System

Abstract

An object of a system according to an embodiment is to provide an opportunity for a AI avatar to meet a user instead even if the user does not perform an action by himself / herself.SOLUTION: A system according to an embodiment includes a basic-information registering unit, a AI avatar generating unit, an automatic transmitting unit, and a content checking unit. The basic information registration unit registers basic information and hobbies and preferences. The AI avatar generating unit generates a AI avatar based on the basic data and the hobbies and preferences registered by the basic data registering unit. The automatic transmission unit automatically transmits a like of the AI avatar generated by the AI avatar generation unit to the other party. The content check unit checks the content of the communication performed by the AI avatar.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] Conventional technology requires users to take action themselves, which limits opportunities for encounters.

[0005] The system according to the embodiment aims to provide an opportunity for a user to meet someone through an AI avatar, without the user having to take any action themselves. [Means for solving the problem]

[0006] The system according to the embodiment includes a basic information registration unit, an AI avatar generation unit, an automatic sending unit, and a content checking unit. The basic information registration unit registers basic information and hobbies and preferences. The AI ​​avatar generation unit generates an AI avatar based on the basic information and hobbies and preferences registered by the basic information registration unit. The automatic sending unit allows the AI ​​avatar generated by the AI ​​avatar generation unit to automatically send a "Like" to the other party. The content checking unit checks the content of the exchange conducted by the AI ​​avatar. [Effects of the Invention]

[0007] In the system according to the embodiment, an AI avatar can provide opportunities for encounters without the user having to take any action themselves. [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 AI ​​avatar system according to an embodiment of the present invention is a system in which an AI avatar automatically sends "likes" and messages to other users based on the basic information and hobbies and preferences registered by the user. As a result, the AI ​​avatar system automatically communicates on behalf of the user, and the user only needs to check the content of the messages. This allows the user to encounter people they would not have met through their own efforts, or people with whom they have a high compatibility.

[0029] The AI ​​avatar system according to the embodiment includes a basic information registration unit, an AI avatar generation unit, an automatic transmission unit, and a content check unit. The basic information registration unit registers a user's basic information and hobbies and preferences. For example, the user can enter information such as their name, age, gender, hobbies and preferences, and activities of interest into the system. The AI ​​avatar generation unit generates an AI avatar based on the basic information and hobbies and preferences registered by the basic information registration unit. For example, the generation AI finds a person who shares the user's hobbies and preferences and sends that person a message such as, "Hello, we have common hobbies, so I'd like to talk." The automatic transmission unit allows the AI ​​avatar generated by the AI ​​avatar generation unit to automatically send a "like" to the person. For example, the AI ​​avatar finds a person who shares the user's hobbies and preferences and sends a "like" to that person. The content check unit checks the content of the exchanges conducted by the AI ​​avatar. For example, the user can check the messages sent by the AI ​​avatar and the replies from the other person. This allows the AI ​​avatar system to automatically exchange messages on behalf of the user, while the user only needs to check the content of the messages. Users can meet people they would not have met through their own efforts, or people with whom they have a high compatibility.

[0030] The basic information registration unit can analyze a user's past behavioral history or social media postings to automatically infer and register the user's hobbies and preferences. The basic information registration unit, for example, analyzes a user's past behavioral history to automatically infer the user's hobbies and preferences. For example, the basic information registration unit infers hobbies such as watching movies or outdoor activities based on the user's frequently visited websites and app usage history. The basic information registration unit also analyzes social media postings to automatically infer the user's hobbies and preferences. For example, the basic information registration unit extracts interests such as travel and cooking from photos and comments posted by the user and registers them in the system. The basic information registration unit also analyzes a user's online shopping history to automatically infer the user's hobbies and preferences. For example, the basic information registration unit infers an interest in fashion or gadgets from products purchased or product pages viewed. In this way, the user's hobbies and preferences can be automatically inferred and registered by analyzing a user's past behavioral history and social media postings.

[0031] The basic information registration unit allows the generation AI to provide real-time feedback on the information registered by the user, thereby extracting detailed information. For example, when a user registers their hobbies and preferences, the basic information registration unit allows the generation AI to ask questions in real time to extract detailed information. For example, if the user enters "I like watching movies," the generation AI will ask, "What genre of movies do you like?" When a user enters basic information, the basic information registration unit also asks questions to request supplemental information and create a detailed profile. For example, if the user enters "I'm interested in outdoor activities," the generation AI will ask, "Specifically, what activities do you like?" When a user registers activities of interest to the basic information registration unit, the generation AI will ask related questions to collect more specific information. For example, if the user enters "I like traveling," the generation AI will ask, "Where was your most recent travel destination?" This allows real-time feedback on the information registered by the user to extract more detailed information.

[0032] The basic information registration unit can analyze a user's voice input, extract hobbies and preferences from the voice, and register them. For example, when a user registers hobbies and preferences by voice, the basic information registration unit analyzes the content using voice recognition technology and automatically extracts the hobbies and preferences. For example, if the user inputs "I like watching movies" by voice, the basic information registration unit registers that information in the system. Furthermore, when a user inputs basic information by voice, the basic information registration unit extracts detailed information using voice analysis technology and registers it in the system. For example, if the user inputs "I'm interested in outdoor activities" by voice, the basic information registration unit analyzes the content using voice recognition technology and automatically extracts hobbies and preferences. For example, if the user inputs "I like traveling" by voice, the basic information registration unit registers that information in the system. In this way, the user's voice input can be analyzed, and hobbies and preferences can be automatically extracted and registered from the voice.

[0033] The basic information registration unit collects data on events or activities the user has participated in in the past and can estimate the user's hobbies and preferences based on the data. The basic information registration unit, for example, collects data on events the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in music or sports can be estimated based on the user's participation history in music festivals or sporting events. The basic information registration unit also collects data on activities the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in social contribution or learning can be estimated based on the user's participation history in volunteer activities or workshops. The basic information registration unit also collects data on online events the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in a particular field can be estimated based on the user's participation history in webinars or online seminars. This makes it possible to collect data on events and activities the user has participated in in the past and estimate the user's hobbies and preferences based on the data.

[0034] The AI ​​avatar generation unit can generate a more realistic AI avatar based on the user's facial photo or voice characteristics. The AI ​​avatar generation unit, for example, analyzes the user's facial photo and generates a realistic AI avatar based on the facial features. For example, it creates an avatar that reflects the user's facial contours, eye shape, hairstyle, etc. The AI ​​avatar generation unit also analyzes the user's vocal characteristics and generates a realistic AI avatar based on the user's vocal tone and speaking style. For example, it creates an avatar that reflects the pitch and rhythm of the voice. The AI ​​avatar generation unit also combines the user's facial photo and voice characteristics to generate a more realistic AI avatar. For example, it creates an avatar that reflects the user's facial expression and voice tone. This allows the generation of a more realistic AI avatar based on the user's facial photo and voice characteristics.

