photos of past partners and reproduces the appearance. For recordings of phone calls, voice is reproduced using voice synthesis technology. For email exchanges and SNS posts, personality is reproduced using natural language processing technology. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, generation AI, or may be performed without using generation AI. Based on the collected data, the generation unit analyzes the characteristics of the user's past partners in detail and builds a model for generating a virtual partner. For example, image recognition technology is used to extract facial features from photos and videos, and a 3D model is generated. Voice synthesis technology is used to analyze voice features from recordings of phone calls and generate natural voice. Using natural language processing technology, the system extracts personality and speech characteristics from emails and SNS posts to recreate the personality of a virtual partner. By combining these technologies, the generation unit can generate a virtual partner that is very similar to the user's past partners. Furthermore, the generation unit has the ability to continuously learn and improve so that the generated virtual partner can adapt to conversations with the user. For example, the generation unit analyzes the conversation history with the user and incorporates feedback to make the virtual partner's responses more natural and appropriate. This allows the generation unit to respond flexibly to the user's needs and emotions, providing a more realistic conversation experience.

The dialogue unit uses the virtual partner generated by the generation unit to dialogue with the user. The dialogue unit detects, for example, the emotional state of the user and adjusts the response of the virtual partner according to the detected emotional state. For example, when the user feels sad, the dialogue unit causes the virtual partner to speak words of comfort. Furthermore, when the user is relaxed, the dialogue unit can also have a relaxed conversation with the virtual partner. Furthermore, when the user is stressed, the dialogue unit can also cause the virtual partner to speak words that reduce stress. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. The dialogue unit can use voice recognition technology or facial expression recognition technology to detect the emotional state of the user. For example, the dialogue unit can analyze changes in the user's tone of voice and speaking style to estimate the emotional state. Furthermore, the user's facial expression is captured by a camera and the emotions are analyzed using facial expression recognition technology. This allows the dialogue unit to grasp the user's emotional state in real time and generate an appropriate response. Furthermore, the dialogue unit can analyze the user's past dialogue history and grasp the user's preferences and interests. This allows the virtual partner to have a conversation that incorporates topics of interest to the user and the user's preferred speaking style. For example, if the user has a particular hobby or interest, the virtual partner can provide information related to that topic and show empathy, resulting in a more intimate conversation. Through conversation with the user, the dialogue unit can reduce the user's sense of loneliness and provide psychological support. This allows the system according to the embodiment to respond flexibly according to the user's emotional state, thereby improving user satisfaction.

The collection unit can collect data about past partners in the form of text, audio, images, or videos. For example, the collection unit collects email exchanges with past partners in text format. The collection unit can also collect recordings of phone calls with past partners in audio format. The collection unit can also collect photos and videos with past partners in image format or video format. For example, the collection unit collects email exchanges with past partners in text format. Recordings of phone calls are collected in audio format. Photos and videos are collected in image format or video format. This improves the accuracy of reproducing virtual partners by collecting data in various formats. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The generation unit can reproduce the appearance, voice, and personality of the virtual partner based on the data collected by the collection unit. The generation unit reproduces the appearance from, for example, photos and videos of the past partner. The generation unit can also reproduce the voice from recordings of phone calls of the past partner. Furthermore, the generation unit can reproduce the personality from email exchanges and SNS posts of the past partner. For example, the generation unit generates a 3D model based on photos of the past partner to reproduce the appearance. For recordings of phone calls, voice synthesis technology is used to reproduce the voice. For email exchanges and SNS posts, natural language processing technology is used to reproduce the personality. As a result, by reproducing the appearance, voice, and personality of the virtual partner, the dialogue with the user becomes more natural. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can detect the emotional state of the user and adjust the response of the virtual partner based on the detected emotional state. The dialogue unit, for example, detects the emotional state of the user and adjusts the response of the virtual partner according to the detected emotional state. For example, when the user feels sad, the dialogue unit causes the virtual partner to offer words of comfort. In addition, when the user is relaxed, the dialogue unit can also have a relaxed conversation with the virtual partner. Furthermore, when the user is stressed, the dialogue unit can also cause the virtual partner to offer words to reduce stress. This allows for a more appropriate dialogue by responding according to the user's emotional state. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The learning unit can continuously improve the dialogue content of the virtual partner based on the user's feedback. The learning unit continuously improves the dialogue content of the virtual partner based on, for example, the user's feedback. For example, when the user provides positive feedback on the dialogue content, the learning unit strengthens the dialogue content. In addition, when the user provides negative feedback on the dialogue content, the learning unit can also improve the dialogue content. Furthermore, the learning unit can analyze the user's feedback and extract a pattern of the dialogue content to improve it. For example, the learning unit extracts a pattern of the dialogue content based on the user's feedback and improves the dialogue content. In this way, the dialogue content is continuously improved by reflecting the user's feedback. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI.

