System

Abstract

An object of the system according to the embodiment is to enable a user to create a AI character for himself / herself and enjoy a realistic conversation experience.SOLUTION: A system includes a generation unit, a conversation providing unit, an access unit, and a growth unit. The generation unit generates a AI character on the basis of an instruction from a user. The conversation providing unit provides a realistic conversation experience using the AI character generated by the generation unit. The access unit enables the conversation experience provided by the conversation providing unit to be accessed through the message application. The growing unit grows the AI character in accordance with the user's conversation style or preference through the conversation provided by the conversation providing unit.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 has made it difficult for users to create their own AI characters and enjoy a realistic conversation experience.

[0005] The system according to the embodiment aims to enable users to create their own AI characters and enjoy a realistic conversation experience. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation unit, a conversation providing unit, an access unit, and a growth unit. The generation unit generates an AI character based on a user's instructions. The conversation providing unit provides a realistic conversation experience using the AI ​​character generated by the generation unit. The access unit makes the conversation experience provided by the conversation providing unit accessible through a messaging app. The growth unit grows the AI ​​character to match the user's conversation style and preferences through the conversation provided by the conversation providing unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to create their own AI characters and enjoy a realistic conversation experience. [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 ​​character service according to an embodiment of the present invention is a system that allows users to create their own AI characters and enjoy a realistic conversation experience while developing them. As a result, the AI ​​character service can provide users with a realistic conversation experience and an AI character that grows to suit the user's conversation style and preferences.

[0029] An AI character service according to an embodiment includes a generation unit, a conversation providing unit, an access unit, and a growth unit. The generation unit generates an AI character based on a user's instructions. For example, when a user inputs a prompt such as "I want a cheerful and energetic character," the generation unit generates a character based on the instruction. The generation unit also sets the character's appearance, personality, speaking style, and other aspects based on the user's instructions. The conversation providing unit provides a realistic conversation experience using the AI ​​character generated by the generation unit. For example, when a user asks, "How was your day?", the conversation providing unit responds with, "I had a great time today. I read a new book." The conversation providing unit also converts the generated AI's response into speech and conveys it to the user. The access unit makes the conversation experience provided by the conversation providing unit accessible through a messaging app. For example, when a user sends a message such as "Good morning" through a messaging app such as LINE, WhatsApp, or Facebook Messenger, the access unit responds with, "Good morning! What are your plans for today?" The growth unit grows the AI ​​character to match the user's conversation style and preferences through the conversation provided by the conversation providing unit. For example, the growth unit learns the user's frequently used words and topics and generates responses based on them. As a result, the AI ​​character service according to the embodiment allows users to create and grow their own personalized AI character and enjoy a realistic conversation experience.

[0030] The generation unit can analyze a user's past SNS posts and message history to automatically generate an AI character that is optimal for each individual user. For example, the generation unit analyzes a user's past SNS posts and extracts the user's interests and personality from the content of the posts. For example, for a user who likes to travel, it generates a character that loves to travel. The generation unit also analyzes message history to learn words and phrases that the user frequently uses. For example, it reflects the user's frequently used jokes and expressions in the character. The generation unit also analyzes the user's emotional tendencies from SNS posts and message history and sets the character's personality based on that. For example, it generates a character with a cheerful personality for a user who posts a lot of positive things. This makes it possible to automatically generate an optimal character for each individual user by analyzing a user's past SNS posts and message history.

[0031] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the season or event. For example, the generation unit automatically changes the character's clothing and background according to the season. For example, a swimsuit and beach background are set in summer, and a coat and snowy scenery are set in winter. The generation unit also changes the character's appearance and personality to match a specific event. For example, it generates a character dressed in costume for Halloween, and a Santa Claus-style character for Christmas. The generation unit also sets a special message and appearance for the user's birthday or anniversary. For example, on a birthday, a character wearing a party hat is displayed along with a birthday message. In this way, the personality and appearance of the character selected by the user can be automatically changed according to the season or event.

[0032] The generation unit can generate the appearance and personality of an AI character based on photos and illustrations uploaded by a user. For example, the generation unit analyzes photos uploaded by a user and generates the character's appearance based on the characteristics of the photos. For example, it creates a pet-like character based on a photo of the user's pet. The generation unit also sets the character's appearance and personality based on an illustration drawn by the user. For example, it generates a hero-like character based on a superhero illustration drawn by the user. The generation unit also analyzes the color and shape of the uploaded photos and illustrations and sets the character's clothing and accessories based on that. For example, it customizes the character's clothing based on the user's favorite colors. In this way, the character's appearance and personality can be generated based on the photos and illustrations uploaded by the user.