[0035] The AI ​​avatar generation unit can analyze a user's past message history and create an AI avatar that reflects the user's communication style. The AI ​​avatar generation unit, for example, analyzes a user's past message history and creates an AI avatar that reflects the user's communication style. For example, it reflects the user's frequently used phrases and expressions in the avatar. The AI ​​avatar generation unit also creates an AI avatar that reflects the user's speaking style and language use based on the user's message history. For example, it reflects polite language and casual speaking in the avatar. The AI ​​avatar generation unit also analyzes the user's message history and creates an AI avatar that learns the user's communication style. For example, it reflects the user's frequently used emojis and stamps in the avatar. In this way, it is possible to analyze a user's past message history and create an AI avatar that reflects the user's communication style.

[0036] The AI ​​avatar generation unit can provide a customizable AI avatar based on a user's pet or favorite character. The AI ​​avatar generation unit creates an AI avatar that resembles the user's pet, for example, based on a photo of the user's pet. For example, it generates an avatar that reflects the characteristics of a dog or cat. The AI ​​avatar generation unit also provides a customizable AI avatar based on a user's favorite character. For example, it creates an avatar that reflects an anime character or a movie character. The AI ​​avatar generation unit also provides a customizable AI avatar that reflects the characteristics of a user's pet or favorite character, after the user selects the pet or favorite character. For example, it generates an avatar that reflects the pet's name and the character's characteristics. This makes it possible to provide a customizable AI avatar based on a user's pet or favorite character.

[0037] The AI ​​avatar generation unit creates AI avatars for different situations based on the user's hobbies and preferences, and can use them according to the situation. The AI ​​avatar generation unit creates AI avatars for different situations based on the user's hobbies and preferences, for example, creating an avatar for watching movies and an avatar for outdoor activities. The AI ​​avatar generation unit also creates multiple AI avatars based on the user's interests and uses them according to the situation. For example, it creates an avatar for work and an avatar for private use. The AI ​​avatar generation unit also creates AI avatars for different situations based on the user's hobbies and preferences, allowing the user to easily switch between them. For example, it creates an avatar for traveling and an avatar for watching sports. This allows multiple AI avatars for different situations to be created based on the user's hobbies and preferences, and can be used according to the situation.

[0038] The automatic sending unit can analyze the user's past history of "likes" or messages and send "likes" or messages at the optimal timing. The automatic sending unit, for example, analyzes the user's past history of "likes" and sends "likes" at the optimal timing. For example, if a user tends to send "likes" during a specific time period, the automatic sending unit sends "likes" according to that time period. The automatic sending unit also analyzes the user's past message history and sends messages at the optimal timing. For example, if a user tends to send messages on a specific day of the week, the automatic sending unit sends messages according to that day of the week. The automatic sending unit also estimates the time when the other party is most likely to respond based on the user's history of "likes" and messages, and sends "likes" or messages at that time. For example, if the other party tends to be online during a specific time period, the automatic sending unit sends messages according to that time period. In this way, the user's past history of "likes" and messages can be analyzed and "likes" or messages can be sent at the optimal timing.

[0039] The automatic sending unit can analyze a user's voice message, generate a text message from the voice, and send it. For example, when a user inputs a message by voice, the automatic sending unit automatically generates and sends a text message using voice recognition technology. For example, if a user inputs "Hello, we have a common hobby, so I'd like to talk," the content is converted into text and sent. The automatic sending unit also analyzes a user's voice message and builds a system that automatically generates a text message. For example, if a user inputs "Like" by voice, the content is converted into text and sent. The automatic sending unit also analyzes a user's voice message in real time and automatically generates and sends a text message. For example, if a user inputs "I'd like to talk," the content is converted into text and sent. In this way, a user's voice message can be analyzed and a text message can be automatically generated and sent from the voice.

[0040] The automatic transmission unit can send "likes" and messages related to specific events and activities based on the user's hobbies and preferences. The automatic transmission unit automatically sends "likes" and messages related to specific events based on the user's hobbies and preferences, for example. For example, to a user who likes watching movies, it sends a message including information about a movie event. The automatic transmission unit also automatically sends "likes" and messages related to specific activities based on the user's interests. For example, to a user who is interested in outdoor activities, it sends a message including information about a hiking event. The automatic transmission unit also builds a system that automatically sends "likes" and messages related to specific events and activities based on the user's hobbies and preferences. For example, to a user who likes traveling, it sends a message including information about a travel event. In this way, it is possible to automatically send "likes" and messages related to specific events and activities based on the user's hobbies and preferences.

[0041] The content check unit can analyze interactions between AI avatars and learn and apply optimal communication patterns. The content check unit, for example, analyzes interactions between AI avatars and learns optimal communication patterns. For example, it applies the patterns of successful interactions to other interactions. The content check unit also analyzes the message history between AI avatars and builds a system that learns optimal communication patterns. For example, it learns patterns that result in many positive responses and applies them to other interactions. The content check unit also analyzes interactions between AI avatars in real time and learns and applies optimal communication patterns. For example, it sends optimal messages based on the other party's response. This makes it possible to analyze interactions between AI avatars and learn and apply optimal communication patterns.

[0042] The content checking unit can visualize interactions between AI avatars, allowing users to intuitively understand. The content checking unit, for example, builds a system that visualizes interactions between AI avatars, allowing users to intuitively understand. For example, it displays message exchanges in charts and graphs. The content checking unit also visualizes interactions between AI avatars, allowing users to easily grasp the content. For example, it displays summaries of messages. The content checking unit also develops a system that visualizes interactions between AI avatars in real time, allowing users to intuitively understand. For example, it displays the flow of messages in a timeline. This makes it possible to visualize interactions between AI avatars, allowing users to intuitively understand.

[0043] The content checking unit translates interactions between AI avatars that speak different languages, thereby promoting international encounters. For example, the content checking unit builds a system that automatically translates interactions between AI avatars that speak different languages, thereby promoting international encounters. For example, it translates interactions between Japanese and English in real time. The content checking unit also automatically translates interactions between AI avatars to facilitate communication between users that speak different languages. For example, it translates interactions between French and Spanish. The content checking unit also develops a system that automatically translates interactions between AI avatars that speak different languages ​​in real time, thereby promoting international encounters. For example, it translates interactions between Chinese and German. This allows for automatic translation of interactions between AI avatars that speak different languages, thereby promoting international encounters.

[0044] The content checking unit can link interactions between AI avatars across different platforms. For example, the content checking unit builds a system that links interactions between AI avatars across different platforms. For example, it links interactions between social networking sites and messaging apps. The content checking unit also links interactions between AI avatars across different platforms, allowing users to use multiple platforms. For example, it links interactions between online games and chat apps. The content checking unit also develops a system that links interactions between AI avatars across different platforms in real time. For example, it links interactions between video calling apps and messaging apps. This allows interactions between AI avatars to be linked across different platforms.

[0045] The content checking unit can generate summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time. For example, the content checking unit can build a system that automatically generates summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time. For example, it can extract and display the main points of messages. The content checking unit can also analyze interactions between AI avatars, summarize the important points, and provide them to the user. For example, it can display highlights of the conversation. The content checking unit can also develop a system that generates summaries of interactions conducted by the AI ​​avatar in real time, allowing the user to easily understand the content. For example, it can notify the user of a message summary. This allows the content checking unit to automatically generate summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time.