The collection unit can estimate the user's emotion and adjust the timing of data collection based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the timing of data collection based on the estimated user's emotion. For example, when the user is feeling sad, the collection unit causes the emotion engine to estimate the emotion and temporarily stops data collection. In addition, when the user is relaxed, the collection unit can also cause the emotion engine to estimate the emotion and actively collect data. Furthermore, when the user is feeling stressed, the collection unit can also cause the emotion engine to estimate the emotion and reduce the frequency of data collection. This enables more appropriate data collection by collecting data at a timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI.

The collection unit can analyze the user's relationship with past partners and select an appropriate data collection method. The collection unit, for example, analyzes the user's relationship with past partners and selects the optimal data collection method. For example, the collection unit preferentially collects data of partners with whom the user has frequently contacted in the past. In addition, if the user has a deep relationship with a specific partner, the collection unit can also collect detailed data about the partner. Furthermore, the collection unit can also focus on collecting data of partners with whom the user has shared important events in the past. For example, the collection unit preferentially collects data of partners with whom the user has frequently contacted in the past. In the case where the user has a deep relationship with a specific partner, detailed data about the partner is collected. Data of partners with whom the user has shared important events in the past is collected with focus. This allows for more accurate virtual partners to be generated by collecting data based on relationships. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The collection unit can perform filtering based on the user's current living situation and areas of interest when collecting data. For example, the collection unit performs filtering based on the user's current living situation and areas of interest when collecting data. For example, the collection unit preferentially collects data related to topics in which the user is currently interested. The collection unit can also filter and collect highly relevant data according to the user's current living situation. Furthermore, the collection unit can also preferentially collect information that the user needs in the current living situation. For example, the collection unit preferentially collects data related to topics in which the user is currently interested. The collection unit filters and collects highly relevant data according to the user's current living situation. The collection unit preferentially collects information that the user needs in the current living situation. This makes it possible to collect data according to the user's current situation. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority of data to be collected based on the estimated user's emotion. For example, when the user is feeling sad, the emotion engine estimates the emotion and preferentially collects comforting data. In addition, when the user is relaxed, the collection unit can also estimate the emotion and preferentially collect interesting data. Furthermore, when the user is feeling stressed, the emotion engine can estimate the emotion and preferentially collect relaxing data. For example, when the user is feeling sad, the collection unit estimates the emotion and preferentially collects comforting data. When the user is relaxed, the emotion engine estimates the emotion and preferentially collects interesting data. When the user is stressed, the emotion engine estimates the emotion and preferentially collects relaxing data. This enables more appropriate data collection by determining the priority of data according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or may be performed without using AI.

When collecting data, the collection unit can prioritize collecting highly relevant data in consideration of the geographical location information of the user. For example, when collecting data, the collection unit prioritizes collecting highly relevant data in consideration of the geographical location information of the user. For example, the collection unit prioritizes collecting data related to the location where the user is currently located. The collection unit can also collect data related to places the user has visited in the past. Furthermore, the collection unit can also collect data related to places the user plans to visit in the future. For example, the collection unit prioritizes collecting data related to the location where the user is currently located. Collects data related to places the user has visited in the past. Collects data related to places the user plans to visit in the future. This makes it possible to collect data based on geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The collection unit can analyze the user's social media activity and collect related data when collecting data. For example, the collection unit analyzes the user's social media activity and collects related data when collecting data. For example, the collection unit collects data related to topics that the user frequently mentions on social media. The collection unit can also collect data related to photos and videos that the user shared on social media. Furthermore, the collection unit can collect data related to accounts that the user follows on social media. For example, the collection unit collects data related to topics that the user frequently mentions on social media. Collects data related to photos and videos that the user shared on social media. Collects data related to accounts that the user follows on social media. This makes it possible to collect data based on social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

