System

Abstract

An object of the system according to the embodiment is to realize a natural conversation with a specific character.SOLUTION: A system according to an embodiment includes a user input unit, a speech generation unit, and a character learning unit. The user input unit receives an input from a user. The conversation generation unit generates a conversation on the basis of the input received by the user input unit. The character learning unit learns the tone and personality of a specific character.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 had the problem of making it difficult to realize natural conversations with specific characters.

[0005] The system according to the embodiment aims to realize natural conversation with a specific character. [Means for solving the problem]

[0006] The system according to the embodiment includes a user input unit, a conversation generation unit, and a character learning unit. The user input unit receives input from a user. The conversation generation unit generates conversation based on the input received by the user input unit. The character learning unit learns the tone of voice and personality of a specific character. [Effects of the Invention]

[0007] The system according to the embodiment can realize natural conversation with a specific character. [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 nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) A telephone conversation system according to an embodiment of the present invention is a system that allows users to have telephone conversations with specific characters. In this system, a generation AI automatically generates conversation content. This allows the user to enjoy natural conversations with the specific characters.

[0029] A telephone conversation system according to an embodiment includes a generation AI, a user input unit, a conversation generation unit, and a character learning unit. The generation AI includes a user input unit that accepts input from a user. For example, the user input unit can accept text input. The user input unit can also accept voice input. The user input unit can also accept gesture input. The conversation generation unit generates a conversation based on the input accepted by the user input unit. For example, the conversation generation unit generates a text-based conversation. The conversation generation unit can also generate a voice-based conversation. The conversation generation unit can also generate a conversation taking into account the character's tone of voice and personality. The character learning unit learns the tone of voice and personality of a specific character. For example, the character learning unit learns a friendly tone of voice. The character learning unit can also learn a strict personality. The character learning unit can also learn the characteristics of a humorous character. This enables the telephone conversation system to generate a natural conversation with a specific character based on the user's input. For example, if a user says, "Hello, Dad," the generated AI will respond with, "Hello, how are you?" If a user asks, "How are you doing lately?", the generated AI will respond with, "I've been busy lately, but I'm doing well." If the character has a sense of humor, the generated AI can add a joke at an appropriate time. If a user asks, "What did you do today?", the generated AI will respond with, "I went for a walk today." If a user wants to talk about a specific topic, the generated AI will provide information related to that topic and move the conversation forward. This allows users to enjoy conversations that are tailored to their interests.

[0030] The conversation generation unit can refer to the user's past conversation history and revisit past topics to maintain consistency in the conversation. For example, the generation AI in the conversation generation unit can refer to the user's past conversation history and revisit topics that came up in previous conversations. For example, if the user said "I'm going on a trip" in a previous conversation, the generation AI can ask "How was your trip?" The conversation generation unit can also store the user's past conversation history in a database and refer to it as needed. For example, it can refer to the text log stored in the database and revisit past topics. This allows consistency in the conversation to be maintained.

[0031] The conversation generation unit can be equipped with a group chat function in which multiple characters simultaneously participate in a conversation. In the conversation generation unit, for example, the generation AI controls multiple characters simultaneously to realize a group chat with a user. For example, when a user asks, "How is everyone?", multiple characters report their respective situations. The conversation generation unit can also provide a group chat function in which multiple users simultaneously participate. For example, multiple users send messages at the same time, and characters respond to them. The conversation generation unit can also set a message synchronization method, allowing multiple characters to have a consistent conversation. This makes it possible to have a group chat with multiple characters.

[0032] The conversation generation unit can have a function in which a character grasps the user's schedule and plans and provides reminders and advice at the appropriate time. In the conversation generation unit, for example, the generation AI grasps the user's schedule and provides reminders at the appropriate time. For example, when the user says, "I have a meeting tomorrow," the generation AI reminds the user by asking, "Are you ready for the meeting?" The conversation generation unit can also manage the user's schedule and set reminders through collaboration with a calendar app. For example, it can provide reminders based on plans registered in the calendar app. The conversation generation unit can also provide advice based on the user's schedule. For example, when the user says, "I have a presentation next week," the generation AI advises, "You should start preparing for the presentation." This makes it possible to provide reminders and advice based on the user's schedule.