[0046] The content checking unit can highlight important messages or exchanges when the user checks. The content checking unit, for example, builds a system that highlights important messages and exchanges when the user checks. For example, it highlights important keywords and phrases. The content checking unit also automatically identifies important messages in exchanges between AI avatars and highlights them when the user checks. For example, it highlights important decisions in a conversation. The content checking unit also develops a system that highlights important exchanges when the user checks, allowing the user to easily understand the content. For example, it displays important messages in different colors. This allows important messages and exchanges to be highlighted when the user checks.

[0047] The content check unit can provide a function to read out loud the content that the user is checking. For example, the content check unit builds a system that provides a function to read out loud the content that the user is checking. For example, an AI avatar reads out a summary of the exchange. The content check unit also provides a function to read out loud important messages and exchanges when the user is checking. For example, highlights of the conversation are notified by voice. The content check unit also develops a system that provides a function to read out loud the content that the user is checking in real time. For example, important messages are read out loud. This makes it possible to provide a function to read out loud the content that the user is checking.

[0048] The content checking unit converts the content that the user is checking into a visual note or a mind map, making it easier to understand visually. The content checking unit, for example, converts the content that the user is checking into a visual note, building a system that makes it easier to understand visually. For example, the main points of a message are displayed using diagrams or icons. The content checking unit also converts the content that the user is checking into a mind map format, making it easier to understand visually. For example, the flow of a conversation is displayed using a mind map. The content checking unit also develops a system that converts the content that the user is checking into a visual note or a mind map, making it easier to understand visually. For example, important messages are visualized and displayed. This allows the content that the user is checking to be converted into a visual note or a mind map, making it easier to understand visually.

[0049] The content checking unit can analyze the user's past dating history and develop an algorithm that recommends the most suitable partner. The content checking unit, for example, analyzes the user's past dating history and develops an algorithm that recommends the most suitable partner. For example, partners are recommended based on patterns of successful dating in the past. The content checking unit also builds a system that recommends the most suitable partner based on the user's dating history. For example, partners who share common hobbies and interests are recommended. The content checking unit also analyzes the user's past dating history in real time and develops an algorithm that recommends the most suitable partner. For example, partners are recommended based on past success stories. This makes it possible to develop an algorithm that analyzes the user's past dating history and recommends the most suitable partner.

[0050] The content checking unit can recommend people related to specific events or activities based on the user's hobbies and preferences. The content checking unit, for example, builds a system that recommends people related to specific events based on the user's hobbies and preferences. For example, to a user who likes watching movies, it recommends people who will participate in a movie event. The content checking unit also recommends people related to specific activities based on the user's interests. For example, to a user who is interested in outdoor activities, it recommends people who will participate in a hiking event. The content checking unit also develops an algorithm that recommends people related to specific events or activities based on the user's hobbies and preferences. For example, to a user who likes traveling, it recommends people who will participate in a travel event. In this way, it is possible to recommend people related to specific events or activities based on the user's hobbies and preferences.

[0051] The content check unit can analyze a user's voice message and infer the other party's hobbies and preferences from the voice to make recommendations. The content check unit, for example, analyzes a user's voice message and builds a system that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I like watching movies," the system recommends other parties based on that information. The content check unit also analyzes a user's voice message in real time and develops an algorithm that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I'm interested in outdoor activities," the system recommends other parties based on that information. The content check unit also analyzes a user's voice message and develops a system that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I like traveling," the system recommends other parties based on that information. This makes it possible to analyze a user's voice message and infer the other party's hobbies and preferences from the voice to make recommendations.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The basic information registration unit collects the user's health data and can estimate the user's hobbies and preferences based on the user's health condition. For example, it can analyze data from the user's fitness tracker to understand the user's exercise habits and health condition. The basic information registration unit can also analyze the user's food records to estimate the user's food preferences and health orientation. For example, it can estimate the user's food preferences, such as vegetarian or gluten-free, based on the user's recorded dietary information. The basic information registration unit can also analyze the user's sleep data to understand the user's sleep patterns and stress levels. This enables the user's hobbies and preferences to be estimated more accurately based on the user's health data.

[0054] The AI ​​avatar generation unit can analyze the user's past travel history and customize the background and clothing of the AI ​​avatar based on the travel destination. For example, based on information about cities and countries the user has visited in the past, the avatar can reflect backgrounds and clothing related to those locations. The AI ​​avatar generation unit can also generate an avatar that incorporates the culture and customs of the user's travel destination. For example, the avatar can reflect traditional clothing and accessories from the country the user has visited. The AI ​​avatar generation unit can also analyze photos of the user's travel destination and generate an avatar that incorporates those scenery into the background. This makes it possible to provide a more personalized AI avatar based on the user's travel history.

[0055] The automatic sending unit can analyze the user's calendar information and send "likes" and messages at optimal times based on the user's schedule. For example, the automatic sending unit can send messages at times when the user has more time, avoiding busy times. The automatic sending unit can also send messages related to specific events or activities based on the user's schedule. For example, the automatic sending unit can send messages containing information related to an event the user plans to attend. The automatic sending unit can also send "likes" and messages based on the user's calendar information at times that match the other party's schedule. This enables communication that is optimized for the user's schedule.

[0056] The AI ​​avatar generation unit can analyze the behavioral data of a user's pet and generate an AI avatar that reflects the pet's characteristics. For example, it can customize the avatar's movements and voice based on the pet's movements and cries. The AI ​​avatar generation unit can also analyze the pet's health data and generate an avatar that matches its health condition. For example, it can generate an active avatar if the pet is healthy, and a calm avatar if the pet is in poor health. The AI ​​avatar generation unit can also analyze a photo of the pet and generate an avatar that reflects its characteristics. This allows for the provision of a more realistic AI avatar based on the user's pet.

[0057] The content checking unit can highlight important messages or exchanges when the user checks them. For example, it can highlight important keywords or phrases. The content checking unit can also automatically identify important messages in exchanges between AI avatars and highlight them when the user checks them. For example, it can highlight important decisions made in a conversation. The content checking unit will also develop a system that highlights important exchanges when the user checks them, making it easy to understand the content. For example, it can display important messages in different colors. This allows important messages and exchanges to be highlighted when the user checks them.

[0058] The content checking unit can analyze the user's past dating history and develop an algorithm that recommends the most suitable partner. For example, it can recommend partners based on patterns of successful dating in the past. The content checking unit can also build a system that recommends the most suitable partner based on the user's dating history. For example, it can recommend partners who share common hobbies and interests. The content checking unit can also analyze the user's past dating history in real time and develop an algorithm that recommends the most suitable partner. For example, it can recommend partners based on past success stories. This makes it possible to develop an algorithm that analyzes the user's past dating history and recommends the most suitable partner.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The basic information registration unit registers the user's basic information and hobbies and interests. For example, the user can enter information such as name, age, gender, hobbies and interests, and activities of interest into the system. Step 2: The AI ​​avatar generation unit generates an AI avatar based on the basic information and hobbies and preferences registered by the basic information registration unit. For example, the generation AI finds a person who matches the user's hobbies and preferences and sends that person a message such as, "Hello, we have a common hobby, so I'd like to talk." Step 3: In the automatic sending unit, the AI ​​avatar generated by the AI ​​avatar generation unit automatically sends a "Like" to the other party. For example, the AI ​​avatar finds a partner who matches the user's hobbies and preferences and sends a "Like" to that partner. Step 4: The content checker checks the content of the interaction conducted by the AI ​​avatar. For example, the user can check the messages sent by the AI ​​avatar and the replies from the other party. This allows the user to understand the content of the interaction conducted by the AI ​​avatar and intervene if necessary.