The generation unit can estimate the user's emotion and adjust the appearance and voice reproduction method of the virtual partner based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the appearance and voice reproduction method of the virtual partner based on the estimated user's emotion. For example, when the user is feeling sad, the generation unit causes the emotion engine to estimate the emotion and reproduce a gentle voice and a calm appearance. Furthermore, when the user is relaxed, the generation unit can also cause the emotion engine to estimate the emotion and reproduce a natural voice and appearance. Furthermore, when the user is feeling stressed, the generation unit can also cause the emotion engine to estimate the emotion and reproduce a calm voice and appearance. For example, when the user is feeling sad, the generation unit causes the emotion engine to estimate the emotion and reproduce a gentle voice and a calm appearance. When the user is relaxed, the emotion engine estimates the emotion and reproduces a natural voice and appearance. When the user is stressed, the emotion engine estimates the emotion and reproduces a calm voice and appearance. This makes it possible to reproduce the appearance and voice according to the user's emotion. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using the generation AI or can be performed without using the generation AI.

The generation unit can reproduce the personality of the virtual partner by analyzing the behavioral patterns of the past partner at the time of generation. For example, the generation unit reproduces the personality of the virtual partner by analyzing the behavioral patterns of the past partner at the time of generation. For example, the generation unit reproduces the personality of the virtual partner based on the behavior frequently performed by the past partner. The generation unit can also extract and reproduce personality characteristics from the emails and SNS posts of the past partner. Furthermore, the generation unit can reproduce the speaking style and catchphrases from the voice data of the past partner. For example, the generation unit reproduces the personality of the virtual partner based on the behavior frequently performed by the past partner. The personality characteristics are extracted and reproduced from the emails and SNS posts of the past partner. The speaking style and catchphrases are reproduced from the voice data of the past partner. This makes it possible to reproduce the personality based on the past behavioral patterns. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The generation unit can customize the response of the virtual partner based on the user's current emotional state at the time of generation. For example, the generation unit customizes the response of the virtual partner based on the user's current emotional state at the time of generation. For example, when the user is feeling sad, the generation unit uses an emotion engine to estimate the emotion and customize words of comfort to respond. In addition, when the user is relaxed, the generation unit can also use an emotion engine to estimate the emotion and customize a relaxing conversation to respond. Furthermore, when the user is feeling stressed, the generation unit can also use an emotion engine to estimate the emotion and customize words to reduce stress to respond. For example, when the user is feeling sad, the generation unit uses an emotion engine to estimate the emotion and customize words of comfort to respond. When the user is relaxed, the emotion engine estimates the emotion and customizes a relaxing conversation to respond. When the user is feeling stressed, the emotion engine estimates the emotion and customizes words to reduce stress to respond. This makes it possible to customize the response according to the user's emotional state. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The generation unit can estimate the user's emotion and adjust the personality of the virtual partner based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the personality of the virtual partner based on the estimated user's emotion. For example, when the user is feeling sad, the emotion engine estimates the emotion and generates a virtual partner with a gentle personality. In addition, when the user is relaxed, the generation unit can also estimate the emotion and generate a virtual partner with a natural personality. Furthermore, when the user is feeling stress, the generation unit can also estimate the emotion and generate a virtual partner with a calm personality. For example, when the user is feeling sad, the generation unit estimates the emotion and generates a virtual partner with a gentle personality. When the user is relaxed, the emotion engine estimates the emotion and generates a virtual partner with a natural personality. When the user is stressed, the emotion engine estimates the emotion and generates a virtual partner with a calm personality. This makes it possible to adjust the personality according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The generation unit can generate a virtual partner reflecting the hobbies and interests of the past partner at the time of generation. The generation unit generates a virtual partner reflecting the hobbies and interests of the past partner at the time of generation, for example. The generation unit reproduces the hobbies of the virtual partner based on the hobbies that the past partner had. The generation unit can also reproduce the interests of the virtual partner based on topics that the past partner was interested in. Furthermore, the generation unit can also reproduce the interests of the virtual partner based on themes that the past partner frequently talked about. For example, the generation unit reproduces the hobbies of the virtual partner based on the hobbies that the past partner had. The virtual partner's interests are reproduced based on topics that the past partner was interested in. The virtual partner's interests are reproduced based on themes that the past partner frequently talked about. This makes it possible to generate a virtual partner based on past hobbies and interests. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI.