[0033] The generation unit adds a function that allows multiple users to jointly develop a single AI character, thereby promoting use in group chats. The generation unit adds, for example, a function for jointly developing a character within a group chat. For example, each member can give different instructions to the character, and the character will grow accordingly. The generation unit also provides an interface that allows multiple users to jointly customize the character's appearance and personality. For example, a voting function can be used to determine the character's clothing and personality. The generation unit also enables the character to converse with all members within the group chat. For example, the character generates responses that correspond to the topic of the entire group. This allows multiple users to jointly develop a single character, promoting use in group chats.

[0034] The conversation providing unit can understand the context of the conversation and generate a consistent response by referring to the content of past conversations. For example, the conversation providing unit adds a function to store the content of past conversations in a database and refer to it in the current conversation. For example, a consistent response is generated based on what the user has previously said. The conversation providing unit also analyzes the context of the conversation and builds a system that automatically refers to related content of past conversations. For example, the conversation providing unit may bring up a topic of a hobby that the user previously talked about. The conversation providing unit also develops an algorithm that generates a response based on the content of past conversations to maintain the consistency of the conversation. For example, the conversation providing unit may ask about the progress of a plan that the user previously discussed. This makes it possible to understand the context of the conversation and generate a consistent response by referring to the content of past conversations.

[0035] The conversation providing unit can analyze the user's speaking rate and tone and generate a voice response that matches the rate. For example, the conversation providing unit analyzes the user's speaking rate in real time and generates a voice response that matches the rate. For example, if the user speaks slowly, the character also responds slowly. The conversation providing unit also analyzes the user's tone and generates an emotional voice response that matches the rate. For example, if the user speaks excitedly, the character also responds in an excited tone. The conversation providing unit also develops an algorithm that adjusts the character's voice response based on the analysis results of the speaking rate and tone. For example, if the user speaks in a calm tone, the character also responds in a calm tone. This makes it possible to analyze the user's speaking rate and tone and generate a voice response that matches the rate and tone.

[0036] The conversation providing unit can automatically suggest topics that the user is likely to be interested in during a conversation. For example, the conversation providing unit analyzes the content of the user's past conversations and automatically suggests topics that the user is likely to be interested in. For example, it suggests topics related to hobbies that the user has previously talked about. The conversation providing unit also analyzes the flow of a conversation and builds a system that suggests related topics in real time. For example, if the user is talking about traveling, it suggests information about travel destinations. The conversation providing unit also develops an algorithm that suggests new topics during a conversation based on the user's interests. For example, it suggests topics related to movies that the user likes. This makes it possible to automatically suggest topics that the user is likely to be interested in during a conversation.

[0037] The conversation providing unit can automatically summarize the content of a conversation, allowing the user to review it later. For example, the conversation providing unit builds a system that analyzes the content of a conversation in real time and automatically summarizes important points. For example, it displays the main points of the conversation in bullet points. The conversation providing unit also adds a function to automatically generate a summary of the conversation and save it so that the user can review it later. For example, it adds the summary to the conversation history. The conversation providing unit also summarizes the content of the conversation and provides an interface that the user can easily access. For example, it saves the summary in a searchable format. This allows the content of the conversation to be automatically summarized, allowing the user to review it later.

[0038] The Access Department utilizes the notification function of a messaging app to send reminders to users to converse with an AI character at a specific time. For example, the Access Department uses the notification function of a messaging app to send conversation reminders with a character at a time set by the user. For example, sending a "good morning" message every morning at 8:00. The Access Department also builds a system that automatically sets conversation reminders with a character based on the user's schedule. For example, it sends reminders in conjunction with the user's calendar. The Access Department also adds a function to send conversation reminders with a character to coincide with specific events or anniversaries. For example, it sends a special message on the user's birthday. This allows the user to send a reminder to converse with a character at a specific time.

[0039] The access unit can synchronize conversations within a messaging app to other devices. For example, the access unit can synchronize conversations within a messaging app to a smart speaker, allowing the user to converse with a character by voice. For example, the user can continue the conversation on the smart speaker when at home. The access unit can also synchronize conversations within a messaging app to a smartwatch, allowing the user to easily communicate with a character. For example, the user can continue the conversation on the smartwatch when on the go. The access unit can also synchronize conversations within a messaging app to multiple devices, allowing the user to seamlessly continue the conversation on any device. For example, the same conversation can be continued on a smartphone, tablet, and PC. This allows conversations within a messaging app to be synchronized to other devices.