[0061] (Example 2) The AI ​​avatar system according to an embodiment of the present invention is a system in which an AI avatar automatically sends "likes" and messages to other users based on the basic information and hobbies and preferences registered by the user. As a result, the AI ​​avatar system automatically communicates on behalf of the user, and the user only needs to check the content of the messages. This allows the user to encounter people they would not have met through their own efforts, or people with whom they have a high compatibility.

[0062] The AI ​​avatar system according to the embodiment includes a basic information registration unit, an AI avatar generation unit, an automatic transmission unit, and a content check unit. The basic information registration unit registers a user's basic information and hobbies and preferences. For example, the user can enter information such as their name, age, gender, hobbies and preferences, and activities of interest into the system. The AI ​​avatar generation unit generates an AI avatar based on the basic information and hobbies and preferences registered by the basic information registration unit. For example, the generation AI finds a person who shares the user's hobbies and preferences and sends that person a message such as, "Hello, we have common hobbies, so I'd like to talk." The automatic transmission unit allows the AI ​​avatar generated by the AI ​​avatar generation unit to automatically send a "like" to the person. For example, the AI ​​avatar finds a person who shares the user's hobbies and preferences and sends a "like" to that person. The content check unit checks the content of the exchanges conducted by the AI ​​avatar. For example, the user can check the messages sent by the AI ​​avatar and the replies from the other person. This allows the AI ​​avatar system to automatically exchange messages on behalf of the user, while the user only needs to check the content of the messages. Users can meet people they would not have met through their own efforts, or people with whom they have a high compatibility.

[0063] The basic information registration unit can analyze a user's past behavioral history or social media postings to automatically infer and register the user's hobbies and preferences. The basic information registration unit, for example, analyzes a user's past behavioral history to automatically infer the user's hobbies and preferences. For example, the basic information registration unit infers hobbies such as watching movies or outdoor activities based on the user's frequently visited websites and app usage history. The basic information registration unit also analyzes social media postings to automatically infer the user's hobbies and preferences. For example, the basic information registration unit extracts interests such as travel and cooking from photos and comments posted by the user and registers them in the system. The basic information registration unit also analyzes a user's online shopping history to automatically infer the user's hobbies and preferences. For example, the basic information registration unit infers an interest in fashion or gadgets from products purchased or product pages viewed. In this way, the user's hobbies and preferences can be automatically inferred and registered by analyzing a user's past behavioral history and social media postings.

[0064] The basic information registration unit allows the generation AI to provide real-time feedback on the information registered by the user, thereby extracting detailed information. For example, when a user registers their hobbies and preferences, the basic information registration unit allows the generation AI to ask questions in real time to extract detailed information. For example, if the user enters "I like watching movies," the generation AI will ask, "What genre of movies do you like?" When a user enters basic information, the basic information registration unit also asks questions to request supplemental information and create a detailed profile. For example, if the user enters "I'm interested in outdoor activities," the generation AI will ask, "Specifically, what activities do you like?" When a user registers activities of interest to the basic information registration unit, the generation AI will ask related questions to collect more specific information. For example, if the user enters "I like traveling," the generation AI will ask, "Where was your most recent travel destination?" This allows real-time feedback on the information registered by the user to extract more detailed information.

[0065] The basic information registration unit can use the emotion estimation function to analyze the emotion of the user when entering information and generate questions that elicit positive emotions. For example, when the user enters basic information, the basic information registration unit uses the emotion estimation function to analyze the emotion and automatically generate questions that elicit positive emotions. For example, if the user is entering basic information with a happy look on their face, the basic information registration unit may ask, "What's something fun that happened to you recently?" Furthermore, when the user registers their hobbies and preferences, the basic information registration unit uses the emotion estimation function to analyze the emotion and ask questions that elicit positive emotions. For example, if the user is excited, the basic information registration unit may ask, "What made you start that hobby?" Furthermore, when the user enters an activity that interests them, the basic information registration unit uses the emotion estimation function to analyze the emotion and automatically generate questions that elicit positive emotions. For example, if the user is entering information with a smile on their face, the basic information registration unit may ask, "What was the most enjoyable experience you had in that activity?" In this way, the emotion of the user when entering information can be analyzed and questions that elicit positive emotions can be automatically generated.

[0066] The basic information registration unit can analyze a user's voice input, extract hobbies and preferences from the voice, and register them. For example, when a user registers hobbies and preferences by voice, the basic information registration unit analyzes the content using voice recognition technology and automatically extracts the hobbies and preferences. For example, if the user inputs "I like watching movies" by voice, the basic information registration unit registers that information in the system. Furthermore, when a user inputs basic information by voice, the basic information registration unit extracts detailed information using voice analysis technology and registers it in the system. For example, if the user inputs "I'm interested in outdoor activities" by voice, the basic information registration unit analyzes the content using voice recognition technology and automatically extracts hobbies and preferences. For example, if the user inputs "I like traveling" by voice, the basic information registration unit registers that information in the system. In this way, the user's voice input can be analyzed, and hobbies and preferences can be automatically extracted and registered from the voice.

[0067] The basic information registration unit collects data on events or activities the user has participated in in the past and can estimate the user's hobbies and preferences based on the data. The basic information registration unit, for example, collects data on events the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in music or sports can be estimated based on the user's participation history in music festivals or sporting events. The basic information registration unit also collects data on activities the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in social contribution or learning can be estimated based on the user's participation history in volunteer activities or workshops. The basic information registration unit also collects data on online events the user has participated in in the past and estimates the user's hobbies and preferences based on the data. For example, the user's interest in a particular field can be estimated based on the user's participation history in webinars or online seminars. This makes it possible to collect data on events and activities the user has participated in in the past and estimate the user's hobbies and preferences based on the data.

[0068] The basic information registration unit can use the emotion estimation function to analyze the emotional response to the information registered by the user and provide an interface that elicits a positive response. For example, when the user inputs basic information, the basic information registration unit can use the emotion estimation function to analyze the emotional response and provide an interface that elicits a positive response. For example, if the user is entering basic information with a happy look on their face, a positive message can be displayed. Furthermore, when the user registers hobbies and preferences, the basic information registration unit can use the emotion estimation function to analyze the emotional response and provide an interface that elicits a positive response. For example, if the user is excited, an encouraging message can be displayed. Furthermore, when the user inputs activities in which they are interested, the basic information registration unit can use the emotion estimation function to analyze the emotional response and provide an interface that elicits a positive response. For example, if the user is entering with a smile on their face, a compliment can be displayed. In this way, it is possible to analyze the emotional response to the information registered by the user and provide an interface that elicits a positive response.