The generation unit can generate a virtual partner reflecting the lifestyle habits of the past partner at the time of generation. The generation unit generates a virtual partner reflecting the lifestyle habits of the past partner at the time of generation, for example. The generation unit reproduces the lifestyle habits of the virtual partner based on the lifestyle habits of the past partner, for example. The generation unit can also reproduce the behavior of the virtual partner based on the daily routine of the past partner. Furthermore, the generation unit can also reproduce the behavior of the virtual partner based on a specific habit of the past partner. For example, the generation unit reproduces the lifestyle habits of the virtual partner based on the lifestyle habits of the past partner. The behavior of the virtual partner is reproduced based on the daily routine of the past partner. The behavior of the virtual partner is reproduced based on a specific habit of the past partner. This makes it possible to generate a virtual partner based on past lifestyle habits. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can estimate the user's emotion and adjust the tone and content of the dialogue based on the estimated user's emotion. The dialogue unit, for example, estimates the user's emotion and adjusts the tone and content of the dialogue based on the estimated user's emotion. For example, when the user is feeling sad, the emotion engine estimates the emotion and the dialogue is performed with a comforting tone and content. Also, when the user is relaxed, the dialogue unit can estimate the emotion and the dialogue is performed with a relaxing tone and content. Furthermore, when the user is feeling stressed, the dialogue unit can estimate the emotion and the dialogue is performed with a tone and content that reduces stress. For example, when the user is feeling sad, the dialogue unit estimates the emotion and the dialogue is performed with a comforting tone and content. When the user is relaxed, the emotion engine estimates the emotion and the dialogue is performed with a relaxing tone and content. When the user is feeling stressed, the emotion engine estimates the emotion and the dialogue is performed with a relaxing tone and content. This makes it possible to adjust the tone and content of the dialogue according to the user's emotion. The emotion estimation is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the dialogue unit can be performed, for example, using the generation AI or can be performed without using the generation AI.

The dialogue unit can generate an appropriate response by referring to the user's past dialogue history during dialogue. For example, the dialogue unit generates an appropriate response by referring to the user's past dialogue history during dialogue. For example, the dialogue unit generates an optimal response based on the content of dialogues the user has had in the past. The dialogue unit can also extract a preferred response pattern from the user's past dialogue history and respond. Furthermore, the dialogue unit can generate an optimal response based on the content of dialogues that the user has preferred in the past. For example, the dialogue unit generates an optimal response based on the content of dialogues the user has had in the past. A preferred response pattern is extracted from the user's past dialogue history and responded. An optimal response is generated based on the content of dialogues that the user has preferred in the past. This makes it possible to generate an optimal response based on the past dialogue history. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can customize the dialogue content based on the user's current living situation during the dialogue. For example, the dialogue unit customizes the dialogue content based on the user's current living situation during the dialogue. For example, the dialogue unit customizes the dialogue content based on information the user needs in the current living situation. The dialogue unit can also provide highly relevant dialogue content according to the user's current living situation. Furthermore, the dialogue unit can customize the dialogue content based on topics in which the user is interested in the current living situation. For example, the dialogue unit customizes the dialogue content based on information the user needs in the current living situation. Provides highly relevant dialogue content according to the user's current living situation. Customizes the dialogue content based on topics in which the user is interested in the current living situation. This makes it possible to customize the dialogue content according to the current living situation. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can estimate the user's emotions and adjust the frequency of dialogue based on the estimated user's emotions. The dialogue unit, for example, estimates the user's emotions and adjusts the frequency of dialogue based on the estimated user's emotions. For example, when the user is feeling sad, the emotion engine estimates the emotions and dialogues frequently. Also, when the user is relaxed, the emotion engine can estimate the emotions and dialogue at a moderate frequency. Furthermore, when the user is feeling stressed, the emotion engine can estimate the emotions and reduce the frequency of dialogue. For example, when the user is feeling sad, the emotion engine estimates the emotions and dialogues frequently. When the user is relaxed, the emotion engine estimates the emotions and dialogues at a moderate frequency. When the user is feeling stressed, the emotion engine estimates the emotions and reduces the frequency of dialogue. This makes it possible to adjust the frequency of dialogue according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The dialogue unit can provide highly relevant dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit can provide highly relevant dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit can provide dialogue content based on information related to the location where the user is currently located, for example. The dialogue unit can also provide dialogue content based on information related to locations where the user has visited in the past. The dialogue unit can also provide dialogue content based on information related to locations where the user plans to visit in the future. For example, the dialogue unit provides dialogue content based on information related to the location where the user is currently located. The dialogue unit provides dialogue content based on information related to locations where the user has visited in the past. The dialogue unit provides dialogue content based on information related to locations where the user plans to visit in the future. This makes it possible to provide dialogue content based on geographical location information. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The dialogue unit can customize the dialogue content by analyzing the user's social media activity during the dialogue. For example, the dialogue unit customizes the dialogue content by analyzing the user's social media activity during the dialogue. The dialogue unit, for example, provides dialogue content related to topics that the user frequently mentions on social media. The dialogue unit can also provide dialogue content related to photos and videos that the user has shared on social media. Furthermore, the dialogue unit can also provide dialogue content related to accounts that the user follows on social media. For example, the dialogue unit provides dialogue content related to topics that the user frequently mentions on social media. Provides dialogue content related to photos and videos that the user has shared on social media. Provides dialogue content related to accounts that the user follows on social media. This makes it possible to customize the dialogue content based on social media activity. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The learning unit can estimate the user's emotions and select learning data based on the estimated user's emotions. For example, the learning unit estimates the user's emotions and selects learning data based on the estimated user's emotions. For example, when the user is feeling sad, the emotion engine estimates the emotions and selects comforting data as learning data. In addition, when the user is relaxed, the learning unit can also estimate the emotions and select interesting data as learning data. In addition, when the user is feeling stressed, the emotion engine can estimate the emotions and select relaxing data as learning data. For example, when the user is feeling sad, the learning unit estimates the emotions and selects comforting data as learning data. When the user is relaxed, the emotion engine estimates the emotions and selects interesting data as learning data. When the user is stressed, the emotion engine estimates the emotions and selects relaxing data as learning data. This makes it possible to select learning data according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. The learning unit selects an optimal learning algorithm based on past learning data, for example. The learning unit can also optimize the algorithm by extracting effective learning patterns from past learning data. Furthermore, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit optimizes the algorithm by extracting effective learning patterns from past learning data. The learning unit analyzes past learning data and adjusts the parameters of the learning algorithm. This makes it possible to optimize the learning algorithm based on past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user's emotions. The learning unit, for example, estimates the user's emotions and adjusts the frequency of learning based on the estimated user's emotions. For example, when the user is feeling sad, the emotion engine estimates the emotions and increases the frequency of learning. Also, when the user is relaxed, the emotion engine can estimate the emotions and perform learning at a moderate frequency. Furthermore, when the user is feeling stressed, the emotion engine can estimate the emotions and reduce the frequency of learning. For example, when the user is feeling sad, the learning unit estimates the emotions and increases the frequency of learning. When the user is relaxed, the emotion engine estimates the emotions and performs learning at a moderate frequency. When the user is feeling stressed, the emotion engine estimates the emotions and reduces the frequency of learning. This makes it possible to adjust the frequency of learning according to the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