[0033] The conversation generation unit can analyze user input and automatically select a conversation topic based on the user's interests and concerns. For example, the generation AI in the conversation generation unit analyzes user input and automatically selects a conversation topic based on the user's interests and concerns. For example, if a user asks, "What movies have you seen recently?", the generation AI may expand the topic by asking, "What movies have you seen recently?" The conversation generation unit can also analyze the user's interests and concerns based on past input data and select a topic based on that. For example, if a user has asked many questions about movies in the past, the generation AI will select a topic related to movies. The conversation generation unit can also set criteria for selecting a topic based on user input and select a topic based on that. This enables conversations based on the user's interests and concerns.

[0034] The conversation generation unit can translate user input in real time, enabling natural conversations with users who speak different languages. For example, the conversation generation unit uses a generation AI to translate user input in real time, enabling natural conversations with users who speak different languages. For example, when a user speaks in Japanese, the generation AI translates it into English and responds. The conversation generation unit can also translate user input in real time using a machine translation model. For example, a neural machine translation model can be used to perform highly accurate translations. The conversation generation unit can also use real-time translation technology to smoothly conduct conversations between different languages. For example, when a user speaks in English, the generation AI translates it into Japanese and responds. This enables natural conversations with users who speak different languages.

[0035] The conversation generation unit can have a function in which a character suggests quizzes and games to a user based on user input. In the conversation generation unit, for example, a generation AI suggests a quiz to a user based on user input. For example, when a user says, "I'm bored," the generation AI suggests, "Shall we try a quiz?" The conversation generation unit can also suggest games based on user input. For example, when a user says, "Is there anything fun to do?" the generation AI suggests, "Shall we play a game?" The conversation generation unit can also generate specific content for quizzes and games and provide them to the user. For example, the generation AI generates quiz questions based on the user's interests and asks them to the user. This makes it possible to suggest quizzes and games to the user.

[0036] The conversation generation unit can have a function in which a character provides study and training advice to a user based on user input. In the conversation generation unit, for example, the generation AI provides study advice to a user based on user input. For example, if a user says, "Studying is difficult," the generation AI advises, "Try this method." The conversation generation unit can also provide training advice based on user input. For example, if a user says, "I can't keep up with exercise," the generation AI advises, "Try doing a little bit every day." The conversation generation unit can also generate specific study and training plans and provide them to the user. For example, the generation AI creates a study plan based on the user's goals and proposes it to the user. This makes it possible to provide study and training advice to the user.

[0037] The character learning unit can learn not only a character's tone of voice and personality, but also the character's history and background information, enabling deeper conversations. For example, the character learning unit allows the generation AI to learn not only a character's tone of voice and personality, but also the character's history and background information, enabling deeper conversations. For example, it can incorporate the character's past events and episodes into the conversation. The character learning unit can also learn the character's background story and generate conversations based on that. For example, it can reflect the character's upbringing and past experiences in the conversation. The character learning unit can also store the character's history and background information in a database and reference it as needed. This allows the character's history and background information to be learned, enabling deeper conversations.

[0038] The character learning unit can also learn the character's voice tone and accent to generate more realistic voice responses. For example, the character learning unit allows the generation AI to learn the character's voice tone and accent to generate more realistic voice responses. For example, the character speaks with an accent from a specific region. The character learning unit can also reproduce the character's voice tone and accent using voice synthesis technology. For example, the character's voice characteristics are reproduced using voice synthesis technology. The character learning unit can also store the character's voice tone and accent in a database and refer to it as needed. This allows the character's voice tone and accent to be learned, enabling more realistic voice responses.

[0039] The character learning unit can have a function to generate a new character by combining the speech tones and personalities of different characters. In the character learning unit, for example, the generation AI combines the speech tones and personalities of different characters to generate a new character. For example, a character that combines humor and seriousness can be created. The character learning unit can also generate a new character by combining the characteristics of different characters. For example, a new character can be created by combining the speech tones and personalities of multiple characters. The character learning unit can also store the personalities and speech tones of the new character in a database and refer to them as needed. This makes it possible to generate a new character by combining the speech tones and personalities of different characters.