[0040] The Access Department can automatically categorize conversations within a messaging app based on themes selected by the user. For example, the Access Department analyzes conversations within a messaging app and builds a system that automatically categorizes them based on themes selected by the user. For example, conversations can be categorized by theme, such as work, hobbies, and family. The Access Department also adds a function that categorizes the content of conversations by theme and allows users to easily access them later. For example, it makes conversations related to a specific theme searchable. The Access Department also develops an algorithm that automatically tags and categorizes the content of conversations based on themes selected by the user. For example, it categorizes conversations about travel with a "travel" tag. This allows conversations within a messaging app to be automatically categorized based on themes selected by the user.

[0041] The growth unit can analyze the user's conversation style in detail and learn specific phrases and expressions. For example, the growth unit can analyze the user's conversation style in detail and build a system that learns frequently used phrases and expressions. For example, the growth unit can reflect the user's frequently used jokes and catchphrases in the character. The growth unit can also add a function that allows the character to imitate the user's expressions based on the analysis results of the conversation style. For example, the character can use specific expressions that the user uses. The growth unit can also learn the user's conversation style and develop an algorithm that customizes the character's responses based on that. For example, if the user prefers casual language, the character will also respond using casual language. This makes it possible to analyze the user's conversation style in detail and learn specific phrases and expressions.

[0042] The growth unit can automatically update the hobbies and interests of an AI character according to the user's preferences. For example, the growth unit analyzes the content of a user's conversations and builds a system that learns the user's hobbies and interests. For example, the growth unit reflects information related to hobbies that the user often talks about in the character. The growth unit also develops an algorithm that automatically updates the character's hobbies and interests according to the user's preferences. For example, if a user starts a new hobby, the character will also become interested in that hobby. The growth unit also builds a system that dynamically adjusts the character's hobbies and interests according to changes in the user's preferences. For example, if a user starts to become interested in a new topic, the character will also become interested in that topic. This allows the character's hobbies and interests to be automatically updated according to the user's preferences.

[0043] The growth unit can customize the growth of an AI character based on feedback provided by a user to the AI ​​character. For example, the growth unit collects feedback provided by a user to a character and builds a system that customizes the character's growth based on that data. For example, if a user wants to change the character's personality, that feedback is reflected. The growth unit also develops an algorithm that dynamically adjusts the character's growth direction based on the feedback data. For example, if a user wants to improve the character's responses, the response is adjusted based on that feedback. The growth unit also analyzes user feedback in real time and builds a system that customizes the character's growth based on the results. For example, if a user wants to change the character's appearance, that feedback is immediately reflected. This allows the character's growth to be customized based on the feedback provided by the user to the character.

[0044] The growth unit visually displays the growth process of an AI character, allowing the user to check the progress of growth. The growth unit, for example, provides an interface that visually displays the character's growth process. For example, it displays the character's growth stages in a graph or chart. The growth unit also builds a system that allows the user to check the character's growth progress in real time. For example, it displays the character's growth points and achieved goals. The growth unit also visually displays the character's growth process and adds a function that allows the user to track the growth progress. For example, it displays the character's growth history in a timeline format. This visually displays the character's growth process, allowing the user to check the growth progress.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] The generation unit can set the hobbies and interests of the AI ​​character based on the music and movie genres selected by the user. For example, if the user likes rock music, the character can be set to be knowledgeable about rock music. The generation unit can also analyze the genres of movies watched by the user and set the character's movie preferences based on that. For example, if the user watches a lot of science fiction movies, the character can be set to be interested in science fiction movies. Furthermore, the generation unit can customize the content of the character's conversation based on the music and movie genres selected by the user. For example, if the user likes jazz music, the character can talk about jazz. This allows the character's hobbies and interests to be set based on the user's music and movie preferences.

[0047] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user in accordance with the user's life events. For example, if the user gets married, the character can send a message of congratulations. Also, if the user starts a new job, the generation unit can have the character send a message of encouragement. Furthermore, if the user moves, the generation unit can have the character provide advice about the new environment. In this way, the personality and appearance of the character can be automatically changed in accordance with the user's life events.

[0048] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the user's health condition. For example, if the user starts exercising, the character can provide exercise advice. Also, if the user inputs the results of a health check, the generation unit can have the character provide health information. Furthermore, if the user is feeling stressed, the generation unit can have the character make suggestions to help the user relax. This makes it possible to automatically change the personality and appearance of the character according to the user's health condition.