The learning unit can weight the learning data based on the user's dialogue history during learning. For example, the learning unit weights the learning data based on the user's dialogue history during learning. The learning unit weights the learning data based on, for example, the dialogue content of the user's past. The learning unit can also weight important dialogue content from the user's dialogue history. Furthermore, the learning unit can weight the learning data based on dialogue content that the user liked in the past. For example, the learning unit weights the learning data based on the dialogue content of the user's past. From the user's dialogue history, weights important dialogue content. The learning unit weights the learning data based on dialogue content that the user liked in the past. This makes it possible to weight the learning data based on the dialogue history. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI.

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

The system can also customize the virtual partner's dialogue content based on the user's current life situation to reduce the user's sense of loneliness. For example, if the user is facing a particular problem in his or her current life situation, the virtual partner can provide advice on that problem. If the user has started a new hobby, the virtual partner can provide information related to that hobby. Furthermore, if the user is planning to travel, the virtual partner can provide information and advice on travel destinations. This allows for more personalized support by providing dialogue content that is appropriate for the user's current life situation.

The system can also estimate the user's emotions and adjust the tone and content of the virtual partner's dialogue based on the estimated emotions. For example, if the user is feeling stressed, the virtual partner can provide topics to help them relax. If the user is feeling happy, the virtual partner can engage in a dialogue that shares that joy. Furthermore, if the user is feeling anxious, the virtual partner can speak words that reassure the user. This makes it possible to have a dialogue that corresponds to the user's emotions, providing more effective support.

The system can also analyze the user's past interaction history and optimize the content of the virtual partner's interaction. For example, the virtual partner can revisit topics that the user liked in the past. It can also adjust the content of the interaction to avoid topics that the user avoided in the past. It can also provide new information related to topics that the user was particularly interested in in the past. This makes it possible to have personalized interactions based on the user's past interaction history.