[0069] The AI ​​avatar generation unit can generate a more realistic AI avatar based on the user's facial photo or voice characteristics. The AI ​​avatar generation unit, for example, analyzes the user's facial photo and generates a realistic AI avatar based on the facial features. For example, it creates an avatar that reflects the user's facial contours, eye shape, hairstyle, etc. The AI ​​avatar generation unit also analyzes the user's vocal characteristics and generates a realistic AI avatar based on the user's vocal tone and speaking style. For example, it creates an avatar that reflects the pitch and rhythm of the voice. The AI ​​avatar generation unit also combines the user's facial photo and voice characteristics to generate a more realistic AI avatar. For example, it creates an avatar that reflects the user's facial expression and voice tone. This allows the generation of a more realistic AI avatar based on the user's facial photo and voice characteristics.

[0070] The AI ​​avatar generation unit can analyze a user's past message history and create an AI avatar that reflects the user's communication style. The AI ​​avatar generation unit, for example, analyzes a user's past message history and creates an AI avatar that reflects the user's communication style. For example, it reflects the user's frequently used phrases and expressions in the avatar. The AI ​​avatar generation unit also creates an AI avatar that reflects the user's speaking style and language use based on the user's message history. For example, it reflects polite language and casual speaking in the avatar. The AI ​​avatar generation unit also analyzes the user's message history and creates an AI avatar that learns the user's communication style. For example, it reflects the user's frequently used emojis and stamps in the avatar. In this way, it is possible to analyze a user's past message history and create an AI avatar that reflects the user's communication style.

[0071] The AI ​​avatar generation unit uses the emotion estimation function to create an AI avatar that reflects the user's emotional state and can generate and send messages according to the emotions. The AI ​​avatar generation unit, for example, uses the emotion estimation function to create an AI avatar that reflects the user's emotional state. For example, if the user is happy, it generates an avatar with a smiling expression. The AI ​​avatar generation unit also sends a message according to the user's emotional state. For example, if the user is sad, it sends an encouraging message. The AI ​​avatar generation unit also uses the emotion estimation function to create an AI avatar that reflects the user's emotional state in real time. For example, if the user is excited, it generates an avatar with an excited expression. This makes it possible to create an AI avatar that reflects the user's emotional state and send a message according to the emotion.

[0072] The AI ​​avatar generation unit can provide a customizable AI avatar based on a user's pet or favorite character. The AI ​​avatar generation unit creates an AI avatar that resembles the user's pet, for example, based on a photo of the user's pet. For example, it generates an avatar that reflects the characteristics of a dog or cat. The AI ​​avatar generation unit also provides a customizable AI avatar based on a user's favorite character. For example, it creates an avatar that reflects an anime character or a movie character. The AI ​​avatar generation unit also provides a customizable AI avatar that reflects the characteristics of a user's pet or favorite character, after the user selects the pet or favorite character. For example, it generates an avatar that reflects the pet's name and the character's characteristics. This makes it possible to provide a customizable AI avatar based on a user's pet or favorite character.

[0073] The AI ​​avatar generation unit creates AI avatars for different situations based on the user's hobbies and preferences, and can use them according to the situation. The AI ​​avatar generation unit creates AI avatars for different situations based on the user's hobbies and preferences, for example, creating an avatar for watching movies and an avatar for outdoor activities. The AI ​​avatar generation unit also creates multiple AI avatars based on the user's interests and uses them according to the situation. For example, it creates an avatar for work and an avatar for private use. The AI ​​avatar generation unit also creates AI avatars for different situations based on the user's hobbies and preferences, allowing the user to easily switch between them. For example, it creates an avatar for traveling and an avatar for watching sports. This allows multiple AI avatars for different situations to be created based on the user's hobbies and preferences, and can be used according to the situation.

[0074] The AI ​​avatar generation unit can use the emotion estimation function to change the appearance or behavior of the AI ​​avatar according to the user's emotions. For example, the AI ​​avatar generation unit uses the emotion estimation function to change the appearance of the AI ​​avatar according to the user's emotions. For example, if the user is happy, it displays a smiling avatar. The AI ​​avatar generation unit also changes the behavior of the AI ​​avatar according to the user's emotions. For example, if the user is sad, it displays an avatar that sends a comforting message. The AI ​​avatar generation unit also uses the emotion estimation function to change the appearance and behavior of the AI ​​avatar in real time according to the user's emotions. For example, if the user is excited, it displays an avatar with an excited expression and behavior. This makes it possible to change the appearance and behavior of the AI ​​avatar according to the user's emotions.

[0075] The automatic sending unit can analyze the user's past history of "likes" or messages and send "likes" or messages at the optimal timing. The automatic sending unit, for example, analyzes the user's past history of "likes" and sends "likes" at the optimal timing. For example, if a user tends to send "likes" during a specific time period, the automatic sending unit sends "likes" according to that time period. The automatic sending unit also analyzes the user's past message history and sends messages at the optimal timing. For example, if a user tends to send messages on a specific day of the week, the automatic sending unit sends messages according to that day of the week. The automatic sending unit also estimates the time when the other party is most likely to respond based on the user's history of "likes" and messages, and sends "likes" or messages at that time. For example, if the other party tends to be online during a specific time period, the automatic sending unit sends messages according to that time period. In this way, the user's past history of "likes" and messages can be analyzed and "likes" or messages can be sent at the optimal timing.

[0076] The automatic sending unit can analyze the emotional state of the user in real time and generate a message according to the emotion. For example, the automatic sending unit analyzes the emotional state of the user in real time and automatically generates a message according to the emotion. For example, if the user is happy, a positive message is sent. The automatic sending unit also builds a system that analyzes the emotional state of the user and automatically generates a message according to the emotion. For example, if the user is sad, an encouraging message is sent. The automatic sending unit also monitors the emotional state of the user in real time and automatically generates a message according to the emotion. For example, if the user is excited, a message sharing the excitement is sent. In this way, the emotional state of the user can be analyzed in real time and a message according to the emotion can be automatically generated.

[0077] The automatic sending unit can use the emotion estimation function to estimate the emotional state of the other party and generate and send a message accordingly. The automatic sending unit, for example, uses the emotion estimation function to estimate the emotional state of the other party and send a message according to that emotion. For example, if the other party is happy, it sends a message of empathy. The automatic sending unit also builds a system that analyzes the emotional state of the other party in real time and automatically generates a message according to that emotion. For example, if the other party is sad, it sends a message of comfort. The automatic sending unit also uses the emotion estimation function to monitor the emotional state of the other party in real time and send a message according to that emotion. For example, if the other party is excited, it sends a message sharing the excitement. In this way, it is possible to estimate the emotional state of the other party and send a message according to that emotion.

[0078] The automatic sending unit can analyze a user's voice message, generate a text message from the voice, and send it. For example, when a user inputs a message by voice, the automatic sending unit automatically generates and sends a text message using voice recognition technology. For example, if a user inputs "Hello, we have a common hobby, so I'd like to talk," the content is converted into text and sent. The automatic sending unit also analyzes a user's voice message and builds a system that automatically generates a text message. For example, if a user inputs "Like" by voice, the content is converted into text and sent. The automatic sending unit also analyzes a user's voice message in real time and automatically generates and sends a text message. For example, if a user inputs "I'd like to talk," the content is converted into text and sent. In this way, a user's voice message can be analyzed and a text message can be automatically generated and sent from the voice.