[0049] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the user's hobbies and interests. For example, if the user starts a new hobby, the character can provide information about that hobby. Also, if the user has a specific interest, the generation unit can have the character provide topics related to that interest. Furthermore, if the user participates in an event related to a hobby or interest, the generation unit can have the character provide information about that event. This makes it possible to automatically change the personality and appearance of the character according to the user's hobbies and interests.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The generator generates an AI character based on the user's instructions. For example, if the user inputs a prompt such as "I want a bright and energetic character," the generator generates a character based on that instruction. The generator also sets the character's appearance, personality, speaking style, etc. based on the user's instructions. Step 2: The conversation provider uses the AI ​​character generated by the generator to provide a realistic conversation experience. For example, if a user asks, "How was your day?", the character responds with, "I had a great time today. I read a new book." The conversation provider then converts the response into speech and conveys it to the user. Step 3: The access unit makes the conversation experience provided by the conversation providing unit accessible through a messaging app. For example, when a user sends a message such as "Good morning" through a messaging app such as LINE, WhatsApp, or Facebook Messenger, the access unit responds with a message such as "Good morning! What are your plans for today?" Step 4: The development unit develops the AI ​​character to match the user's conversation style and preferences through conversations provided by the conversation provider. For example, it learns the user's frequently used words and topics and generates responses based on them.

[0052] (Example 2) The AI ​​character service according to an embodiment of the present invention is a system that allows users to create their own AI characters and enjoy a realistic conversation experience while developing them. As a result, the AI ​​character service can provide users with a realistic conversation experience and an AI character that grows to suit the user's conversation style and preferences.

[0053] An AI character service according to an embodiment includes a generation unit, a conversation providing unit, an access unit, and a growth unit. The generation unit generates an AI character based on a user's instructions. For example, when a user inputs a prompt such as "I want a cheerful and energetic character," the generation unit generates a character based on the instruction. The generation unit also sets the character's appearance, personality, speaking style, and other aspects based on the user's instructions. The conversation providing unit provides a realistic conversation experience using the AI ​​character generated by the generation unit. For example, when a user asks, "How was your day?", the conversation providing unit responds with, "I had a great time today. I read a new book." The conversation providing unit also converts the generated AI's response into speech and conveys it to the user. The access unit makes the conversation experience provided by the conversation providing unit accessible through a messaging app. For example, when a user sends a message such as "Good morning" through a messaging app such as LINE, WhatsApp, or Facebook Messenger, the access unit responds with, "Good morning! What are your plans for today?" The growth unit grows the AI ​​character to match the user's conversation style and preferences through the conversation provided by the conversation providing unit. For example, the growth unit learns the user's frequently used words and topics and generates responses based on them. As a result, the AI ​​character service according to the embodiment allows users to create and grow their own personalized AI character and enjoy a realistic conversation experience.

[0054] The generation unit can analyze a user's past SNS posts and message history to automatically generate an AI character that is optimal for each individual user. For example, the generation unit analyzes a user's past SNS posts and extracts the user's interests and personality from the content of the posts. For example, for a user who likes to travel, it generates a character that loves to travel. The generation unit also analyzes message history to learn words and phrases that the user frequently uses. For example, it reflects the user's frequently used jokes and expressions in the character. The generation unit also analyzes the user's emotional tendencies from SNS posts and message history and sets the character's personality based on that. For example, it generates a character with a cheerful personality for a user who posts a lot of positive things. This makes it possible to automatically generate an optimal character for each individual user by analyzing a user's past SNS posts and message history.

[0055] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the season or event. For example, the generation unit automatically changes the character's clothing and background according to the season. For example, a swimsuit and beach background are set in summer, and a coat and snowy scenery are set in winter. The generation unit also changes the character's appearance and personality to match a specific event. For example, it generates a character dressed in costume for Halloween, and a Santa Claus-style character for Christmas. The generation unit also sets a special message and appearance for the user's birthday or anniversary. For example, on a birthday, a character wearing a party hat is displayed along with a birthday message. In this way, the personality and appearance of the character selected by the user can be automatically changed according to the season or event.

[0056] The generation unit can use the emotion estimation function to generate responses and actions of the AI ​​character according to the user's current emotional state. For example, the generation unit estimates emotions from the user's input content and generates a response accordingly. For example, if the user inputs sad content, the character sends an encouraging message. The generation unit also changes the character's facial expression and tone according to the user's emotional state. For example, if the user is happy, the character also responds with a smile. The generation unit also makes the character act in accordance with the user's emotions based on the emotion estimation data. For example, if the user is feeling stressed, the generation unit makes suggestions to help them relax. This makes it possible to generate responses and actions of the character according to the user's current emotional state.