[0040] The character learning unit can provide a function for customizing a character's personality and tone of voice according to the user's preferences. In the character learning unit, for example, the generation AI customizes a character's personality and tone of voice according to the user's preferences. For example, if a user requests, "Speak more gently," the generation AI adjusts the character's tone. The character learning unit can also adjust a character's personality and tone of voice based on the user's preferences. For example, if a user requests, "Speak more entertainingly," the generation AI increases the character's humor. The character learning unit can also store the character settings customized based on the user's preferences in a database and refer to them as needed. This makes it possible to customize a character's personality and tone of voice according to the user's preferences.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The telephone conversation system can be equipped with a health management function that monitors the user's health condition and provides appropriate advice. For example, if a user says, "I've been feeling tired lately," the generation AI will advise, "It's important to get enough sleep." The conversation generation unit can also collect the user's health data and provide advice based on their health condition. For example, it can suggest, "Try walking a little more today," based on the user's step count data. The conversation generation unit can also provide reminders based on the user's health condition. For example, it can remind the user to "stay hydrated." This can support the user's health management.

[0043] A telephone conversation system can be equipped with a function that suggests related events and activities based on the user's hobbies and interests. For example, if a user says, "I like music," the generation AI can suggest, "There's a concert happening nearby." The conversation generation unit can also refer to the user's past conversation history and suggest events based on their interests. For example, if a user says, "I like movies," the AI ​​can suggest, "A new movie will be released this weekend." The conversation generation unit can also suggest activities based on the user's interests. For example, the AI ​​can suggest, "Why not go hiking this weekend?" This makes it possible to make suggestions based on the user's hobbies and interests.

[0044] The telephone conversation system can be equipped with a function in which a character suggests travel plans to the user based on the user's input. For example, if the user says, "I want to go on a trip," the generation AI will suggest, "How about this place?" The conversation generation unit can also suggest travel plans based on the user's interests and budget. For example, it could suggest, "Here are some travel destinations that you can enjoy within your budget." The conversation generation unit can also refer to the user's past travel history and suggest travel plans based on that. For example, it could suggest, "I also recommend this place, which is close to places you've visited before." This makes it possible to suggest travel plans to the user.

[0045] The telephone conversation system can be equipped with a function in which a character suggests new hobby ideas to the user based on the user's input. For example, if the user says, "I want to find a new hobby," the generation AI will suggest, "What do you think of this hobby?" The conversation generation unit can also suggest hobby ideas based on the user's interests and skills. For example, it could suggest, "Why not try this hobby that's easy to start?" The conversation generation unit can also refer to the user's past conversation history about hobbies and suggest new hobby ideas based on that. For example, it could suggest, "I also recommend this hobby that you talked about before." This makes it possible to suggest new hobby ideas to the user.

[0046] The telephone conversation system can be equipped with a function in which a character manages the user's learning progress based on the user's input. For example, if the user says, "I'm not making progress in my studies," the generation AI can suggest, "Let's try this section today." The conversation generation unit can also manage progress based on the user's learning goals and provide appropriate advice. For example, it can suggest, "Let's review this section for the next test." The conversation generation unit can also refer to the user's learning history and manage progress based on that. For example, it can suggest, "Let's focus on reviewing this section, which you struggled with in the last test." This makes it possible to manage the user's learning progress and provide appropriate advice.

[0047] The telephone conversation system can be equipped with a function in which a character suggests cooking recipes to the user based on the user's input. For example, if the user says, "I want to make something delicious," the generation AI will suggest, "How about this recipe?" The conversation generation unit can also suggest recipes based on the user's preferences and ingredients. For example, it could suggest, "Why not try this recipe that can be made with the ingredients in your refrigerator?" The conversation generation unit can also refer to the user's past cooking history and suggest recipes based on that. For example, it could suggest, "I also recommend this dish that I made before." This makes it possible to suggest cooking recipes to the user.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The user input unit accepts input from the user, such as text input, voice input, or gesture input. Step 2: The conversation generation unit generates conversation based on the input received by the user input unit. For example, the conversation generation unit can generate text-based conversation or voice-based conversation, taking into account the character's tone of voice and personality. Step 3: The character learning unit learns the tone and personality of a specific character. For example, it can learn the characteristics of a character who has a friendly tone, a strict personality, or a humorous personality.

