System

Abstract

To provide a system that offers knowledge or opinions of great persons or influencers in dialogue.SOLUTION: A system includes a collection unit, a learning unit, a selection unit, an interaction unit, and an argument unit. The collection unit collects books or video content of great persons or influencers. The learning unit causes AI to learn the data collected by the collection unit. The selection unit allows a user to select a great person. The interaction unit allows the user to interact with a great-person avatar selected by the selection unit. The argument unit manages arguments between the great-persons avatars.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to obtain the knowledge and opinions of great people and influencers in a direct, interactive format.

[0005] The system according to the embodiment aims to provide the knowledge and opinions of great people and influencers in an interactive format. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a selection unit, a dialogue unit, and a discussion unit. The collection unit collects books or video content about great people or influencers. The learning unit trains an AI on the data collected by the collection unit. The selection unit allows a user to select a great person. The dialogue unit allows the user to dialogue with the great person avatar selected by the selection unit. The discussion unit manages discussions between the great person avatars. [Effects of the Invention]

[0007] The system according to the embodiment can provide the knowledge and opinions of great people and influencers in an interactive format. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, 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).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a 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.

[0018] 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, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process 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 process 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.

[0025] 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 a 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 these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] 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 together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that 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 perform processing similar to that of the specific processing unit 290 using these models.

[0027] 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. Furthermore, 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.

[0028] (Example 1) The great figure avatar system of an embodiment of the present invention fine-tunes AI to learn statements made by historical figures and influencers in books and video content, and then constructs an AI avatar of that person. Users can select a great figure they would like to discuss their concerns with and receive advice from that figure through chat. Furthermore, by enabling discussions between great figure avatars, it is possible to clarify different values ​​and opinions and raise awareness of diversity and inclusion. For example, books and video content by great figures and influencers are collected. The collected data includes detailed information, including the content and context of statements. Examples include speeches, interviews, and the contents of books by great figures. Next, the AI ​​is trained on the collected data. The AI ​​analyzes the collected data and learns the speech patterns and values ​​of great figures and influencers. For example, the AI ​​can understand what a particular great figure said in a given situation and reproduce that person's characteristics. Users select a great figure to have their concerns listened to through the system. For example, if a user selects "I would like to consult with Einstein about my concerns," an AI avatar of Einstein is generated. Users can chat with Einstein and get advice. It's also possible for great-figure avatars to debate with each other. For example, AI avatars of Einstein and Gandhi debate to clarify their differing values ​​and opinions. This allows users to become more aware of diversity and inclusion. This system gives users the feeling of receiving direct advice from great historical figures and influencers, and by learning about different values ​​and opinions, they can grow and gain new perspectives. The great-figure avatar system thus gives users the feeling of receiving direct advice from great historical figures and influencers, and by learning about different values ​​and opinions, they can grow and gain new perspectives.

[0029] The great person avatar system according to the embodiment includes a collection unit, a learning unit, a selection unit, a dialogue unit, and a discussion unit. The collection unit collects books and video content by great people and influencers. For example, the collection unit can automatically collect content on the Internet using web scraping technology. The collection unit can also obtain data from specific platforms using an API. For example, the collection unit collects content such as e-books and videos from video sites (e.g., YouTube® videos). The learning unit trains an AI based on the collected data. For example, the learning unit learns the speech patterns and values ​​of great people and influencers using deep learning technology. The learning unit can analyze text data using natural language processing technology to understand the context and intent of the speech. For example, the learning unit analyzes the content of speeches and interviews by great people and learns their speech patterns. The selection unit selects great people to whom the user wants to share their concerns. For example, the selection unit provides search and filtering functions, allowing the user to easily find specific great people. The selection unit can also recommend the most suitable great person based on the user's past selection history and current interests. The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural conversation with the great person avatar. The dialogue unit can use a generation AI to generate appropriate answers to the user's questions. For example, if the user selects "I want to talk to Einstein about my problems," the dialogue unit generates an AI avatar of Einstein and engages in a dialogue with the user. The discussion unit manages discussions between the great person avatars. For example, the discussion unit sets discussion topics and manages the order of comments, ensuring smooth discussions between the great person avatars. The discussion unit can use a generation AI to generate comments for the great person avatars and clarify different values ​​and opinions. For example, the discussion unit allows AI avatars of Einstein and Gandhi to hold a discussion, providing users with an awareness of diversity and inclusion.As a result, the great figure avatar system of the embodiment provides users with the feeling of receiving direct advice from great historical figures and influencers, and by learning different values ​​and opinions, users can grow as individuals and gain new perspectives.

[0030] The collection unit collects books and video content from famous people and influencers. The collection unit can automatically collect content from the Internet using, for example, web scraping technology. Specifically, web scraping technology can automatically extract data such as text, images, and videos from specific websites and store them in a database. For example, the collection unit downloads works by famous people from e-book platforms and collects interview and lecture videos from YouTube and other video sharing sites. The collection unit can also use APIs to obtain data from specific platforms. By using APIs, the collection unit can efficiently obtain data based on specific criteria and quickly gather the necessary information. For example, the collection unit can use an e-book API to obtain all works by a specific author in one go, or use a video platform API to automatically collect videos related to specific keywords. This allows the collection unit to collect a wide range of data from various sources and comprehensively cover the statements and actions of famous people and influencers. Furthermore, the collection unit can centrally manage the collected data and perform data cleansing processes to prevent data duplication and loss. This allows the collection unit to provide highly reliable data and improve the accuracy of the subsequent learning and dialogue units.

[0031] The learning unit trains the AI ​​using the collected data. For example, the learning unit uses deep learning technology to learn the speech patterns and values ​​of great figures and influencers. Specifically, it builds a deep learning model and trains the model using collected text and audio data. For example, the learning unit analyzes the content of speeches and interviews by great figures to learn their speech patterns. It can analyze text data using natural language processing technology to understand the context and intent of their statements. For example, the learning unit analyzes the text of great figures' writings and speeches, extracting frequently used phrases and keywords and capturing the characteristics of their statements. It can also analyze audio data to learn characteristics of great figures' speaking styles, tone of voice, rhythm, and other characteristics. This allows the learning unit to reproduce the speech styles and values ​​of great figures and influencers with high accuracy. Furthermore, the learning unit continuously updates the collected data and incorporates new information to improve the accuracy of the model. For example, if newly discovered letters or unpublished interviews of great figures are collected, these data can be added to the learning and the model can be retrained to reproduce more accurate speech patterns. This allows the learning unit to constantly provide highly accurate models based on the latest information, enabling the user to have a realistic dialogue experience.

[0032] The selection unit selects a great person the user wants to talk to. The selection unit provides, for example, a search function and a filtering function, allowing the user to easily find a specific great person. Specifically, the selection unit displays a list of related great people based on keywords entered by the user, allowing the user to quickly find a great person of interest. The filtering function can also be used to narrow search results based on criteria such as the great person's field, era, or nationality. For example, the user can select categories such as "scientists" or "philosophers" to display only relevant great people. Furthermore, the selection unit can recommend the most suitable great person based on the user's past selection history and current interests. For example, an algorithm can be implemented to analyze the great people selected by the user in the past and the content of the conversations, and automatically recommend great people that match the user's interests. This allows the selection unit to quickly and accurately find a great person to discuss their concerns with, thereby improving the user experience. Furthermore, the selection unit can provide detailed information and profiles about the great person selected by the user, helping the user gain a deeper understanding of the great person. This allows the user to select an appropriate great person and receive useful advice through conversations.

[0033] The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat and voice dialogue, allowing the user to have natural conversations with the great person avatar. Specifically, text chat allows the great person avatar to respond to questions entered by the user in text format. Voice dialogue allows the user to vocally enter questions through a microphone, and the great person avatar responds vocally. The dialogue unit can generate appropriate answers to the user's questions using a generation AI. For example, if a user selects "I want to consult Einstein about my problems," the dialogue unit generates an AI avatar of Einstein and engages in a conversation with the user. The generation AI analyzes the user's question and generates appropriate answers based on Einstein's speech patterns and values. This allows the dialogue unit to enjoy realistic conversations with the great person avatar. Furthermore, the dialogue unit can support ongoing dialogue by saving the user's dialogue history and referencing past dialogue content. For example, the great person avatar can provide appropriate follow-up questions or advice based on the user's previous consultations. This allows the dialogue unit to provide the user with a consistent dialogue experience and deep insight into the user's concerns and questions.