[0057] The generation unit can generate the appearance and personality of an AI character based on photos and illustrations uploaded by a user. For example, the generation unit analyzes photos uploaded by a user and generates the character's appearance based on the characteristics of the photos. For example, it creates a pet-like character based on a photo of the user's pet. The generation unit also sets the character's appearance and personality based on an illustration drawn by the user. For example, it generates a hero-like character based on a superhero illustration drawn by the user. The generation unit also analyzes the color and shape of the uploaded photos and illustrations and sets the character's clothing and accessories based on that. For example, it customizes the character's clothing based on the user's favorite colors. In this way, the character's appearance and personality can be generated based on the photos and illustrations uploaded by the user.

[0058] The generation unit adds a function that allows multiple users to jointly develop a single AI character, thereby promoting use in group chats. The generation unit adds, for example, a function for jointly developing a character within a group chat. For example, each member can give different instructions to the character, and the character will grow accordingly. The generation unit also provides an interface that allows multiple users to jointly customize the character's appearance and personality. For example, a voting function can be used to determine the character's clothing and personality. The generation unit also enables the character to converse with all members within the group chat. For example, the character generates responses that correspond to the topic of the entire group. This allows multiple users to jointly develop a single character, promoting use in group chats.

[0059] The conversation providing unit can understand the context of the conversation and generate a consistent response by referring to the content of past conversations. For example, the conversation providing unit adds a function to store the content of past conversations in a database and refer to it in the current conversation. For example, a consistent response is generated based on what the user has previously said. The conversation providing unit also analyzes the context of the conversation and builds a system that automatically refers to related content of past conversations. For example, the conversation providing unit may bring up a topic of a hobby that the user previously talked about. The conversation providing unit also develops an algorithm that generates a response based on the content of past conversations to maintain the consistency of the conversation. For example, the conversation providing unit may ask about the progress of a plan that the user previously discussed. This makes it possible to understand the context of the conversation and generate a consistent response by referring to the content of past conversations.

[0060] The conversation providing unit can analyze the user's speaking rate and tone and generate a voice response that matches the rate. For example, the conversation providing unit analyzes the user's speaking rate in real time and generates a voice response that matches the rate. For example, if the user speaks slowly, the character also responds slowly. The conversation providing unit also analyzes the user's tone and generates an emotional voice response that matches the rate. For example, if the user speaks excitedly, the character also responds in an excited tone. The conversation providing unit also develops an algorithm that adjusts the character's voice response based on the analysis results of the speaking rate and tone. For example, if the user speaks in a calm tone, the character also responds in a calm tone. This makes it possible to analyze the user's speaking rate and tone and generate a voice response that matches the rate and tone.

[0061] The conversation providing unit can use the emotion estimation function to generate responses using tones and expressions that correspond to the user's emotions. The conversation providing unit, for example, analyzes the user's emotions in real time and generates responses using tones and expressions that correspond to those emotions. For example, if the user is sad, the character responds in a gentle tone. The conversation providing unit also develops an algorithm that generates responses using expressions that match the user's emotions based on the emotion estimation data. For example, if the user is angry, the character responds calmly. The conversation providing unit also builds a system that dynamically adjusts the character's tone and expression according to the user's emotional state. For example, if the user is happy, the character responds in a bright tone. This makes it possible to generate responses using tones and expressions that correspond to the user's emotions.

[0062] The conversation providing unit can automatically suggest topics that the user is likely to be interested in during a conversation. For example, the conversation providing unit analyzes the content of the user's past conversations and automatically suggests topics that the user is likely to be interested in. For example, it suggests topics related to hobbies that the user has previously talked about. The conversation providing unit also analyzes the flow of a conversation and builds a system that suggests related topics in real time. For example, if the user is talking about traveling, it suggests information about travel destinations. The conversation providing unit also develops an algorithm that suggests new topics during a conversation based on the user's interests. For example, it suggests topics related to movies that the user likes. This makes it possible to automatically suggest topics that the user is likely to be interested in during a conversation.

[0063] The conversation providing unit can automatically summarize the content of a conversation, allowing the user to review it later. For example, the conversation providing unit builds a system that analyzes the content of a conversation in real time and automatically summarizes important points. For example, it displays the main points of the conversation in bullet points. The conversation providing unit also adds a function to automatically generate a summary of the conversation and save it so that the user can review it later. For example, it adds the summary to the conversation history. The conversation providing unit also summarizes the content of the conversation and provides an interface that the user can easily access. For example, it saves the summary in a searchable format. This allows the content of the conversation to be automatically summarized, allowing the user to review it later.