[0079] The automatic transmission unit can send "likes" and messages related to specific events and activities based on the user's hobbies and preferences. The automatic transmission unit automatically sends "likes" and messages related to specific events based on the user's hobbies and preferences, for example. For example, to a user who likes watching movies, it sends a message including information about a movie event. The automatic transmission unit also automatically sends "likes" and messages related to specific activities based on the user's interests. For example, to a user who is interested in outdoor activities, it sends a message including information about a hiking event. The automatic transmission unit also builds a system that automatically sends "likes" and messages related to specific events and activities based on the user's hobbies and preferences. For example, to a user who likes traveling, it sends a message including information about a travel event. In this way, it is possible to automatically send "likes" and messages related to specific events and activities based on the user's hobbies and preferences.

[0080] The automatic sending unit can use the emotion estimation function to analyze the emotional reaction of the other party in real time and generate and send an optimal message. The automatic sending unit, for example, uses the emotion estimation function to analyze the emotional reaction of the other party in real time and send an optimal message according to that emotion. For example, if the other party is happy, it sends a message of empathy. The automatic sending unit also builds a system that analyzes the emotional reaction of the other party in real time and automatically generates an optimal message according to that emotion. For example, if the other party is sad, it sends a message of comfort. The automatic sending unit also uses the emotion estimation function to monitor the emotional reaction of the other party in real time and send an optimal message according to that emotion. For example, if the other party is excited, it sends a message that shares the excitement. In this way, the emotional reaction of the other party can be analyzed in real time and an optimal message can be sent.

[0081] The content check unit can analyze interactions between AI avatars and learn and apply optimal communication patterns. The content check unit, for example, analyzes interactions between AI avatars and learns optimal communication patterns. For example, it applies the patterns of successful interactions to other interactions. The content check unit also analyzes the message history between AI avatars and builds a system that learns optimal communication patterns. For example, it learns patterns that result in many positive responses and applies them to other interactions. The content check unit also analyzes interactions between AI avatars in real time and learns and applies optimal communication patterns. For example, it sends optimal messages based on the other party's response. This makes it possible to analyze interactions between AI avatars and learn and apply optimal communication patterns.

[0082] The content check unit can use the emotion estimation function to estimate the emotions of the other party and generate a response accordingly. The content check unit can, for example, use the emotion estimation function to estimate the emotions of the other party and respond accordingly. For example, if the other party is happy, it sends a message of empathy. The content check unit can also use the emotion estimation function to analyze the emotions of the other party in real time during interactions between AI avatars and respond accordingly. For example, if the other party is sad, it sends a message of comfort. The content check unit can also use the emotion estimation function to monitor the emotions of the other party in real time and build a system that responds according to those emotions. For example, if the other party is excited, it sends a message that shares the excitement. This makes it possible to estimate the emotions of the other party using the emotion estimation function and respond accordingly.

[0083] The content checking unit can visualize interactions between AI avatars, allowing users to intuitively understand. The content checking unit, for example, builds a system that visualizes interactions between AI avatars, allowing users to intuitively understand. For example, it displays message exchanges in charts and graphs. The content checking unit also visualizes interactions between AI avatars, allowing users to easily grasp the content. For example, it displays summaries of messages. The content checking unit also develops a system that visualizes interactions between AI avatars in real time, allowing users to intuitively understand. For example, it displays the flow of messages in a timeline. This makes it possible to visualize interactions between AI avatars, allowing users to intuitively understand.

[0084] The content checking unit translates interactions between AI avatars that speak different languages, thereby promoting international encounters. For example, the content checking unit builds a system that automatically translates interactions between AI avatars that speak different languages, thereby promoting international encounters. For example, it translates interactions between Japanese and English in real time. The content checking unit also automatically translates interactions between AI avatars to facilitate communication between users that speak different languages. For example, it translates interactions between French and Spanish. The content checking unit also develops a system that automatically translates interactions between AI avatars that speak different languages ​​in real time, thereby promoting international encounters. For example, it translates interactions between Chinese and German. This allows for automatic translation of interactions between AI avatars that speak different languages, thereby promoting international encounters.

[0085] The content checking unit can link interactions between AI avatars across different platforms. For example, the content checking unit builds a system that links interactions between AI avatars across different platforms. For example, it links interactions between social networking sites and messaging apps. The content checking unit also links interactions between AI avatars across different platforms, allowing users to use multiple platforms. For example, it links interactions between online games and chat apps. The content checking unit also develops a system that links interactions between AI avatars across different platforms in real time. For example, it links interactions between video calling apps and messaging apps. This allows interactions between AI avatars to be linked across different platforms.

[0086] The content check unit uses the emotion estimation function to monitor changes in emotions in interactions between AI avatars in real time and respond optimally. The content check unit, for example, uses the emotion estimation function to monitor changes in emotions in interactions between AI avatars in real time and respond optimally according to those emotions. For example, if the other party is happy, it sends a message of empathy. The content check unit also uses the emotion estimation function to analyze changes in emotions in interactions between AI avatars in real time and builds a system that responds optimally according to those emotions. For example, if the other party is sad, it sends a message of comfort. The content check unit also uses the emotion estimation function to monitor changes in emotions in interactions between AI avatars in real time and develops a system that responds optimally according to those emotions. For example, if the other party is excited, it sends a message that shares that excitement. In this way, the emotion estimation function can be used to monitor changes in emotions in interactions between AI avatars in real time and respond optimally.

[0087] The content checking unit can generate summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time. For example, the content checking unit can build a system that automatically generates summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time. For example, it can extract and display the main points of messages. The content checking unit can also analyze interactions between AI avatars, summarize the important points, and provide them to the user. For example, it can display highlights of the conversation. The content checking unit can also develop a system that generates summaries of interactions conducted by the AI ​​avatar in real time, allowing the user to easily understand the content. For example, it can notify the user of a message summary. This allows the content checking unit to automatically generate summaries of interactions conducted by the AI ​​avatar, allowing the user to understand the content in a short amount of time.

[0088] The content checking unit can highlight important messages or exchanges when the user checks. The content checking unit, for example, builds a system that highlights important messages and exchanges when the user checks. For example, it highlights important keywords and phrases. The content checking unit also automatically identifies important messages in exchanges between AI avatars and highlights them when the user checks. For example, it highlights important decisions in a conversation. The content checking unit also develops a system that highlights important exchanges when the user checks, allowing the user to easily understand the content. For example, it displays important messages in different colors. This allows important messages and exchanges to be highlighted when the user checks.