The system can also estimate the user's emotions and adjust the way the virtual partner's appearance and voice are reproduced based on the estimated emotions. For example, if the user is feeling sad, the virtual partner can reproduce a gentle voice and a calm appearance. If the user is relaxed, the virtual partner can reproduce a natural voice and appearance. Furthermore, if the user is stressed, the virtual partner can reproduce a calm voice and appearance. This makes it possible to reproduce the appearance and voice according to the user's emotions, providing more effective dialogue.

The system can also customize the dialogue of the virtual partner by taking into account the user's current geographic location. For example, it can provide information related to the location where the user is currently located, or it can reminisce about places the user has visited in the past, or it can provide information and advice about places the user plans to visit in the future. This allows for personalized dialogue based on geographic location.

The system can also estimate the user's emotions and adjust the virtual partner's personality based on the estimated emotions. For example, if the user is feeling sad, the virtual partner can be adjusted to have a kind personality. If the user is relaxed, the virtual partner can be adjusted to have a natural personality. Furthermore, if the user is feeling stressed, the virtual partner can be adjusted to have a calm personality. This allows the personality to be adjusted according to the user's emotions, providing a more effective dialogue.

The system can also analyze the user's social media activity and customize the dialogue content for the virtual partner. For example, the system can provide dialogue content related to topics the user frequently mentions on social media. It can also provide dialogue content related to photos and videos the user has shared on social media. It can also provide dialogue content related to accounts the user follows on social media. This allows for personalized dialogue based on social media activity.

The system can also estimate the user's emotions and customize the virtual partner's responses based on the estimated emotions. For example, if the user is feeling sad, the virtual partner can respond with customized words of comfort. If the user is feeling relaxed, the virtual partner can respond with customized relaxing conversation. Furthermore, if the user is feeling stressed, the virtual partner can respond with customized words that reduce stress. This allows for customized responses according to the user's emotional state, providing more effective interactions.

The system can also analyze the behavioral patterns of the user's past partners and recreate the virtual partner's personality. For example, it can recreate a virtual partner's personality based on the actions that the past partner frequently engaged in. It can also extract and recreate personality traits from the past partner's emails and social media posts. It can also recreate the speaking style and catchphrases from the past partner's voice data. This makes it possible to recreate personalities based on past behavioral patterns, providing a more natural dialogue.

The system can also estimate the user's emotions and adjust the frequency of the virtual partner's interactions based on the estimated emotions. For example, if the user feels sad, the virtual partner can interact frequently. If the user feels relaxed, the virtual partner can interact at a moderate frequency. Furthermore, if the user feels stressed, the virtual partner can decrease the frequency of interactions. This makes it possible to adjust the frequency of interactions according to the user's emotions, providing more effective support.

The process flow for Example 2 is briefly explained below.

Step 1: The collection unit collects data on the user's past partners. Data on the user's past partners includes, for example, text messages, photos, and voice recordings. The collection unit can collect email correspondence with past partners, telephone recordings, photos, and videos. These data are collected in text, audio, image, and video formats. The processing in the collection unit may be performed using AI.
Step 2: The generation unit generates a virtual partner based on the data collected by the collection unit. The generation unit recreates the appearance from photos and videos of past partners, the voice from phone recordings, and the personality from email exchanges and SNS posts. These processes are performed using 3D model generation, voice synthesis technology, and natural language processing technology. The processing in the generation unit may also be performed using generation AI.
Step 3: The dialogue unit uses the virtual partner generated by the generation unit to dialogue with the user. The dialogue unit detects the user's emotional state and adjusts the response of the virtual partner according to the detected emotional state. For example, if the user feels sad, the virtual partner will offer comforting words, if the user is relaxed, the virtual partner will engage in a relaxing conversation, and if the user is stressed, the virtual partner will offer words to relieve stress. The processing in the dialogue unit may be performed using a generation AI.

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

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (registered trademark) (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, processing performed by AI, including the generating AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including the generating AI.

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. The specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

For example, the collection unit can collect data on the user's past partners using the camera 42 and microphone 38B of the smart device 14. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to generate a virtual partner. The dialogue unit is realized, for example, by the control unit 46A of the smart device 14, and engages in dialogue with the user using the generated virtual partner. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[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, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN 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, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 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 the voice according to instructions from the processor 46.

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

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

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

The 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.

The 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. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores the specific processing program 60. 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 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can use these models to perform processing similar to that of the specific processing unit 290.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input for the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The 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 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 required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

For example, the collection unit can collect data on the user's past partners using the camera 42 and microphone 238 of the smart glasses 214. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to generate a virtual partner. The dialogue unit is realized, for example, by the control unit 46A of the smart glasses 214, and engages in dialogue with the user using the generated virtual partner. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[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, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN and/or a LAN.