[0064] The conversation providing unit uses the emotion estimation function to record the emotions felt by the user during a conversation and enable them to review them later. The conversation providing unit, for example, builds a system that analyzes the user's emotions in real time during a conversation and records the data. For example, it saves an emotion score at each point in the conversation. The conversation providing unit also provides an interface that allows the user to later review the emotions felt during a conversation based on the emotion estimation data. For example, it displays emotional fluctuations in a graph. The conversation providing unit also adds a function that records emotion data during a conversation and allows the user to later review the conversation based on that data. For example, it highlights emotional peak points. This allows the user to record the emotions felt during a conversation and review them later.

[0065] The Access Department utilizes the notification function of a messaging app to send reminders to users to converse with an AI character at a specific time. For example, the Access Department uses the notification function of a messaging app to send conversation reminders with a character at a time set by the user. For example, sending a "good morning" message every morning at 8:00. The Access Department also builds a system that automatically sets conversation reminders with a character based on the user's schedule. For example, it sends reminders in conjunction with the user's calendar. The Access Department also adds a function to send conversation reminders with a character to coincide with specific events or anniversaries. For example, it sends a special message on the user's birthday. This allows the user to send a reminder to converse with a character at a specific time.

[0066] The access unit can use the emotion estimation function to analyze the emotions of users when they send messages in real time and generate responses accordingly. For example, the access unit builds a system that analyzes the emotions of users when they send messages in real time and generates responses according to those emotions. For example, if the user is angry, a character will respond calmly. The access unit also develops an algorithm that generates responses that match the user's emotions based on the emotion estimation data. For example, if the user is sad, a character will send an encouraging message. The access unit also builds a system that dynamically adjusts the character's tone and expression according to the user's emotional state. For example, if the user is happy, a character will respond in a bright tone. This makes it possible to analyze the emotions of users when they send messages in real time and generate responses accordingly.

[0067] The access unit can synchronize conversations within a messaging app to other devices. For example, the access unit can synchronize conversations within a messaging app to a smart speaker, allowing the user to converse with a character by voice. For example, the user can continue the conversation on the smart speaker when at home. The access unit can also synchronize conversations within a messaging app to a smartwatch, allowing the user to easily communicate with a character. For example, the user can continue the conversation on the smartwatch when on the go. The access unit can also synchronize conversations within a messaging app to multiple devices, allowing the user to seamlessly continue the conversation on any device. For example, the same conversation can be continued on a smartphone, tablet, and PC. This allows conversations within a messaging app to be synchronized to other devices.

[0068] The Access Department can automatically categorize conversations within a messaging app based on themes selected by the user. For example, the Access Department analyzes conversations within a messaging app and builds a system that automatically categorizes them based on themes selected by the user. For example, conversations can be categorized by theme, such as work, hobbies, and family. The Access Department also adds a function that categorizes the content of conversations by theme and allows users to easily access them later. For example, it makes conversations related to a specific theme searchable. The Access Department also develops an algorithm that automatically tags and categorizes the content of conversations based on themes selected by the user. For example, it categorizes conversations about travel with a "travel" tag. This allows conversations within a messaging app to be automatically categorized based on themes selected by the user.

[0069] Access uses its emotion estimation function to analyze the emotions felt by users during conversations in messaging apps and adjust the responses of AI characters based on the results. For example, Access will build a system that analyzes users' emotions in real time during conversations in messaging apps and adjusts character responses based on that data. For example, if a user is feeling stressed, the character will make suggestions to help them relax. Access will also develop an algorithm that generates responses tailored to the user's emotions based on the emotion estimation data. For example, if a user is happy, the character will send a congratulatory message. Access will also build a system that dynamically adjusts the character's tone and expression according to the user's emotional state. For example, if a user is sad, the character will respond in a gentle tone. This allows Access to analyze the emotions felt by users during conversations in messaging apps and adjust character responses based on the results.

[0070] The growth unit can analyze the user's conversation style in detail and learn specific phrases and expressions. For example, the growth unit can analyze the user's conversation style in detail and build a system that learns frequently used phrases and expressions. For example, the growth unit can reflect the user's frequently used jokes and catchphrases in the character. The growth unit can also add a function that allows the character to imitate the user's expressions based on the analysis results of the conversation style. For example, the character can use specific expressions that the user uses. The growth unit can also learn the user's conversation style and develop an algorithm that customizes the character's responses based on that. For example, if the user prefers casual language, the character will also respond using casual language. This makes it possible to analyze the user's conversation style in detail and learn specific phrases and expressions.