[0050] (Example 2) A telephone conversation system according to an embodiment of the present invention is a system that allows users to have telephone conversations with specific characters. In this system, a generation AI automatically generates conversation content. This allows the user to enjoy natural conversations with the specific characters.

[0051] A telephone conversation system according to an embodiment includes a generation AI, a user input unit, a conversation generation unit, and a character learning unit. The generation AI includes a user input unit that accepts input from a user. For example, the user input unit can accept text input. The user input unit can also accept voice input. The user input unit can also accept gesture input. The conversation generation unit generates a conversation based on the input accepted by the user input unit. For example, the conversation generation unit generates a text-based conversation. The conversation generation unit can also generate a voice-based conversation. The conversation generation unit can also generate a conversation taking into account the character's tone of voice and personality. The character learning unit learns the tone of voice and personality of a specific character. For example, the character learning unit learns a friendly tone of voice. The character learning unit can also learn a strict personality. The character learning unit can also learn the characteristics of a humorous character. This enables the telephone conversation system to generate a natural conversation with a specific character based on the user's input. For example, if a user says, "Hello, Dad," the generated AI will respond with, "Hello, how are you?" If a user asks, "How are you doing lately?", the generated AI will respond with, "I've been busy lately, but I'm doing well." If the character has a sense of humor, the generated AI can add a joke at an appropriate time. If a user asks, "What did you do today?", the generated AI will respond with, "I went for a walk today." If a user wants to talk about a specific topic, the generated AI will provide information related to that topic and move the conversation forward. This allows users to enjoy conversations that are tailored to their interests.

[0052] The conversation generation unit can refer to the user's past conversation history and revisit past topics to maintain consistency in the conversation. For example, the generation AI in the conversation generation unit can refer to the user's past conversation history and revisit topics that came up in previous conversations. For example, if the user said "I'm going on a trip" in a previous conversation, the generation AI can ask "How was your trip?" The conversation generation unit can also store the user's past conversation history in a database and refer to it as needed. For example, it can refer to the text log stored in the database and revisit past topics. This allows consistency in the conversation to be maintained.

[0053] The conversation generation unit can simulate the emotional state of a character and change the character's reaction according to the user's emotions. For example, the generation AI in the conversation generation unit simulates the emotional state of a character and changes the reaction according to the user's emotions. For example, if the user speaks in a sad voice, the generation AI gently asks, "What's wrong? Did something happen?" The conversation generation unit can also simulate the character's emotional state using an emotion model. For example, it can simulate changes in the character's facial expression and voice based on the emotion model. The conversation generation unit can also estimate the user's emotions using voice tone analysis and facial expression recognition technology and change the character's reaction accordingly. This enables natural conversation that corresponds to the user's emotions.

[0054] The conversation generation unit can use the emotion estimation function to analyze the user's emotions in real time and generate a response from the character that comforts or encourages the user. For example, the conversation generation unit can use the emotion estimation function to analyze the user's emotions in real time and generate a response from the character that comforts the user. For example, if the user speaks in a sad voice, the generation AI can comfort them by saying, "It's okay, it'll get better." The conversation generation unit can also analyze the user's emotions using an emotion estimation algorithm and generate an appropriate response based on that. For example, it can estimate the user's emotions using a machine learning model and generate phrases to comfort them. The conversation generation unit can also set criteria for generating responses based on the user's emotions and generate responses based on those criteria. This enables appropriate responses to be provided according to the user's emotions.

[0055] The conversation generation unit can be equipped with a group chat function in which multiple characters simultaneously participate in a conversation. In the conversation generation unit, for example, the generation AI controls multiple characters simultaneously to realize a group chat with a user. For example, when a user asks, "How is everyone?", multiple characters report their respective situations. The conversation generation unit can also provide a group chat function in which multiple users simultaneously participate. For example, multiple users send messages at the same time, and characters respond to them. The conversation generation unit can also set a message synchronization method, allowing multiple characters to have a consistent conversation. This makes it possible to have a group chat with multiple characters.