The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I/F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 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 the voice according to instructions from the processor 46.

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

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

Figure 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Figure 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

The 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.

The 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. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores the specific program 60. 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. The headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input for the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

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. The 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 type 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 type 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 type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

For example, the collection unit can collect data on the user's past partners using the camera 42 and microphone 238 of the headset terminal 314. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to generate a virtual partner. The dialogue unit is realized, for example, by the control unit 46A of the headset terminal 314, and engages in dialogue with the user using the generated virtual partner. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[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, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I/F 26 are also connected to the bus 34. The communication I/F 26 is connected to a network 54. Examples of the network 54 include a WAN 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, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

The microphone 238 receives instructions and the like from the user 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 the voice according to instructions from the processor 46.

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

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

The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and legs. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

The 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.

The 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. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores the specific program 60. 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating the user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The 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. In addition, 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.

For example, the collection unit can collect data on the user's past partners using the camera 42 and microphone 238 of the robot 414. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to generate a virtual partner. The dialogue unit is realized, for example, by the control unit 46A of the robot 414, and uses the generated virtual partner to engage in dialogue with the user. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

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

9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. Emotions that represent states and actions arising from a state of mind are arranged on the outer sides of the concentric circles. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

These emotions are distributed in the three o'clock direction of emotion map 400, and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness takes precedence over internal sensations, resulting in a sense of calm.

The inside of emotion map 400 represents what is going on inside the mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible (expressed in behavior) the emotions become.

Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery power, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions that belong to an area called "reaction" where sensation is dominant. The right half of the emotion map is lined with emotions that belong to an area called "situation" where situation recognition is dominant.

The emotion map defines two emotions that encourage learning. The first is the negative emotion around the middle of "repentance" or "reflection" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input to a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Figure 10. Figure 10 shows an example in which multiple emotions, "peace of mind," "calm," and "reassuring," have similar emotion values.

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

In the above embodiment, an example has been described in which the specific processing program 56 is stored in the storage 32, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

The specific processing program 56 may also be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

The various processors listed below can be used as hardware resources for executing specific processes. Examples of processors include a CPU, which is a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically to execute specific processes. All of these processors have built-in or connected memory, and all of these processors execute specific processes by using the memory.

The hardware resource that executes the specific process may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific process may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured by combining one or more CPUs with software, and this processor functions as a hardware resource that executes a specific process. Secondly, there is a configuration in which a processor is used that realizes the functions of the entire system, including multiple hardware resources that execute a specific process, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the various processors mentioned above as hardware resources.

More specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processing described above is merely an example. It goes without saying that unnecessary steps can be deleted, new steps can be added, and the processing order can be changed without departing from the spirit of the invention.

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

The above description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above explanation of the configuration, function, action, and effect is an explanation of an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. Also, in order to avoid confusion and to make it easier to understand the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense 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 by reference into this specification to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