[0034] The discussion section manages discussions between great person avatars. For example, the discussion section sets discussion topics and manages the order of comments, ensuring smooth progress between the great person avatars. Specifically, the discussion section starts discussions between great person avatars based on topics set by the user and manages the order and content of each avatar's comments. The discussion section uses a generation AI to generate comments from the great person avatars and clarify different values ​​and opinions. For example, the discussion section uses AI avatars of Einstein and Gandhi to hold a discussion, providing users with awareness of diversity and inclusion. The generation AI generates appropriate comments during the discussion based on the speech patterns and values ​​of each great person, supporting deeper discussions. This allows the discussion section to provide users with opportunities to learn different perspectives and opinions, enabling self-growth and new perspectives. Furthermore, the discussion section can monitor the progress of the discussion in real time and adjust the direction of the discussion as needed. For example, if a discussion becomes one-sided or becomes too biased toward a particular topic, the discussion section can suggest a new topic at the appropriate time or change the focus of the discussion to achieve a balanced discussion. In this way, the discussion section can provide users with diverse perspectives and opinions and support them in gaining deeper insights.

[0035] The collection unit can collect books or video content from famous people or influencers. The collection unit can automatically collect content on the Internet using, for example, web scraping technology. The collection unit can also obtain data from specific platforms using APIs. For example, the collection unit collects content such as e-books and YouTube videos. By collecting books and video content from famous people or influencers, data can be obtained for AI learning. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input data collected using web scraping technology into AI and have the AI ​​analyze the data.

[0036] The learning unit can analyze the collected data and learn the speech patterns or values ​​of great figures or influencers. The learning unit can, for example, use deep learning technology to learn the speech patterns and values ​​of great figures and influencers. The learning unit can analyze text data using natural language processing technology to understand the context and intent of the statements. For example, the learning unit can analyze the content of speeches and interviews of great figures and learn their speech patterns. In this way, the accuracy of the AI ​​avatar is improved by analyzing the collected data and learning the speech patterns and values ​​of great figures and influencers. Some or all of the above-mentioned processing in the learning unit is performed using a generation AI. For example, the learning unit can input the collected data into the generation AI and have the generation AI learn the speech patterns and values.

[0037] The selection unit allows the user to select a great person with whom they would like to consult. The selection unit may provide, for example, a search function or a filtering function, allowing the user to easily find a specific great person. The selection unit may also recommend the most suitable great person based on the user's past selection history and current interests. This allows the user to select a great person to listen to their concerns, thereby generating an appropriate great person avatar. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit may input the user's past selection history into AI and have the AI ​​recommend the most suitable great person.

[0038] The dialogue unit allows the user to have a chat-style conversation with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural conversation with the great person avatar. The dialogue unit can generate an appropriate answer to the user's question using a generation AI. For example, when a user selects "I want to talk to Einstein about my worries," the dialogue unit generates an AI avatar of Einstein and engages in a conversation with the user. This allows the user to have a chat-style conversation with the selected great person avatar and receive advice from the great person. Some or all of the above-mentioned processing in the dialogue unit is performed using a generation AI. For example, the dialogue unit can input a user's question into the generation AI and have the generation AI generate an appropriate answer.

[0039] The discussion unit can manage discussions between great person avatars. For example, the discussion unit can set discussion topics and manage the order of comments to ensure that discussions between great person avatars proceed smoothly. The discussion unit can use a generation AI to generate comments made by the great person avatars and clarify different values ​​and opinions. For example, the discussion unit can have AI avatars of Einstein and Gandhi hold a discussion to provide users with awareness of diversity and inclusion. By managing discussions between great person avatars, different values ​​and opinions can be clarified and users can become aware of diversity and inclusion. Some or all of the above-mentioned processing in the discussion unit can be performed using AI, for example, or without AI. For example, the discussion unit can input discussion topic settings into AI and have the AI ​​generate comment content.

[0040] The collection unit can evaluate the reliability of statements made by famous people or influencers and prioritize collection of highly reliable content. For example, if a statement made by a famous person or influencer is based on academic literature, the collection unit can prioritize collection of that content. The collection unit can also prioritize collection of content made by a famous person or influencer that has received a large amount of support. The collection unit can also prioritize collection of content made by a famous person or influencer that is related to historically important events. In this way, by preferentially collecting highly reliable content, the AI ​​can learn highly reliable data. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can input the reliability evaluation of statements into AI and have the AI ​​select highly reliable content.

[0041] When collecting data, the collection unit can simultaneously collect not only the content of the statements made in the content but also the background and circumstances of the statements. For example, the collection unit may record the location and time when a statement was made by a famous person and collect background information. The collection unit may also collect the social circumstances and trends when an influencer made a statement. The collection unit may also collect the emotions and intentions of the famous person or influencer when the statement was made. In this way, by simultaneously collecting the background and circumstances of the statement, more detailed data can be learned by the AI. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input data on the background and circumstances of the statement into the AI ​​and have the AI ​​collect detailed data.

[0042] The collection unit can select content to collect taking into consideration the geographical and cultural background of the great person or influencer. For example, the collection unit collects content related to the great person's or influencer's hometown or area of ​​activity. The collection unit can also collect content based on the great person's or influencer's cultural background. The collection unit can also collect content related to the history and culture of the area where the great person or influencer made a statement. This allows for more appropriate data to be collected by selecting content taking into consideration the geographical and cultural background. Some or all of the above-mentioned processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the geographical and cultural background into AI and have the AI ​​select the content.

[0043] The collection unit can analyze the social media activities of celebrities and influencers and collect related content. For example, the collection unit collects social media statements and posts by celebrities and influencers. The collection unit can also collect content related to accounts and topics followed by celebrities and influencers. The collection unit can also analyze the social media activity history of celebrities and influencers and collect related content. This allows for the collection of more diverse data by analyzing social media activities. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, AI, for example. For example, the collection unit can input social media activity data into AI and have the AI ​​collect related content.

[0044] During learning, the learning unit can analyze the context of statements made by famous people or influencers to understand the intention and background of the statements. For example, the learning unit can analyze the social background when a famous person made a statement to understand their intention. The learning unit can also analyze the trends and circumstances when an influencer made a statement to understand their intention. The learning unit can also analyze the emotions and intentions of famous people or influencers when they made a statement to understand their background. This enables more accurate learning by analyzing the context of statements. Some 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. For example, the learning unit can input context data of a statement into AI and have the AI ​​understand the intention and background.

[0045] During learning, the learning unit can determine learning priorities based on the frequency and importance of statements made by famous people or influencers. For example, the learning unit prioritizes learning of frequently made statements made by famous people or influencers. The learning unit can also prioritize learning of important statements made by famous people or influencers. The learning unit can also determine learning priorities based on the influence of the statements made by famous people or influencers. This enables efficient learning by determining learning priorities based on the frequency and importance of statements. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the frequency and importance of statements into AI and have the AI ​​determine the learning priorities.

[0046] During learning, the learning unit can weight the learning data based on the time and circumstances of the statement made by the famous person or influencer. For example, the learning unit weights the data based on the time when the statement was made by the famous person or influencer. The learning unit can also weight the data based on the circumstances in which the statement was made by the famous person or influencer. The learning unit can also weight the data based on the social background at the time when the statement was made by the famous person or influencer. In this way, more accurate learning is possible by weighting the data based on the time and circumstances of the statement. Some 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. For example, the learning unit can input data on the time and circumstances of the statement into AI and have the AI ​​weight the data.

[0047] During learning, the learning unit can improve the accuracy of the learning by referring to literature related to great people and influencers. The learning unit can improve the accuracy of the learning by referring to, for example, books written by great people and influencers. The learning unit can also improve the accuracy of the learning by referring to academic papers related to great people and influencers. The learning unit can also improve the accuracy of the learning by referring to historical materials related to great people and influencers. In this way, the accuracy of the learning is improved by referring to related literature. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI, or can be performed without using AI. For example, the learning unit can input data from related literature into the AI ​​and have the AI ​​improve the accuracy of the learning.

[0048] When making a selection, the selection unit can recommend the most suitable great person by referring to the user's past selection history. For example, the selection unit recommends the most suitable great person based on great people selected by the user in the past. The selection unit can also recommend great people with similar concerns from the user's past selection history. The selection unit can also analyze the user's past selection history and recommend the most suitable great person. In this way, by referring to the past selection history, the most suitable great person can be recommended to the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data of the past selection history into AI and have the AI ​​recommend the most suitable great person.