[0071] The growth unit can automatically update the hobbies and interests of an AI character according to the user's preferences. For example, the growth unit analyzes the content of a user's conversations and builds a system that learns the user's hobbies and interests. For example, the growth unit reflects information related to hobbies that the user often talks about in the character. The growth unit also develops an algorithm that automatically updates the character's hobbies and interests according to the user's preferences. For example, if a user starts a new hobby, the character will also become interested in that hobby. The growth unit also builds a system that dynamically adjusts the character's hobbies and interests according to changes in the user's preferences. For example, if a user starts to become interested in a new topic, the character will also become interested in that topic. This allows the character's hobbies and interests to be automatically updated according to the user's preferences.

[0072] The growth unit can customize the growth of an AI character based on feedback provided by a user to the AI ​​character. For example, the growth unit collects feedback provided by a user to a character and builds a system that customizes the character's growth based on that data. For example, if a user wants to change the character's personality, that feedback is reflected. The growth unit also develops an algorithm that dynamically adjusts the character's growth direction based on the feedback data. For example, if a user wants to improve the character's responses, the response is adjusted based on that feedback. The growth unit also analyzes user feedback in real time and builds a system that customizes the character's growth based on the results. For example, if a user wants to change the character's appearance, that feedback is immediately reflected. This allows the character's growth to be customized based on the feedback provided by the user to the character.

[0073] The growth unit visually displays the growth process of an AI character, allowing the user to check the progress of growth. The growth unit, for example, provides an interface that visually displays the character's growth process. For example, it displays the character's growth stages in a graph or chart. The growth unit also builds a system that allows the user to check the character's growth progress in real time. For example, it displays the character's growth points and achieved goals. The growth unit also visually displays the character's growth process and adds a function that allows the user to track the growth progress. For example, it displays the character's growth history in a timeline format. This visually displays the character's growth process, allowing the user to check the growth progress.

[0074] The growth unit uses the emotion estimation function to analyze the user's emotions toward the growth of an AI character and can adjust the growth direction based on the results. For example, the growth unit analyzes the user's emotions toward the character's growth in real time and builds a system that adjusts the character's growth direction based on that data. For example, if the user is satisfied with the character's growth, that direction is maintained. The growth unit also develops an algorithm that sets a growth scenario according to the user's emotions based on the emotion estimation data. For example, if the user is dissatisfied with the character's growth, the growth direction is changed based on that feedback. The growth unit also analyzes the user's emotional reactions and builds a system that adjusts the character's behavior and responses based on the results. For example, if the user has positive emotions toward the character's growth, that direction is reinforced. This makes it possible to analyze the user's emotions toward the character's growth and adjust the growth direction based on the results.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The generation unit can analyze the user's voice tone and speaking style and customize the AI ​​character's voice and speaking style based on that. For example, if the user speaks in a calm tone, the character will respond in a similarly calm tone. The generation unit can also learn the characteristics of the user's voice and adjust the character's voice based on that. For example, if the user speaks in a high-pitched voice, the character will respond in a high-pitched voice. Furthermore, the generation unit can analyze the emotion in the user's voice and change the character's voice tone and expression based on that. For example, if the user speaks excitedly, the character will respond in an excited tone. This allows the character's voice and speaking style to be customized based on the user's voice tone and speaking style.

[0077] The generation unit can set the hobbies and interests of the AI ​​character based on the music and movie genres selected by the user. For example, if the user likes rock music, the character can be set to be knowledgeable about rock music. The generation unit can also analyze the genres of movies watched by the user and set the character's movie preferences based on that. For example, if the user watches a lot of science fiction movies, the character can be set to be interested in science fiction movies. Furthermore, the generation unit can customize the content of the character's conversation based on the music and movie genres selected by the user. For example, if the user likes jazz music, the character can talk about jazz. This allows the character's hobbies and interests to be set based on the user's music and movie preferences.

[0078] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user in accordance with the user's life events. For example, if the user gets married, the character can send a message of congratulations. Also, if the user starts a new job, the generation unit can have the character send a message of encouragement. Furthermore, if the user moves, the generation unit can have the character provide advice about the new environment. In this way, the personality and appearance of the character can be automatically changed in accordance with the user's life events.

[0079] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the user's health condition. For example, if the user starts exercising, the character can provide exercise advice. Also, if the user inputs the results of a health check, the generation unit can have the character provide health information. Furthermore, if the user is feeling stressed, the generation unit can have the character make suggestions to help the user relax. This makes it possible to automatically change the personality and appearance of the character according to the user's health condition.

[0080] The generation unit can automatically change the personality and appearance of the AI ​​character selected by the user according to the user's hobbies and interests. For example, if the user starts a new hobby, the character can provide information about that hobby. Also, if the user has a specific interest, the generation unit can have the character provide topics related to that interest. Furthermore, if the user participates in an event related to a hobby or interest, the generation unit can have the character provide information about that event. This makes it possible to automatically change the personality and appearance of the character according to the user's hobbies and interests.