[0089] The content check unit can use the emotion estimation function to analyze the emotional state of the user when checking and provide an interface that draws out positive emotions. The content check unit, for example, uses the emotion estimation function to analyze the emotional state of the user when checking and provide an interface that draws out positive emotions. For example, if the user is checking happily, a positive message is displayed. The content check unit also analyzes the emotional state of the user when checking in real time, and builds a system that provides an interface that draws out positive emotions. For example, if the user is excited, an encouraging message is displayed. The content check unit also uses the emotion estimation function to monitor the emotional state of the user when checking and develops a system that provides an interface that draws out positive emotions. For example, if the user is checking with a smile, a compliment is displayed. In this way, the emotional state of the user when checking can be analyzed and an interface that draws out positive emotions can be provided.

[0090] The content check unit can provide a function to read out loud the content that the user is checking. For example, the content check unit builds a system that provides a function to read out loud the content that the user is checking. For example, an AI avatar reads out a summary of the exchange. The content check unit also provides a function to read out loud important messages and exchanges when the user is checking. For example, highlights of the conversation are notified by voice. The content check unit also develops a system that provides a function to read out loud the content that the user is checking in real time. For example, important messages are read out loud. This makes it possible to provide a function to read out loud the content that the user is checking.

[0091] The content checking unit converts the content that the user is checking into a visual note or a mind map, making it easier to understand visually. The content checking unit, for example, converts the content that the user is checking into a visual note, building a system that makes it easier to understand visually. For example, the main points of a message are displayed using diagrams or icons. The content checking unit also converts the content that the user is checking into a mind map format, making it easier to understand visually. For example, the flow of a conversation is displayed using a mind map. The content checking unit also develops a system that converts the content that the user is checking into a visual note or a mind map, making it easier to understand visually. For example, important messages are visualized and displayed. This allows the content that the user is checking to be converted into a visual note or a mind map, making it easier to understand visually.

[0092] The content check unit uses the emotion estimation function to analyze the emotional reaction of the user when checking and can provide optimal feedback. The content check unit, for example, uses the emotion estimation function to analyze the emotional reaction of the user when checking in real time and provides optimal feedback based on the results. For example, if the user is checking happily, a positive message is displayed. The content check unit also analyzes the emotional reaction of the user when checking and builds a system that provides optimal feedback based on the results. For example, if the user is excited, an encouraging message is displayed. The content check unit also uses the emotion estimation function to monitor the emotional reaction of the user when checking and develops a system that provides optimal feedback based on the results. For example, if the user is checking with a smile, a compliment is displayed. In this way, the emotional reaction of the user when checking can be analyzed and optimal feedback can be provided.

[0093] The content checking unit can analyze the user's past dating history and develop an algorithm that recommends the most suitable partner. The content checking unit, for example, analyzes the user's past dating history and develops an algorithm that recommends the most suitable partner. For example, partners are recommended based on patterns of successful dating in the past. The content checking unit also builds a system that recommends the most suitable partner based on the user's dating history. For example, partners who share common hobbies and interests are recommended. The content checking unit also analyzes the user's past dating history in real time and develops an algorithm that recommends the most suitable partner. For example, partners are recommended based on past success stories. This makes it possible to develop an algorithm that analyzes the user's past dating history and recommends the most suitable partner.

[0094] The content check unit can analyze the user's emotional state in real time and recommend a partner according to that emotion. The content check unit, for example, builds a system that analyzes the user's emotional state in real time and recommends a partner according to that emotion. For example, if the user is happy, it recommends a positive partner. The content check unit also develops an algorithm that analyzes the user's emotional state and recommends a partner according to that emotion. For example, if the user is sad, it recommends a partner to comfort the user. The content check unit also develops a system that monitors the user's emotional state in real time and recommends a partner according to that emotion. For example, if the user is excited, it recommends a partner who can share that excitement. In this way, it is possible to analyze the user's emotional state in real time and recommend a partner according to that emotion.

[0095] The content check unit can use the emotion estimation function to estimate the emotional state of the other party and suggest a meeting at the optimal timing. The content check unit, for example, uses the emotion estimation function to estimate the emotional state of the other party and build a system that suggests a meeting at the optimal timing according to that emotion. For example, if the other party is happy, it suggests a meeting. The content check unit also analyzes the other party's emotional state in real time and develops an algorithm that suggests a meeting at the optimal timing according to that emotion. For example, if the other party is sad, it suggests a meeting. The content check unit also uses the emotion estimation function to monitor the other party's emotional state in real time and develops a system that suggests a meeting at the optimal timing according to that emotion. For example, if the other party is excited, it suggests a meeting. In this way, the other party's emotional state can be estimated and a system that suggests a meeting at the optimal timing.

[0096] The content checking unit can recommend people related to specific events or activities based on the user's hobbies and preferences. The content checking unit, for example, builds a system that recommends people related to specific events based on the user's hobbies and preferences. For example, to a user who likes watching movies, it recommends people who will participate in a movie event. The content checking unit also recommends people related to specific activities based on the user's interests. For example, to a user who is interested in outdoor activities, it recommends people who will participate in a hiking event. The content checking unit also develops an algorithm that recommends people related to specific events or activities based on the user's hobbies and preferences. For example, to a user who likes traveling, it recommends people who will participate in a travel event. In this way, it is possible to recommend people related to specific events or activities based on the user's hobbies and preferences.

[0097] The content check unit can analyze a user's voice message and infer the other party's hobbies and preferences from the voice to make recommendations. The content check unit, for example, analyzes a user's voice message and builds a system that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I like watching movies," the system recommends other parties based on that information. The content check unit also analyzes a user's voice message in real time and develops an algorithm that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I'm interested in outdoor activities," the system recommends other parties based on that information. The content check unit also analyzes a user's voice message and develops a system that infers the other party's hobbies and preferences from the voice and makes recommendations. For example, if a user says, "I like traveling," the system recommends other parties based on that information. This makes it possible to analyze a user's voice message and infer the other party's hobbies and preferences from the voice to make recommendations.

[0098] The content check unit uses the emotion estimation function to identify the person in whom the user is most interested and promote meeting with that person. The content check unit, for example, uses the emotion estimation function to identify the person in whom the user is most interested and build a system to promote meeting with that person. For example, it preferentially recommends people who the user is excited about. The content check unit also analyzes the user's emotional reactions in real time and develops an algorithm to identify the person in whom the user is most interested. For example, it recommends people about whom the user shows positive emotions. The content check unit also uses the emotion estimation function to identify the person in whom the user is most interested and develops a system to promote meeting with that person. For example, it preferentially recommends people who the user responds with a smile. This makes it possible to identify the person in whom the user is most interested and promote meeting with that person.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The basic information registration unit collects the user's health data and can estimate the user's hobbies and preferences based on the user's health condition. For example, it can analyze data from the user's fitness tracker to understand the user's exercise habits and health condition. The basic information registration unit can also analyze the user's food records to estimate the user's food preferences and health orientation. For example, it can estimate the user's food preferences, such as vegetarian or gluten-free, based on the user's recorded dietary information. The basic information registration unit can also analyze the user's sleep data to understand the user's sleep patterns and stress levels. This enables the user's hobbies and preferences to be estimated more accurately based on the user's health data.