[0049] At the time of selection, the selection unit can filter great people based on the user's current worries and interests. The selection unit filters great people based on, for example, the worries the user currently has. The selection unit can also filter great people based on the user's current interests. The selection unit can also filter great people based on the user's current situation. In this way, by filtering great people based on the user's current worries and interests, it is possible to provide great people that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data on the user's current worries and interests into AI and have the AI ​​perform the filtering of great people.

[0050] The selection unit can recommend great people taking into consideration the user's geographical and cultural background when making a selection. For example, the selection unit recommends great people related to the user's hometown or area of ​​activity. The selection unit can also recommend great people based on the user's cultural background. The selection unit can also recommend the most suitable great people based on the user's geographical background. In this way, by recommending great people taking into consideration the user's geographical and cultural background, it is possible to provide great people that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, or without, AI, for example. For example, the selection unit can input data on the geographical and cultural background into AI and have the AI ​​recommend great people.

[0051] At the time of selection, the selection unit can analyze the user's social media activity and recommend related notable figures. For example, the selection unit can analyze the user's social media activity history and recommend related notable figures. The selection unit can also recommend notable figures related to accounts or topics the user follows. The selection unit can also analyze the content of the user's social media posts and recommend the most suitable notable figures. In this way, by analyzing social media activity, it is possible to provide notable figures that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data on social media activity into AI and have the AI ​​recommend notable figures.

[0052] The dialogue unit can generate the content of the dialogue taking into account the context and background of the statement made by the great person during the dialogue. The dialogue unit can generate the content of the dialogue taking into account, for example, the social background when the statement made by the great person. The dialogue unit can also generate the content of the dialogue taking into account the trends and circumstances when the statement made by the influencer. The dialogue unit can also generate the content of the dialogue taking into account the emotions and intentions of the great person or influencer when they made the statement. In this way, by generating the content of the dialogue taking into account the context and background of the statement, it is possible to provide a more appropriate dialogue. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on the context and background of the statement into AI and have the AI ​​generate the content of the dialogue.

[0053] During a dialogue, the dialogue unit can provide optimal advice by referring to the user's past dialogue history. The dialogue unit can provide optimal advice based on, for example, the user's past dialogue history. The dialogue unit can also provide advice from great people who have similar concerns based on the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history and provide the most appropriate advice. In this way, optimal advice can be provided to the user by referring to the past dialogue history. Some or all of the above-described processing in the dialogue unit can be performed using, for example, AI, or can be performed without using AI. For example, the dialogue unit can input data from the past dialogue history into AI and have the AI ​​provide optimal advice.

[0054] The dialogue unit can customize the content of the dialogue based on the user's current living situation and interests during the dialogue. The dialogue unit customizes the content of the dialogue based on, for example, the user's current living situation. The dialogue unit can also customize the content of the dialogue based on the user's current interests. The dialogue unit can also provide optimal dialogue content based on the user's current situation. In this way, by customizing the content of the dialogue based on the user's current living situation and interests, it is possible to provide a dialogue that is suitable for the user. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on the user's current living situation and interests into AI and have the AI ​​customize the content of the dialogue.

[0055] During the dialogue, the dialogue unit can analyze the user's social media activity and provide relevant advice. For example, the dialogue unit can analyze the user's social media activity history and provide relevant advice. The dialogue unit can also provide advice related to accounts or topics the user follows. The dialogue unit can also analyze the content of the user's social media posts and provide optimal advice. In this way, by analyzing social media activity, it is possible to provide advice that is appropriate for the user. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on social media activity into AI and have the AI ​​provide relevant advice.

[0056] The discussion unit can generate the content of the discussion by taking into account the context and background of the statements made by the great person avatar during the discussion. The discussion unit generates the content of the discussion by taking into account, for example, the social background at the time the great person avatar made the statement. The discussion unit can also generate the content of the discussion by taking into account the trends and circumstances at the time the influencer avatar made the statement. The discussion unit can also generate the content of the discussion by taking into account the emotions and intentions at the time the great person avatar made the statement. In this way, by generating the content of the discussion by taking into account the context and background of the statement, more appropriate discussions can be provided. Some or all of the above-mentioned processing in the discussion unit may be performed using, for example, AI, or may be performed without using AI. For example, the discussion unit can input data on the context and background of the statement into AI and have the AI ​​generate the content of the discussion.

[0057] During a discussion, the discussion unit can provide the most appropriate discussion by referring to the past discussion history of the great person avatar. The discussion unit can, for example, provide the most appropriate discussion based on the past discussion history of the great person avatar. The discussion unit can also provide the opinions of great person avatars who have similar discussions from the past discussion history of the great person avatar. The discussion unit can also analyze the past discussion history of the great person avatar and provide the most appropriate discussion. In this way, by referring to the past discussion history, the most appropriate discussion can be provided to the user. Some or all of the above-mentioned processing in the discussion unit may be performed using, for example, AI, or may be performed without using AI. For example, the discussion unit can input data of the past discussion history into AI and have the AI ​​provide the most appropriate discussion.

[0058] During a discussion, the discussion unit can generate the content of the discussion taking into account the geographical and cultural background of the great person avatar. For example, the discussion unit generates a discussion related to the great person avatar's hometown or area of ​​activity. The discussion unit can also generate a discussion based on the cultural background of the great person avatar. The discussion unit can also generate an optimal discussion based on the geographical background of the great person avatar. This allows for more appropriate discussions to be provided by generating the content of the discussion taking into account the geographical and cultural background. Some or all of the above-described processing in the discussion unit may be performed using, or without, AI. For example, the discussion unit can input data on the geographical and cultural background into AI and have the AI ​​generate the content of the discussion.

[0059] During the discussion, the discussion unit can improve the accuracy of the discussion by referring to literature related to the great person avatar. For example, the discussion unit can improve the accuracy of the discussion by referring to books written by the great person avatar. The discussion unit can also improve the accuracy of the discussion by referring to academic papers related to the great person avatar. The discussion unit can also improve the accuracy of the discussion by referring to historical materials related to the great person avatar. In this way, the accuracy of the discussion is improved by referring to related literature. Some or all of the above-mentioned processing in the discussion unit may be performed using AI, for example, or may be performed without using AI. For example, the discussion unit can input data from related literature into AI and have the AI ​​improve the accuracy of the discussion.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The great person avatar system can also analyze a user's past interaction history and provide more personalized advice by taking into account the user's previous inquiries and advice. For example, if a user previously asked an Einstein avatar a physics question, the next interaction could provide new information and advice related to that question. Similarly, if a user consults a Gandhi avatar about a life concern, subsequent interactions could provide ongoing advice based on Gandhi's philosophy. This allows users to receive consistent advice, building deeper understanding and trust.

[0062] The collection unit can further customize content based on the user's interests. For example, if the user is interested in science, content about science-related figures and influencers can be preferentially collected. If the user is interested in history, content about historical figures can be collected. Furthermore, if the user is interested in a particular topic, content related to that topic can be collected. This allows the user to have a more personalized experience by providing content customized based on the user's interests.

[0063] The learning module can also evaluate the reliability of statements made by famous people and influencers, prioritizing learning from highly reliable data. For example, it can prioritize learning from statements based on academic literature or statements that have received a large amount of support. It can also prioritize learning from statements related to historically important events. This allows the AI ​​avatar to learn from highly reliable data, improving its accuracy and reliability.

[0064] The selection unit can further recommend great people taking into consideration the geographical and cultural background of the user. For example, it can recommend great people related to the user's hometown or area of ​​activity. It can also recommend great people based on the user's cultural background. It can also recommend the most suitable great people based on the user's geographical background. In this way, by recommending great people taking into consideration the geographical and cultural background, it is possible to provide great people that are suitable for the user.