[0081] The conversation providing unit can estimate the user's emotions and suggest music that corresponds to those emotions. For example, if the user is sad, the character can suggest relaxing music. Also, if the user is excited, the conversation providing unit can suggest energetic music. Furthermore, the conversation providing unit can create a music playlist for the character according to the user's emotional state. For example, if the user is feeling stressed, the character can create a relaxing playlist. In this way, music can be suggested that corresponds to the user's emotions.

[0082] The conversation providing unit can estimate the user's emotions and suggest movies and dramas that correspond to those emotions. For example, if the user is sad, a character can suggest an inspiring movie. If the user is excited, the conversation providing unit can suggest an action movie. Furthermore, the conversation providing unit can create a list of movies and dramas that the character chooses depending on the user's emotional state. For example, if the user wants to relax, the character can create a list of relaxing movies. This makes it possible to suggest movies and dramas that correspond to the user's emotions.

[0083] The conversation providing unit can estimate the user's emotions and suggest books and articles according to those emotions. For example, if the user is sad, the character can suggest an encouraging book. Also, if the user is excited, the conversation providing unit can suggest an exciting article. Furthermore, the conversation providing unit can create a list of books and articles for the character according to the user's emotional state. For example, if the user wants to relax, the character can create a list of relaxing books. In this way, books and articles can be suggested according to the user's emotions.

[0084] The conversation providing unit can estimate the user's emotions and suggest travel destinations according to those emotions. For example, if the user is sad, the character can suggest a relaxing travel destination. Also, if the user is excited, the conversation providing unit can suggest an adventure trip for the character. Furthermore, the conversation providing unit can allow the character to create a travel plan according to the user's emotional state. For example, if the user is feeling stressed, the character can create a relaxing travel plan. In this way, travel destinations can be suggested according to the user's emotions.

[0085] The conversation providing unit can estimate the user's emotions and suggest dishes and recipes that correspond to those emotions. For example, if the user is sad, the character can suggest dishes that are relaxing. Furthermore, if the user is excited, the conversation providing unit can suggest dishes that are energetic. Furthermore, the conversation providing unit can create recipes for the character to cook according to the user's emotional state. For example, if the user is feeling stressed, the character can create recipes for dishes that are relaxing. In this way, dishes and recipes can be suggested that correspond to the user's emotions.

[0086] The processing flow of the second embodiment will be briefly explained below.

[0087] Step 1: The generator generates an AI character based on the user's instructions. For example, if the user inputs a prompt such as "I want a bright and energetic character," the generator generates a character based on that instruction. The generator also sets the character's appearance, personality, speaking style, etc. based on the user's instructions. Step 2: The conversation provider uses the AI ​​character generated by the generator to provide a realistic conversation experience. For example, if a user asks, "How was your day?", the character responds with, "I had a great time today. I read a new book." The conversation provider then converts the response into speech and conveys it to the user. Step 3: The access unit makes the conversation experience provided by the conversation providing unit accessible through a messaging app. For example, when a user sends a message such as "Good morning" through a messaging app such as LINE, WhatsApp, or Facebook Messenger, the access unit responds with a message such as "Good morning! What are your plans for today?" Step 4: The development unit develops the AI ​​character to match the user's conversation style and preferences through conversations provided by the conversation provider. For example, it learns the user's frequently used words and topics and generates responses based on them.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0092] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0107] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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."

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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]

[0155] 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 generation unit that generates an AI character based on a user's instructions; a conversation providing unit that provides a realistic conversation experience using the AI ​​character generated by the generation unit; an access unit that makes the conversation experience provided by the conversation providing unit accessible through a messaging app; a growth unit that grows the AI ​​character according to the user's conversation style and preferences through the conversation provided by the conversation providing unit. A system characterized by:

2. The generation unit Analyze the user's past SNS posts and message history and automatically generate the AI ​​character that is best suited to each individual user.

2. The system of claim 1.

3. The generation unit The personality and appearance of the AI ​​character selected by the user are automatically changed according to the season and events.

2. The system of claim 1.

4. The generation unit Generating responses and actions of the AI ​​character according to the user's current emotional state.

2. The system of claim 1.

5. The generation unit Generate the appearance and personality of the AI ​​character based on photos and illustrations uploaded by the user 2. The system of claim 1.

6. The generation unit Add a feature that allows multiple users to jointly develop one AI character, promoting use in group chats.

2. The system of claim 1.

Images