(Appendix 1)
A collection unit that collects data regarding the user's past partners;
A generating unit that generates a virtual partner corresponding to the past partner based on the data collected by the collecting unit;
A system comprising: a dialogue unit that uses the virtual partner generated by the generation unit to engage in dialogue with the user.
(Appendix 2)
The collecting unit includes:
The system of claim 1, further comprising: collecting data about the past partners in the form of text, audio, images, or video.
(Appendix 3)
The generation unit is
The system of claim 1, further comprising: recreating the appearance, voice, and personality of the virtual partner based on the data collected by the collection unit.
(Appendix 4)
The dialogue unit includes:
2. The system of claim 1, further comprising: detecting an emotional state of the user; and adjusting responses of the virtual partner based on the detected emotional state.
(Appendix 5)
Based on the user feedback,
The system according to claim 1, further comprising a learning unit for continuously improving the dialogue content of the virtual partner.
(Appendix 6)
The collecting unit includes:
2. The system of claim 1, further comprising: estimating a user's emotion; and adjusting timing of data collection based on the estimated user's emotion.
(Appendix 7)
The collecting unit includes:
The system according to claim 1, further comprising: analyzing a user's past relationships with partners and selecting an appropriate data collection method.
(Appendix 8)
The collecting unit includes:
The system according to claim 1, further comprising filtering the data based on the user's current life situation and areas of interest when collecting the data.
(Appendix 9)
The collecting unit includes:
The system according to claim 1, further comprising: estimating a user's emotion; and determining a priority of data to be collected based on the estimated user's emotion.
(Appendix 10)
The collecting unit includes:
The system according to claim 1, characterized in that, when collecting data, highly relevant data is collected preferentially in consideration of the user's geographical location information.
(Appendix 11)
The collecting unit includes:
The system of claim 1, further comprising: analyzing the user's social media activity and collecting associated data during data collection.
(Appendix 12)
The generation unit is
2. The system of claim 1, further comprising: estimating a user's emotion; and adjusting the appearance and voice reproduction of the virtual partner based on the estimated user's emotion.
(Appendix 13)
The generation unit is
The system according to claim 1, characterized in that, at the time of generation, the behavioral patterns of past partners are analyzed to reproduce the personality of the virtual partner.
(Appendix 14)
The generation unit is
2. The system of claim 1, further comprising: customizing, at the time of generation, the virtual partner's responses based on the user's current emotional state.
(Appendix 15)
The generation unit is
2. The system of claim 1, further comprising: estimating a user's emotion; and adjusting the virtual partner's personality based on the estimated user's emotion.
(Appendix 16)
The generation unit is
The system according to claim 1, wherein the virtual partner is generated by reflecting the hobbies and interests of past partners.
(Appendix 17)
The generation unit is
The system according to claim 1, wherein a virtual partner is generated by reflecting the lifestyle habits of past partners at the time of generation.
(Appendix 18)
The dialogue unit includes:
2. The system of claim 1, further comprising: estimating a user's emotion; and adjusting a tone or content of the dialogue based on the estimated user's emotion.
(Appendix 19)
The dialogue unit includes:
The system according to claim 1, further comprising: a user interface for receiving a response from the user;
(Appendix 20)
The dialogue unit includes:
2. The system of claim 1, further comprising: customizing the dialogue content based on the user's current life situation during the dialogue.
(Appendix 21)
The dialogue unit includes:
The system of claim 1, further comprising: estimating a user's emotion; and adjusting a frequency of interactions based on the estimated user's emotion.
(Appendix 22)
The dialogue unit includes:
The system according to claim 1, characterized in that during a dialogue, the system provides highly relevant dialogue content by taking into account the user's geographical location information.
(Appendix 23)
The dialogue unit includes:
The system of claim 1, further comprising: analyzing the user's social media activity during the interaction to customize the interaction content.
(Appendix 24)
The learning unit is
The system according to claim 1, further comprising: a user's emotion estimation unit; and a learning data selection unit that estimates the user's emotion.
(Appendix 25)
The learning unit is
The system according to claim 1, further comprising: optimizing a learning algorithm by referring to past learning data during learning.
(Appendix 26)
The learning unit is
The system of claim 1, further comprising: estimating a user's emotion; and adjusting a frequency of learning based on the estimated user's emotion.
(Appendix 27)
The learning unit is
2. The system according to claim 1, wherein during learning, the learning data is weighted based on the user's dialogue history.

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

Claims (10)

A collection unit that collects data regarding the user's past partners;
A generating unit that generates a virtual partner corresponding to the past partner based on the data collected by the collecting unit;
A system comprising: a dialogue unit that uses the virtual partner generated by the generation unit to engage in dialogue with the user. The collecting unit includes:
10. The system of claim 1, wherein the data about the past partners is collected in the form of text, audio, images, or video. The generation unit is
The system of claim 1 , further comprising: a virtual partner recreating an appearance, a voice, and a personality based on the data collected by the collection unit. The dialogue unit includes:
The system of claim 1 , further comprising: detecting an emotional state of the user; and adjusting responses of the virtual partner based on the detected emotional state. Based on the user feedback,
The system according to claim 1 , further comprising a learning unit for continuously improving the dialogue content of the virtual partner. The collecting unit includes:
The system of claim 1 , further comprising: estimating an emotion of the user; and adjusting timing of data collection based on the estimated emotion of the user. The collecting unit includes:
The system according to claim 1, further comprising: analyzing the user's past relationships with partners and selecting an appropriate data collection method. The collecting unit includes:
The system of claim 1, wherein data collection is filtered based on the user's current life situation and interests. The collecting unit includes:
The system of claim 1 , further comprising: estimating a sentiment of the user; and prioritizing data to be collected based on the estimated sentiment of the user. The collecting unit includes:
The system according to claim 1, wherein when collecting data, highly relevant data is preferentially collected in consideration of the geographical location information of the user.

Images