[0065] The dialogue unit can further analyze the user's social media activity and provide relevant advice. For example, it can analyze the user's social media activity history and provide relevant advice. It can also provide advice related to accounts and topics the user follows. It can also analyze the content of the user's social media posts and provide optimal advice. In this way, it is possible to provide advice that is appropriate for the user by analyzing social media activity.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The collection unit collects books and video content from famous people and influencers. The collection unit can automatically collect content from the Internet using web scraping technology, for example. The collection unit can also obtain data from specific platforms using APIs. For example, the collection unit collects content such as e-books and YouTube videos. Step 2: The learning unit trains the AI ​​on the collected data. For example, the learning unit uses deep learning technology to learn the speech patterns and values ​​of famous people and influencers. The learning unit can analyze text data using natural language processing technology to understand the context and intent of statements. For example, the learning unit analyzes the content of speeches and interviews by famous people and learns their speech patterns. Step 3: The selection unit selects a great person to whom the user wants to share their concerns. The selection unit may provide, for example, a search function or a filtering function, allowing the user to easily find a specific great person. The selection unit may also recommend the most suitable great person based on the user's past selection history and current interests. Step 4: The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural dialogue with the great person avatar. The dialogue unit can use a generative AI to generate appropriate answers to the user's questions. For example, if the user selects "I would like to consult Einstein about my worries," the dialogue unit generates an AI avatar of Einstein and engages in a dialogue with the user. Step 5: The discussion section manages the discussion between the great person avatars. For example, the discussion section sets the discussion topic and manages the order of comments, ensuring that the discussion between the great person avatars proceeds smoothly. The discussion section uses generative AI to generate comments made by the great person avatars, and can clarify different values ​​and opinions. For example, the discussion section could involve AI avatars of Einstein and Gandhi debating, providing users with an awareness of diversity and inclusion.

[0068] (Example 2) The great figure avatar system of an embodiment of the present invention fine-tunes AI to learn statements made by historical figures and influencers in books and video content, and then constructs an AI avatar of that person. Users can select a great figure they would like to discuss their concerns with and receive advice from that figure through chat. Furthermore, by enabling discussions between great figure avatars, it is possible to clarify different values ​​and opinions and raise awareness of diversity and inclusion. For example, books and video content by great figures and influencers are collected. The collected data includes detailed information, including the content and context of statements. Examples include speeches, interviews, and the contents of books by great figures. Next, the AI ​​is trained on the collected data. The AI ​​analyzes the collected data and learns the speech patterns and values ​​of great figures and influencers. For example, the AI ​​can understand what a particular great figure said in a given situation and reproduce that person's characteristics. Users select a great figure to have their concerns listened to through the system. For example, if a user selects "I would like to consult with Einstein about my concerns," an AI avatar of Einstein is generated. Users can chat with Einstein and get advice. It's also possible for great-figure avatars to debate with each other. For example, AI avatars of Einstein and Gandhi debate to clarify their differing values ​​and opinions. This allows users to become more aware of diversity and inclusion. This system gives users the feeling of receiving direct advice from great historical figures and influencers, and by learning about different values ​​and opinions, they can grow and gain new perspectives. The great-figure avatar system thus gives users the feeling of receiving direct advice from great historical figures and influencers, and by learning about different values ​​and opinions, they can grow and gain new perspectives.

[0069] The great person avatar system according to the embodiment includes a collection unit, a learning unit, a selection unit, a dialogue unit, and a discussion unit. The collection unit collects books and video content by great people and influencers. The collection unit can automatically collect content on the Internet using, for example, web scraping technology. The collection unit can also obtain data from specific platforms using an API. For example, the collection unit collects content such as e-books and videos from video sites (e.g., YouTube videos). The learning unit trains an AI based on the collected data. The learning unit can learn the speech patterns and values ​​of great people and influencers using, for example, deep learning technology. The learning unit can analyze text data using natural language processing technology to understand the context and intent of the speeches. For example, the learning unit analyzes the content of speeches and interviews by great people and learns their speech patterns. The selection unit selects great people to whom the user wants to share their concerns. The selection unit can provide, for example, search and filtering functions, allowing the user to easily find specific great people. The selection unit can also recommend the most suitable great person based on the user's past selection history and current interests. The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural conversation with the great person avatar. The dialogue unit can use a generation AI to generate appropriate answers to the user's questions. For example, if the user selects "I want to talk to Einstein about my problems," the dialogue unit generates an AI avatar of Einstein and engages in a dialogue with the user. The discussion unit manages discussions between the great person avatars. For example, the discussion unit sets discussion topics and manages the order of comments, ensuring smooth discussions between the great person avatars. The discussion unit can use a generation AI to generate comments for the great person avatars and clarify different values ​​and opinions. For example, the discussion unit allows AI avatars of Einstein and Gandhi to hold a discussion, providing users with an awareness of diversity and inclusion.As a result, the great figure avatar system of the embodiment provides users with the feeling of receiving direct advice from great historical figures and influencers, and by learning different values ​​and opinions, users can grow as individuals and gain new perspectives.

[0070] The collection unit collects books and video content from famous people and influencers. The collection unit can automatically collect content from the Internet using, for example, web scraping technology. Specifically, web scraping technology can automatically extract data such as text, images, and videos from specific websites and store them in a database. For example, the collection unit downloads works by famous people from e-book platforms and collects interview and lecture videos from YouTube and other video sharing sites. The collection unit can also use APIs to obtain data from specific platforms. By using APIs, the collection unit can efficiently obtain data based on specific criteria and quickly gather the necessary information. For example, the collection unit can use an e-book API to obtain all works by a specific author in one go, or use a video platform API to automatically collect videos related to specific keywords. This allows the collection unit to collect a wide range of data from various sources and comprehensively cover the statements and actions of famous people and influencers. Furthermore, the collection unit can centrally manage the collected data and perform data cleansing processes to prevent data duplication and loss. This allows the collection unit to provide highly reliable data and improve the accuracy of the subsequent learning and dialogue units.

[0071] The learning unit trains the AI ​​using the collected data. For example, the learning unit uses deep learning technology to learn the speech patterns and values ​​of great figures and influencers. Specifically, it builds a deep learning model and trains the model using collected text and audio data. For example, the learning unit analyzes the content of speeches and interviews by great figures to learn their speech patterns. It can analyze text data using natural language processing technology to understand the context and intent of their statements. For example, the learning unit analyzes the text of great figures' writings and speeches, extracting frequently used phrases and keywords and capturing the characteristics of their statements. It can also analyze audio data to learn characteristics of great figures' speaking styles, tone of voice, rhythm, and other characteristics. This allows the learning unit to reproduce the speech styles and values ​​of great figures and influencers with high accuracy. Furthermore, the learning unit continuously updates the collected data and incorporates new information to improve the accuracy of the model. For example, if newly discovered letters or unpublished interviews of great figures are collected, these data can be added to the learning and the model can be retrained to reproduce more accurate speech patterns. This allows the learning unit to constantly provide highly accurate models based on the latest information, enabling the user to have a realistic dialogue experience.

[0072] The selection unit selects a great person the user wants to talk to. The selection unit provides, for example, a search function and a filtering function, allowing the user to easily find a specific great person. Specifically, the selection unit displays a list of related great people based on keywords entered by the user, allowing the user to quickly find a great person of interest. The filtering function can also be used to narrow search results based on criteria such as the great person's field, era, or nationality. For example, the user can select categories such as "scientists" or "philosophers" to display only relevant great people. Furthermore, the selection unit can recommend the most suitable great person based on the user's past selection history and current interests. For example, an algorithm can be implemented to analyze the great people selected by the user in the past and the content of the conversations, and automatically recommend great people that match the user's interests. This allows the selection unit to quickly and accurately find a great person to discuss their concerns with, thereby improving the user experience. Furthermore, the selection unit can provide detailed information and profiles about the great person selected by the user, helping the user gain a deeper understanding of the great person. This allows the user to select an appropriate great person and receive useful advice through conversations.

[0073] The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat and voice dialogue, allowing the user to have natural conversations with the great person avatar. Specifically, text chat allows the great person avatar to respond to questions entered by the user in text format. Voice dialogue allows the user to vocally enter questions through a microphone, and the great person avatar responds vocally. The dialogue unit can generate appropriate answers to the user's questions using a generation AI. For example, if a user selects "I want to consult Einstein about my problems," the dialogue unit generates an AI avatar of Einstein and engages in a conversation with the user. The generation AI analyzes the user's question and generates appropriate answers based on Einstein's speech patterns and values. This allows the dialogue unit to enjoy realistic conversations with the great person avatar. Furthermore, the dialogue unit can support ongoing dialogue by saving the user's dialogue history and referencing past dialogue content. For example, the great person avatar can provide appropriate follow-up questions or advice based on the user's previous consultations. This allows the dialogue unit to provide the user with a consistent dialogue experience and deep insight into the user's concerns and questions.