[0101] The AI ​​avatar generation unit can analyze the user's past travel history and customize the background and clothing of the AI ​​avatar based on the travel destination. For example, based on information about cities and countries the user has visited in the past, the avatar can reflect backgrounds and clothing related to those locations. The AI ​​avatar generation unit can also generate an avatar that incorporates the culture and customs of the user's travel destination. For example, the avatar can reflect traditional clothing and accessories from the country the user has visited. The AI ​​avatar generation unit can also analyze photos of the user's travel destination and generate an avatar that incorporates those scenery into the background. This makes it possible to provide a more personalized AI avatar based on the user's travel history.

[0102] The automatic sending unit can analyze the user's calendar information and send "likes" and messages at optimal times based on the user's schedule. For example, the automatic sending unit can send messages at times when the user has more time, avoiding busy times. The automatic sending unit can also send messages related to specific events or activities based on the user's schedule. For example, the automatic sending unit can send messages containing information related to an event the user plans to attend. The automatic sending unit can also send "likes" and messages based on the user's calendar information at times that match the other party's schedule. This enables communication that is optimized for the user's schedule.

[0103] The AI ​​avatar generation unit can analyze the behavioral data of a user's pet and generate an AI avatar that reflects the pet's characteristics. For example, it can customize the avatar's movements and voice based on the pet's movements and cries. The AI ​​avatar generation unit can also analyze the pet's health data and generate an avatar that matches its health condition. For example, it can generate an active avatar if the pet is healthy, and a calm avatar if the pet is in poor health. The AI ​​avatar generation unit can also analyze a photo of the pet and generate an avatar that reflects its characteristics. This allows for the provision of a more realistic AI avatar based on the user's pet.

[0104] The basic information registration unit can use the emotion estimation function to analyze the emotion a user feels when entering data and generate questions that reduce stress. For example, if a user is nervous, it asks a question that will relax the user. The basic information registration unit can also analyze the emotion a user feels when entering data and generate questions that will give the user a sense of security. For example, if a user is feeling anxious, it asks a question that will reassure the user. The basic information registration unit can also analyze the emotion a user feels when entering data and generate questions that will elicit positive emotions. For example, if a user is feeling depressed, it asks an encouraging question. In this way, it is possible to analyze the user's emotion and generate questions that will reduce stress and give the user a sense of security.

[0105] The automatic sending unit can use the emotion estimation function to analyze the user's emotional state in real time and generate a message according to the emotion. For example, if the user is happy, a positive message is sent. The automatic sending unit also builds a system that analyzes the user's emotional state and automatically generates a message according to the emotion. For example, if the user is sad, an encouraging message is sent. The automatic sending unit also monitors the user's emotional state in real time and automatically generates a message according to the emotion. For example, if the user is excited, a message sharing the excitement is sent. This makes it possible to analyze the user's emotional state in real time and automatically generate a message according to the emotion.

[0106] The content check unit uses the emotion estimation function to monitor changes in emotions in interactions between AI avatars in real time and respond optimally. For example, if the other party is happy, it sends a message of empathy. The content check unit also uses the emotion estimation function to analyze changes in emotions in interactions between AI avatars in real time and builds a system that responds optimally according to those emotions. For example, if the other party is sad, it sends a message of comfort. The content check unit also uses the emotion estimation function to monitor changes in emotions in interactions between AI avatars in real time and develops a system that responds optimally according to those emotions. For example, if the other party is excited, it sends a message that shares that excitement. In this way, the emotion estimation function can be used to monitor changes in emotions in interactions between AI avatars in real time and respond optimally.

[0107] The content checking unit can highlight important messages or exchanges when the user checks them. For example, it can highlight important keywords or phrases. The content checking unit can also automatically identify important messages in exchanges between AI avatars and highlight them when the user checks them. For example, it can highlight important decisions made in a conversation. The content checking unit will also develop a system that highlights important exchanges when the user checks them, making it easy to understand the content. For example, it can display important messages in different colors. This allows important messages and exchanges to be highlighted when the user checks them.

[0108] The content checking unit can analyze the user's past dating history and develop an algorithm that recommends the most suitable partner. For example, it can recommend partners based on patterns of successful dating in the past. The content checking unit can also build a system that recommends the most suitable partner based on the user's dating history. For example, it can recommend partners who share common hobbies and interests. The content checking unit can also analyze the user's past dating history in real time and develop an algorithm that recommends the most suitable partner. For example, it can recommend partners based on past success stories. This makes it possible to develop an algorithm that analyzes the user's past dating history and recommends the most suitable partner.

[0109] The content check unit uses the emotion estimation function to identify the person in whom the user is most interested and promotes encounters with that person. For example, it prioritizes recommending people who the user is excited about. The content check unit also analyzes the user's emotional reactions in real time and develops an algorithm to identify the person in whom the user is most interested. For example, it recommends people about whom the user shows positive emotions. The content check unit also uses the emotion estimation function to identify the person in whom the user is most interested and develops a system to promote encounters with that person. For example, it prioritizes recommending people who the user responds with a smile. This makes it possible to identify the person in whom the user is most interested and promote encounters with that person.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The basic information registration unit registers the user's basic information and hobbies and interests. For example, the user can enter information such as name, age, gender, hobbies and interests, and activities of interest into the system. Step 2: The AI ​​avatar generation unit generates an AI avatar based on the basic information and hobbies and preferences registered by the basic information registration unit. For example, the generation AI finds a person who matches the user's hobbies and preferences and sends that person a message such as, "Hello, we have a common hobby, so I'd like to talk." Step 3: In the automatic sending unit, the AI ​​avatar generated by the AI ​​avatar generation unit automatically sends a "Like" to the other party. For example, the AI ​​avatar finds a partner who matches the user's hobbies and preferences and sends a "Like" to that partner. Step 4: The content checker checks the content of the interaction conducted by the AI ​​avatar. For example, the user can check the messages sent by the AI ​​avatar and the replies from the other party. This allows the user to understand the content of the interaction conducted by the AI ​​avatar and intervene if necessary.

[0112] 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.

[0113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] 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.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] 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.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0141] 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.

[0142] 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.

[0143] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0144] 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.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0157] 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.

[0158] 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.

[0159] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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. [Explanation of symbols]

[0179] 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 basic information registration unit for registering basic information and hobbies and preferences; an AI avatar generation unit that generates an AI avatar based on the basic information and the hobbies and preferences registered by the basic information registration unit; an automatic sending unit that causes the AI ​​avatar generated by the AI ​​avatar generation unit to automatically send a "Like" to a partner; A content checking unit is provided to check the content of the exchanges made by the AI ​​avatar. A system characterized by:

2. The basic information registration unit Analyzing the user's past behavioral history or social media posts, the user's hobbies and preferences are automatically estimated and registered.

2. The system of claim 1.

3. The basic information registration unit The AI ​​generates information that users register and provides real-time feedback to extract detailed information.

2. The system of claim 1.

4. The basic information registration unit Analyzes the emotions of users as they type and generates questions that elicit positive emotions 2. The system of claim 1.

5. The basic information registration unit Analyzing the user's voice input, extracting and registering the user's interests and preferences from the voice 2. The system of claim 1.

6. The basic information registration unit Collecting data on events or activities that the user has participated in in the past and estimating the user's interests and preferences based on the data 2. The system of claim 1.

Images