[0074] The discussion section manages discussions between great person avatars. For example, the discussion section sets discussion topics and manages the order of comments, ensuring smooth progress between the great person avatars. Specifically, the discussion section starts discussions between great person avatars based on topics set by the user and manages the order and content of each avatar's comments. The discussion section uses a generation AI to generate comments from the great person avatars and clarify different values ​​and opinions. For example, the discussion section uses AI avatars of Einstein and Gandhi to hold a discussion, providing users with awareness of diversity and inclusion. The generation AI generates appropriate comments during the discussion based on the speech patterns and values ​​of each great person, supporting deeper discussions. This allows the discussion section to provide users with opportunities to learn different perspectives and opinions, enabling self-growth and new perspectives. Furthermore, the discussion section can monitor the progress of the discussion in real time and adjust the direction of the discussion as needed. For example, if a discussion becomes one-sided or becomes too biased toward a particular topic, the discussion section can suggest a new topic at the appropriate time or change the focus of the discussion to achieve a balanced discussion. In this way, the discussion section can provide users with diverse perspectives and opinions and support them in gaining deeper insights.

[0075] The collection unit can collect books or video content from famous people or influencers. The collection unit can automatically collect content on the Internet using, for example, web scraping technology. The collection unit can also obtain data from specific platforms using APIs. For example, the collection unit collects content such as e-books and YouTube videos. By collecting books and video content from famous people or influencers, data can be obtained for AI learning. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input data collected using web scraping technology into AI and have the AI ​​analyze the data.

[0076] The learning unit can analyze the collected data and learn the speech patterns or values ​​of great figures or influencers. The learning unit can, for example, use deep learning technology to learn the speech patterns and values ​​of great figures and influencers. The learning unit can analyze text data using natural language processing technology to understand the context and intent of the statements. For example, the learning unit can analyze the content of speeches and interviews of great figures and learn their speech patterns. In this way, the accuracy of the AI ​​avatar is improved by analyzing the collected data and learning the speech patterns and values ​​of great figures and influencers. Some or all of the above-mentioned processing in the learning unit is performed using a generation AI. For example, the learning unit can input the collected data into the generation AI and have the generation AI learn the speech patterns and values.

[0077] The selection unit allows the user to select a great person with whom they would like to consult. The selection unit may provide, for example, a search function or a filtering function, allowing the user to easily find a specific great person. The selection unit may also recommend the most suitable great person based on the user's past selection history and current interests. This allows the user to select a great person to listen to their concerns, thereby generating an appropriate great person avatar. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit may input the user's past selection history into AI and have the AI ​​recommend the most suitable great person.

[0078] The dialogue unit allows the user to have a chat-style conversation with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural conversation with the great person avatar. The dialogue unit can generate an appropriate answer to the user's question using a generation AI. For example, when a user selects "I want to talk to Einstein about my worries," the dialogue unit generates an AI avatar of Einstein and engages in a conversation with the user. This allows the user to have a chat-style conversation with the selected great person avatar and receive advice from the great person. Some or all of the above-mentioned processing in the dialogue unit is performed using a generation AI. For example, the dialogue unit can input a user's question into the generation AI and have the generation AI generate an appropriate answer.

[0079] The discussion unit can manage discussions between great person avatars. For example, the discussion unit can set discussion topics and manage the order of comments to ensure that discussions between great person avatars proceed smoothly. The discussion unit can use a generation AI to generate comments made by the great person avatars and clarify different values ​​and opinions. For example, the discussion unit can have AI avatars of Einstein and Gandhi hold a discussion to provide users with awareness of diversity and inclusion. By managing discussions between great person avatars, different values ​​and opinions can be clarified and users can become aware of diversity and inclusion. Some or all of the above-mentioned processing in the discussion unit can be performed using AI, for example, or without AI. For example, the discussion unit can input discussion topic settings into AI and have the AI ​​generate comment content.

[0080] The collection unit can estimate the user's emotions and adjust the type of content to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can prioritize collecting content that is relaxing. If the user is excited, the collection unit can also prioritize collecting content that is stimulating. Furthermore, if the user is feeling depressed, the collection unit can also prioritize collecting content that includes words of encouragement. This allows the type of content to be collected to be adjusted based on the user's emotions, thereby providing content that is appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the type of content to be collected.

[0081] The collection unit can evaluate the reliability of statements made by famous people or influencers and prioritize collection of highly reliable content. For example, if a statement made by a famous person or influencer is based on academic literature, the collection unit can prioritize collection of that content. The collection unit can also prioritize collection of content made by a famous person or influencer that has received a large amount of support. The collection unit can also prioritize collection of content made by a famous person or influencer that is related to historically important events. In this way, by preferentially collecting highly reliable content, the AI ​​can learn highly reliable data. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can input the reliability evaluation of statements into AI and have the AI ​​select highly reliable content.

[0082] When collecting data, the collection unit can simultaneously collect not only the content of the statements made in the content but also the background and circumstances of the statements. For example, the collection unit may record the location and time when a statement was made by a famous person and collect background information. The collection unit may also collect the social circumstances and trends when an influencer made a statement. The collection unit may also collect the emotions and intentions of the famous person or influencer when the statement was made. In this way, by simultaneously collecting the background and circumstances of the statement, more detailed data can be learned by the AI. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input data on the background and circumstances of the statement into the AI ​​and have the AI ​​collect detailed data.

[0083] The collection unit can estimate the user's emotions and prioritize the content to be collected based on the estimated user emotions. For example, if the user is relaxed, the collection unit can prioritize collecting content that is relaxing. If the user is excited, the collection unit can also prioritize collecting content that is stimulating. Furthermore, if the user is depressed, the collection unit can also prioritize collecting content that includes encouraging words. This allows content appropriate for the user to be provided by prioritizing the content to be collected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of the content to be collected.

[0084] The collection unit can select content to collect taking into consideration the geographical and cultural background of the great person or influencer. For example, the collection unit collects content related to the great person's or influencer's hometown or area of ​​activity. The collection unit can also collect content based on the great person's or influencer's cultural background. The collection unit can also collect content related to the history and culture of the area where the great person or influencer made a statement. This allows for more appropriate data to be collected by selecting content taking into consideration the geographical and cultural background. Some or all of the above-mentioned processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the geographical and cultural background into AI and have the AI ​​select the content.

[0085] The collection unit can analyze the social media activities of celebrities and influencers and collect related content. For example, the collection unit collects social media statements and posts by celebrities and influencers. The collection unit can also collect content related to accounts and topics followed by celebrities and influencers. The collection unit can also analyze the social media activity history of celebrities and influencers and collect related content. This allows for the collection of more diverse data by analyzing social media activities. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, AI, for example. For example, the collection unit can input social media activity data into AI and have the AI ​​collect related content.

[0086] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit can prioritize learning data with relaxing content. If the user is excited, the learning unit can also prioritize learning data with stimulating content. Furthermore, if the user is depressed, the learning unit can also prioritize learning data containing encouraging words. This allows the user to learn data suitable for the user by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit can be performed using the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and have the generation AI select the training data.

[0087] During learning, the learning unit can analyze the context of statements made by famous people or influencers to understand the intention and background of the statements. For example, the learning unit can analyze the social background when a famous person made a statement to understand their intention. The learning unit can also analyze the trends and circumstances when an influencer made a statement to understand their intention. The learning unit can also analyze the emotions and intentions of famous people or influencers when they made a statement to understand their background. This enables more accurate learning by analyzing the context of statements. Some 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. For example, the learning unit can input context data of a statement into AI and have the AI ​​understand the intention and background.

[0088] During learning, the learning unit can determine learning priorities based on the frequency and importance of statements made by famous people or influencers. For example, the learning unit prioritizes learning of frequently made statements made by famous people or influencers. The learning unit can also prioritize learning of important statements made by famous people or influencers. The learning unit can also determine learning priorities based on the influence of the statements made by famous people or influencers. This enables efficient learning by determining learning priorities based on the frequency and importance of statements. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data on the frequency and importance of statements into AI and have the AI ​​determine the learning priorities.

[0089] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated user emotions. For example, if the user is relaxed, the learning unit can set the learning frequency low. If the user is excited, the learning unit can also set the learning frequency high. If the user is depressed, the learning unit can also set the learning frequency to medium. This allows learning that is appropriate for the user by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit can be performed using the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the learning frequency.

[0090] During learning, the learning unit can weight the learning data based on the time and circumstances of the statement made by the famous person or influencer. For example, the learning unit weights the data based on the time when the statement was made by the famous person or influencer. The learning unit can also weight the data based on the circumstances in which the statement was made by the famous person or influencer. The learning unit can also weight the data based on the social background at the time when the statement was made by the famous person or influencer. In this way, more accurate learning is possible by weighting the data based on the time and circumstances of the statement. Some 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. For example, the learning unit can input data on the time and circumstances of the statement into AI and have the AI ​​weight the data.

[0091] During learning, the learning unit can improve the accuracy of the learning by referring to literature related to great people and influencers. The learning unit can improve the accuracy of the learning by referring to, for example, books written by great people and influencers. The learning unit can also improve the accuracy of the learning by referring to academic papers related to great people and influencers. The learning unit can also improve the accuracy of the learning by referring to historical materials related to great people and influencers. In this way, the accuracy of the learning is improved by referring to related literature. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI, or can be performed without using AI. For example, the learning unit can input data from related literature into the AI ​​and have the AI ​​improve the accuracy of the learning.

[0092] The selection unit can estimate the user's emotions and adjust the display method of the options based on the estimated user emotions. For example, if the user is relaxed, the selection unit can display detailed options. If the user is excited, the selection unit can also display concise options. Furthermore, if the user is depressed, the selection unit can display options including encouraging words. This allows the user to be provided with options that are appropriate for them by adjusting the display method of the options based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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-described processing in the selection unit can be performed using the generation AI. For example, the selection unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method of the options.

[0093] When making a selection, the selection unit can recommend the most suitable great person by referring to the user's past selection history. For example, the selection unit recommends the most suitable great person based on great people selected by the user in the past. The selection unit can also recommend great people with similar concerns from the user's past selection history. The selection unit can also analyze the user's past selection history and recommend the most suitable great person. In this way, by referring to the past selection history, the most suitable great person can be recommended to the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data of the past selection history into AI and have the AI ​​recommend the most suitable great person.

[0094] At the time of selection, the selection unit can filter great people based on the user's current worries and interests. The selection unit filters great people based on, for example, the worries the user currently has. The selection unit can also filter great people based on the user's current interests. The selection unit can also filter great people based on the user's current situation. In this way, by filtering great people based on the user's current worries and interests, it is possible to provide great people that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data on the user's current worries and interests into AI and have the AI ​​perform the filtering of great people.

[0095] The selection unit can estimate the user's emotions and prioritize options based on the estimated user emotions. For example, if the user is relaxed, the selection unit can prioritize options with relaxing content to display. If the user is excited, the selection unit can also prioritize options with stimulating content to display. Furthermore, if the user is depressed, the selection unit can also prioritize options containing encouraging words to display. This allows options suitable for the user to be provided by prioritizing options based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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-described processing in the selection unit can be performed using the generation AI. For example, the selection unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of options.

[0096] The selection unit can recommend great people taking into consideration the user's geographical and cultural background when making a selection. For example, the selection unit recommends great people related to the user's hometown or area of ​​activity. The selection unit can also recommend great people based on the user's cultural background. The selection unit can also recommend the most suitable great people based on the user's geographical background. In this way, by recommending great people taking into consideration the user's geographical and cultural background, it is possible to provide great people that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, or without, AI, for example. For example, the selection unit can input data on the geographical and cultural background into AI and have the AI ​​recommend great people.

[0097] At the time of selection, the selection unit can analyze the user's social media activity and recommend related notable figures. For example, the selection unit can analyze the user's social media activity history and recommend related notable figures. The selection unit can also recommend notable figures related to accounts or topics the user follows. The selection unit can also analyze the content of the user's social media posts and recommend the most suitable notable figures. In this way, by analyzing social media activity, it is possible to provide notable figures that are suitable for the user. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input data on social media activity into AI and have the AI ​​recommend notable figures.

[0098] The dialogue unit can estimate the user's emotions and adjust the dialogue expression method based on the estimated user emotions. For example, if the user is relaxed, the dialogue unit can use a calm expression method to dialogue. If the user is excited, the dialogue unit can use a lively expression method to dialogue. Furthermore, if the user is depressed, the dialogue unit can use an expression method that includes words of encouragement to dialogue. This allows the dialogue to be tailored to the user by adjusting the dialogue expression method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the dialogue unit can be performed using the generation AI. For example, the dialogue unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the dialogue expression method.

[0099] The dialogue unit can generate the content of the dialogue taking into account the context and background of the statement made by the great person during the dialogue. The dialogue unit can generate the content of the dialogue taking into account, for example, the social background when the statement made by the great person. The dialogue unit can also generate the content of the dialogue taking into account the trends and circumstances when the statement made by the influencer. The dialogue unit can also generate the content of the dialogue taking into account the emotions and intentions of the great person or influencer when they made the statement. In this way, by generating the content of the dialogue taking into account the context and background of the statement, it is possible to provide a more appropriate dialogue. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on the context and background of the statement into AI and have the AI ​​generate the content of the dialogue.

[0100] During a dialogue, the dialogue unit can provide optimal advice by referring to the user's past dialogue history. The dialogue unit can provide optimal advice based on, for example, the user's past dialogue history. The dialogue unit can also provide advice from great people who have similar concerns based on the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history and provide the most appropriate advice. In this way, optimal advice can be provided to the user by referring to the past dialogue history. Some or all of the above-described processing in the dialogue unit can be performed using, for example, AI, or can be performed without using AI. For example, the dialogue unit can input data from the past dialogue history into AI and have the AI ​​provide optimal advice.

[0101] The dialogue unit can estimate the user's emotions and adjust the length of the dialogue based on the estimated user emotions. For example, the dialogue unit can provide a longer dialogue if the user is relaxed. The dialogue unit can also provide a shorter dialogue if the user is excited. Furthermore, the dialogue unit can provide a medium-length dialogue if the user is depressed. This allows the dialogue to be tailored to the user by adjusting the length of the dialogue based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the dialogue unit can be performed using the generation AI. For example, the dialogue unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the dialogue.

[0102] The dialogue unit can customize the content of the dialogue based on the user's current living situation and interests during the dialogue. The dialogue unit customizes the content of the dialogue based on, for example, the user's current living situation. The dialogue unit can also customize the content of the dialogue based on the user's current interests. The dialogue unit can also provide optimal dialogue content based on the user's current situation. In this way, by customizing the content of the dialogue based on the user's current living situation and interests, it is possible to provide a dialogue that is suitable for the user. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on the user's current living situation and interests into AI and have the AI ​​customize the content of the dialogue.

[0103] During the dialogue, the dialogue unit can analyze the user's social media activity and provide relevant advice. For example, the dialogue unit can analyze the user's social media activity history and provide relevant advice. The dialogue unit can also provide advice related to accounts or topics the user follows. The dialogue unit can also analyze the content of the user's social media posts and provide optimal advice. In this way, by analyzing social media activity, it is possible to provide advice that is appropriate for the user. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input data on social media activity into AI and have the AI ​​provide relevant advice.

[0104] The discussion unit can estimate the user's emotions and adjust the way the discussion proceeds based on the estimated user's emotions. For example, if the user is relaxed, the discussion unit can conduct the discussion in a calm manner. If the user is excited, the discussion unit can conduct the discussion in a lively manner. Furthermore, if the user is depressed, the discussion unit can conduct the discussion in a manner that includes words of encouragement. This allows the discussion to be tailored to the user by adjusting the way the discussion proceeds based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the discussion unit can be performed using the generation AI. For example, the discussion unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the discussion proceeds.

[0105] The discussion unit can generate the content of the discussion by taking into account the context and background of the statements made by the great person avatar during the discussion. The discussion unit generates the content of the discussion by taking into account, for example, the social background at the time the great person avatar made the statement. The discussion unit can also generate the content of the discussion by taking into account the trends and circumstances at the time the influencer avatar made the statement. The discussion unit can also generate the content of the discussion by taking into account the emotions and intentions at the time the great person avatar made the statement. In this way, by generating the content of the discussion by taking into account the context and background of the statement, more appropriate discussions can be provided. Some or all of the above-mentioned processing in the discussion unit may be performed using, for example, AI, or may be performed without using AI. For example, the discussion unit can input data on the context and background of the statement into AI and have the AI ​​generate the content of the discussion.

[0106] During a discussion, the discussion unit can provide the most appropriate discussion by referring to the past discussion history of the great person avatar. The discussion unit can, for example, provide the most appropriate discussion based on the past discussion history of the great person avatar. The discussion unit can also provide the opinions of great person avatars who have similar discussions from the past discussion history of the great person avatar. The discussion unit can also analyze the past discussion history of the great person avatar and provide the most appropriate discussion. In this way, by referring to the past discussion history, the most appropriate discussion can be provided to the user. Some or all of the above-mentioned processing in the discussion unit may be performed using, for example, AI, or may be performed without using AI. For example, the discussion unit can input data of the past discussion history into AI and have the AI ​​provide the most appropriate discussion.

[0107] The discussion unit can estimate the user's emotions and determine the priority of discussions based on the estimated user emotions. For example, if the user is relaxed, the discussion unit can prioritize discussions with relaxing content. If the user is excited, the discussion unit can also prioritize discussions with stimulating content. Furthermore, if the user is depressed, the discussion unit can prioritize discussions that include encouraging words. This allows discussions that are appropriate for the user to be provided by determining the priority of discussions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the discussion unit can be performed using the generation AI. For example, the discussion unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of discussions.

[0108] During a discussion, the discussion unit can generate the content of the discussion taking into account the geographical and cultural background of the great person avatar. For example, the discussion unit generates a discussion related to the great person avatar's hometown or area of ​​activity. The discussion unit can also generate a discussion based on the cultural background of the great person avatar. The discussion unit can also generate an optimal discussion based on the geographical background of the great person avatar. This allows for more appropriate discussions to be provided by generating the content of the discussion taking into account the geographical and cultural background. Some or all of the above-described processing in the discussion unit may be performed using, or without, AI. For example, the discussion unit can input data on the geographical and cultural background into AI and have the AI ​​generate the content of the discussion.

[0109] During the discussion, the discussion unit can improve the accuracy of the discussion by referring to literature related to the great person avatar. For example, the discussion unit can improve the accuracy of the discussion by referring to books written by the great person avatar. The discussion unit can also improve the accuracy of the discussion by referring to academic papers related to the great person avatar. The discussion unit can also improve the accuracy of the discussion by referring to historical materials related to the great person avatar. In this way, the accuracy of the discussion is improved by referring to related literature. Some or all of the above-mentioned processing in the discussion unit may be performed using AI, for example, or may be performed without using AI. For example, the discussion unit can input data from related literature into AI and have the AI ​​improve the accuracy of the discussion.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The great person avatar system can also analyze a user's past interaction history and provide more personalized advice by taking into account the user's previous inquiries and advice. For example, if a user previously asked an Einstein avatar a physics question, the next interaction could provide new information and advice related to that question. Similarly, if a user consults a Gandhi avatar about a life concern, subsequent interactions could provide ongoing advice based on Gandhi's philosophy. This allows users to receive consistent advice, building deeper understanding and trust.

[0112] The collection unit can further customize content based on the user's interests. For example, if the user is interested in science, content about science-related figures and influencers can be preferentially collected. If the user is interested in history, content about historical figures can be collected. Furthermore, if the user is interested in a particular topic, content related to that topic can be collected. This allows the user to have a more personalized experience by providing content customized based on the user's interests.

[0113] The learning module can also evaluate the reliability of statements made by famous people and influencers, prioritizing learning from highly reliable data. For example, it can prioritize learning from statements based on academic literature or statements that have received a large amount of support. It can also prioritize learning from statements related to historically important events. This allows the AI ​​avatar to learn from highly reliable data, improving its accuracy and reliability.

[0114] The selection unit can further recommend great people taking into consideration the geographical and cultural background of the user. For example, it can recommend great people related to the user's hometown or area of ​​activity. It can also recommend great people based on the user's cultural background. It can also recommend the most suitable great people based on the user's geographical background. In this way, by recommending great people taking into consideration the geographical and cultural background, it is possible to provide great people that are suitable for the user.

[0115] The dialogue unit can further analyze the user's social media activity and provide relevant advice. For example, it can analyze the user's social media activity history and provide relevant advice. It can also provide advice related to accounts and topics the user follows. It can also analyze the content of the user's social media posts and provide optimal advice. In this way, it is possible to provide advice that is appropriate for the user by analyzing social media activity.

[0116] The collection unit can estimate the user's emotions and adjust the type of content to be collected based on the estimated user's emotions. For example, if the user is feeling stressed, it can prioritize collecting content that is relaxing. Also, if the user is excited, it can prioritize collecting content that is stimulating. Furthermore, if the user is depressed, it can prioritize collecting content that includes words of encouragement. In this way, by adjusting the type of content to be collected based on the user's emotions, it is possible to provide content that is suitable for the user.

[0117] The learning unit can estimate the user's emotions and select learning data based on the estimated user's emotions. For example, if the user is relaxed, data with relaxing content can be prioritized for learning. Also, if the user is excited, data with stimulating content can be prioritized for learning. Furthermore, if the user is depressed, data containing encouraging words can be prioritized for learning. In this way, by selecting learning data based on the user's emotions, data suitable for the user can be learned.

[0118] The selection unit can estimate the user's emotions and adjust the display method of options based on the estimated user's emotions. For example, if the user is relaxed, detailed options can be displayed. If the user is excited, concise options can be displayed. Furthermore, if the user is depressed, options containing encouraging words can be displayed. In this way, by adjusting the display method of options based on the user's emotions, it is possible to provide options that are suitable for the user.

[0119] The dialogue unit can estimate the user's emotions and adjust the dialogue expression method based on the estimated user's emotions. For example, if the user is relaxed, the dialogue can be conducted using a calm expression method. If the user is excited, the dialogue can be conducted using a lively expression method. Furthermore, if the user is depressed, the dialogue can be conducted using an expression method that includes encouraging words. In this way, by adjusting the dialogue expression method based on the user's emotions, a dialogue that is appropriate for the user can be provided.

[0120] The discussion unit can estimate the user's emotions and adjust the way the discussion proceeds based on the estimated user's emotions. For example, if the user is relaxed, the discussion can be conducted in a calm manner. If the user is excited, the discussion can be conducted in a lively manner. Furthermore, if the user is depressed, the discussion can be conducted in a manner that includes words of encouragement. In this way, by adjusting the way the discussion proceeds based on the user's emotions, it is possible to provide a discussion that is suitable for the user.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The collection unit collects books and video content from famous people and influencers. The collection unit can automatically collect content from the Internet using web scraping technology, for example. The collection unit can also obtain data from specific platforms using APIs. For example, the collection unit collects content such as e-books and YouTube videos. Step 2: The learning unit trains the AI ​​on the collected data. For example, the learning unit uses deep learning technology to learn the speech patterns and values ​​of famous people and influencers. The learning unit can analyze text data using natural language processing technology to understand the context and intent of statements. For example, the learning unit analyzes the content of speeches and interviews by famous people and learns their speech patterns. Step 3: The selection unit selects a great person to whom the user wants to share their concerns. The selection unit may provide, for example, a search function or a filtering function, allowing the user to easily find a specific great person. The selection unit may also recommend the most suitable great person based on the user's past selection history and current interests. Step 4: The dialogue unit allows the user to chat with the selected great person avatar. The dialogue unit provides, for example, text chat or voice dialogue, allowing the user to have a natural dialogue with the great person avatar. The dialogue unit can use a generative AI to generate appropriate answers to the user's questions. For example, if the user selects "I would like to consult Einstein about my worries," the dialogue unit generates an AI avatar of Einstein and engages in a dialogue with the user. Step 5: The discussion section manages the discussion between the great person avatars. For example, the discussion section sets the discussion topic and manages the order of comments, ensuring that the discussion between the great person avatars proceeds smoothly. The discussion section uses generative AI to generate comments made by the great person avatars, and can clarify different values ​​and opinions. For example, the discussion section could involve AI avatars of Einstein and Gandhi debating, providing users with an awareness of diversity and inclusion.

[0123] 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 regarding 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.

[0124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats including 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. The AIs other than the generation AI are, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but are not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or in whole by AI, but are not limited to these examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0125] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements, including the collection unit, learning unit, selection unit, dialogue unit, and discussion unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14 and automatically collects content on the Internet. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and causes AI to learn the collected data. The selection unit is realized by the control unit 46A of the smart device 14 and allows the user to select a great person to whom they would like to have their concerns listened. The dialogue unit is realized by the control unit 46A of the smart device 14 and allows the user to interact with the selected great person avatar in a chat format. The discussion unit is realized by the specific processing unit 290 of the data processing device 12 and manages discussions between the great person avatars. The correspondence between each unit and the device or control unit is not limited to the above example and various modifications are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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, RAM 30, and 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.

[0130] 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.

[0131] 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 audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 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.

[0135] 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.

[0136] 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 a 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 these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 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 perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] 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 regarding 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.

[0140] 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. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0141] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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.

[0142] Each of the multiple elements, including the collection unit, learning unit, selection unit, dialogue unit, and discussion unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214 and automatically collects content on the Internet. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and causes AI to learn the collected data. The selection unit is realized by the control unit 46A of the smart glasses 214 and allows the user to select a great person to whom they would like their concerns listened. The dialogue unit is realized by the control unit 46A of the smart glasses 214 and allows the user to interact with the selected great person avatar in a chat format. The discussion unit is realized by the specific processing unit 290 of the data processing device 12 and manages discussions between the great person avatars. The correspondence between each unit and the device or control unit is not limited to the above example and various modifications are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] 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, RAM 30, and 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.

[0146] 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.

[0147] 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 audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 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.

[0151] 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.

[0152] 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 a 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 these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that 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 identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] 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 regarding 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.

[0156] 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. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0157] 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] Each of the multiple elements, including the collection unit, learning unit, selection unit, dialogue unit, and discussion unit, described above, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the headset-type terminal 314 and automatically collects content on the Internet. The learning unit is implemented by the specific processing unit 290 of the data processing device 12 and causes an AI to learn the collected data. The selection unit is implemented by the control unit 46A of the headset-type terminal 314 and allows the user to select a great person to whom they would like their concerns listened. The dialogue unit is implemented by the control unit 46A of the headset-type terminal 314 and allows the user to chat with the selected great person avatar. The discussion unit is implemented by the specific processing unit 290 of the data processing device 12 and manages discussions between the great person avatars. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 7, a 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.

[0161] 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, RAM 30, and 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.

[0162] 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.

[0163] 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 audio according to instructions from the processor 46.

[0164] 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 images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0165] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0166] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0167] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 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.

[0168] 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.

[0169] 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 a 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 these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0170] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0171] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0172] 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 a user input regarding 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.

[0173] 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. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0174] 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. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0175] Each of the multiple elements, including the collection unit, learning unit, selection unit, dialogue unit, and discussion unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414 and automatically collects content on the Internet. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and causes an AI to learn the collected data. The selection unit is realized by the control unit 46A of the robot 414 and allows the user to select a great person to whom they would like to have their concerns listened. The dialogue unit is realized by the control unit 46A of the robot 414 and allows the user to interact with the selected great person avatar in a chat format. The discussion unit is realized by the specific processing unit 290 of the data processing device 12 and manages discussions between the great person avatars. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0176] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0178] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0179] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0180] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0183] 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.

[0184] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] 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.

[0187] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0188] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0189] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an 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 above-mentioned various processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0191] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0192] The above-described 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 description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0193] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0194] (Appendix 1) A collection department that collects books or video content of great people or influencers; a learning unit that causes an AI to learn the data collected by the collection unit; a selection section in which a user selects a great person; a dialogue unit for allowing a user to dialogue with the great person avatar selected by the selection unit; A discussion unit that manages discussions between great person avatars. A system characterized by: (Appendix 2) The collecting unit Collect books or video content from great people or influencers 2. The system of claim 1. (Appendix 3) The learning unit Analyze the collected data to learn the speech patterns or values ​​of prominent figures or influencers. 2. The system of claim 1. (Appendix 4) The selection unit The user selects the great person they want to consult. 2. The system of claim 1. (Appendix 5) The dialogue unit The user interacts with the selected great person avatar in chat format. 2. The system of claim 1. (Appendix 6) The discussion section Moderate discussions between great avatars 2. The system of claim 1. (Appendix 7) The collecting unit Inferring user emotions and adjusting the type of content to be collected based on the estimated user emotions 2. The system of claim 1. (Appendix 8) The collecting unit Evaluate the credibility of statements made by prominent figures and influencers, and prioritize collection of highly reliable content. 2. The system of claim 1. (Appendix 9) The collecting unit When collecting content, not only the content of the comments but also the context and circumstances of the comments are collected at the same time. 2. The system of claim 1. (Appendix 10) The collecting unit Estimate user emotions and prioritize content to be collected based on the estimated user emotions. 2. The system of claim 1. (Appendix 11) The collecting unit Select content to collect, taking into account the geographical and cultural backgrounds of prominent figures and influencers. 2. The system of claim 1. (Appendix 12) The collecting unit Analyze the social media activity of celebrities and influencers and collect relevant content 2. The system of claim 1. (Appendix 13) The learning unit Estimate the user's emotions and select training data based on the estimated user emotions. 2. The system of claim 1. (Appendix 14) The learning unit During learning, analyze the context of statements made by important people and influencers to understand their intentions and background. 2. The system of claim 1. (Appendix 15) The learning unit When studying, prioritize your learning based on the frequency and importance of statements by prominent figures and influencers. 2. The system of claim 1. (Appendix 16) The learning unit Estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1. (Appendix 17) The learning unit During training, the training data is weighted based on the timing and context of statements made by prominent figures and influencers. 2. The system of claim 1. (Appendix 18) The learning unit When studying, refer to relevant literature on great people and influencers to improve the accuracy of your learning. 2. The system of claim 1. (Appendix 19) The selection unit Inferring user emotions and adjusting the way options are displayed based on the estimated user emotions 2. The system of claim 1. (Appendix 20) The selection unit When selecting, the system will refer to the user's past selection history to recommend the most suitable great person. 2. The system of claim 1. (Appendix 21) The selection unit At the time of selection, filter great people based on the user's current concerns and interests 2. The system of claim 1. (Appendix 22) The selection unit Estimate the user's emotions and prioritize options based on the estimated user emotions. 2. The system of claim 1. (Appendix 23) The selection unit When selecting, recommend great people taking into account the user's geographical and cultural background. 2. The system of claim 1. (Appendix 24) The selection unit At the time of selection, analyze the user's social media activity and recommend relevant great people. 2. The system of claim 1. (Appendix 25) The dialogue unit Estimate the user's emotions and adjust the dialogue expression based on the estimated user emotions. 2. The system of claim 1. (Appendix 26) The dialogue unit During dialogue, the content of the dialogue is generated taking into account the context and background of the great person's words. 2. The system of claim 1. (Appendix 27) The dialogue unit During a conversation, the system provides optimal advice by referencing the user's past conversation history. 2. The system of claim 1. (Appendix 28) The dialogue unit Estimate the user's emotions and adjust the length of the dialogue based on the estimated user emotions. 2. The system of claim 1. (Appendix 29) The dialogue unit At the time of the interaction, customize the content of the interaction based on the user's current life situation and interests 2. The system of claim 1. (Appendix 30) The dialogue unit Analyze your social media activity and provide relevant advice as you interact with them 2. The system of claim 1. (Appendix 31) The discussion section Estimate the user's emotions and adjust the discussion based on the estimated user emotions. 2. The system of claim 1. (Appendix 32) The discussion section During discussions, the content of the discussion is generated taking into account the context and background of the great person avatar's remarks. 2. The system of claim 1. (Appendix 33) The discussion section During discussions, the best discussions are provided by referring to the past discussion history of the great person avatar. 2. The system of claim 1. (Appendix 34) The discussion section Estimate user sentiment and prioritize discussions based on the estimated sentiment 2. The system of claim 1. (Appendix 35) The discussion section During discussions, the content of the discussion is generated taking into account the geographical and cultural background of the great person avatar. 2. The system of claim 1. (Appendix 36) The discussion section During discussions, refer to literature related to the great person avatar to improve the accuracy of the discussion. 2. The system of claim 1. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection department that collects books or video content of great people or influencers; A learning unit that causes an AI to learn the data collected by the collection unit; a selection section in which a user selects a great person; a dialogue unit for allowing a user to dialogue with the great person avatar selected by the selection unit; A discussion unit that manages discussions between great person avatars. A system characterized by:

2. The learning unit is Analyze the collected data and learn the speech patterns or values ​​of great people or influencers.

2. The system of claim 1 .

3. The selection unit is The user selects the great person they want to consult.

2. The system of claim 1 .

4. The dialogue unit includes: The user interacts with the selected great person avatar in chat format.

2. The system of claim 1 .

5. The discussion section includes: Moderate discussions between great avatars 2. The system of claim 1 .

6. The collecting unit includes: Inferring user sentiment and adjusting the type of content to be collected based on the estimated user sentiment 2. The system of claim 1 .

7. The collecting unit includes: Evaluate the credibility of statements made by prominent figures and influencers, and prioritize collection of highly credible content.

2. The system of claim 1 .

Images