[0056] The conversation generation unit can have a function in which a character grasps the user's schedule and plans and provides reminders and advice at the appropriate time. In the conversation generation unit, for example, the generation AI grasps the user's schedule and provides reminders at the appropriate time. For example, when the user says, "I have a meeting tomorrow," the generation AI reminds the user by asking, "Are you ready for the meeting?" The conversation generation unit can also manage the user's schedule and set reminders through collaboration with a calendar app. For example, it can provide reminders based on plans registered in the calendar app. The conversation generation unit can also provide advice based on the user's schedule. For example, when the user says, "I have a presentation next week," the generation AI advises, "You should start preparing for the presentation." This makes it possible to provide reminders and advice based on the user's schedule.

[0057] The conversation generation unit can be equipped with a function that uses an emotion estimation function to analyze the emotions a user has toward a specific character and further personalize the conversation with that character. For example, the conversation generation unit uses the emotion estimation function to analyze the emotions a user has toward a specific character and personalize the conversation with that character. For example, if a user has positive emotions toward a specific character, the generation AI makes that character appear more frequently. The conversation generation unit can also adjust the frequency of a character's appearance and the content of the conversation based on the user's past reactions. For example, if a user has a favorable reaction toward a specific character, the conversation with that character can be increased. The conversation generation unit can also use emotion scoring to evaluate the user's emotions and personalize the conversation based on that evaluation. This enables personalized conversations based on the user's emotions.

[0058] The conversation generation unit can analyze user input and automatically select a conversation topic based on the user's interests and concerns. For example, the generation AI in the conversation generation unit analyzes user input and automatically selects a conversation topic based on the user's interests and concerns. For example, if a user asks, "What movies have you seen recently?", the generation AI may expand the topic by asking, "What movies have you seen recently?" The conversation generation unit can also analyze the user's interests and concerns based on past input data and select a topic based on that. For example, if a user has asked many questions about movies in the past, the generation AI will select a topic related to movies. The conversation generation unit can also set criteria for selecting a topic based on user input and select a topic based on that. This enables conversations based on the user's interests and concerns.

[0059] The conversation generation unit can translate user input in real time, enabling natural conversations with users who speak different languages. For example, the conversation generation unit uses a generation AI to translate user input in real time, enabling natural conversations with users who speak different languages. For example, when a user speaks in Japanese, the generation AI translates it into English and responds. The conversation generation unit can also translate user input in real time using a machine translation model. For example, a neural machine translation model can be used to perform highly accurate translations. The conversation generation unit can also use real-time translation technology to smoothly conduct conversations between different languages. For example, when a user speaks in English, the generation AI translates it into Japanese and responds. This enables natural conversations with users who speak different languages.

[0060] The conversation generation unit can use the emotion estimation function to analyze the emotion of the user's input and generate an appropriate response based on the emotion. The conversation generation unit, for example, uses the emotion estimation function to analyze the emotion of the user's input and generate an appropriate response based on the emotion. For example, if the user expresses anger, the generation AI responds by saying, "Let's speak calmly." The conversation generation unit can also analyze the user's emotion using an emotion estimation algorithm and generate an appropriate response based on the analysis. For example, the conversation generation unit can estimate the user's emotion using a machine learning model and generate an appropriate response. The conversation generation unit can also set criteria for generating a response based on the user's emotion and generate a response based on the criteria. This makes it possible to provide an appropriate response based on the user's emotion.

[0061] The conversation generation unit can have a function in which a character suggests quizzes and games to a user based on user input. In the conversation generation unit, for example, a generation AI suggests a quiz to a user based on user input. For example, when a user says, "I'm bored," the generation AI suggests, "Shall we try a quiz?" The conversation generation unit can also suggest games based on user input. For example, when a user says, "Is there anything fun to do?" the generation AI suggests, "Shall we play a game?" The conversation generation unit can also generate specific content for quizzes and games and provide them to the user. For example, the generation AI generates quiz questions based on the user's interests and asks them to the user. This makes it possible to suggest quizzes and games to the user.

[0062] The conversation generation unit can have a function in which a character provides study and training advice to a user based on user input. In the conversation generation unit, for example, the generation AI provides study advice to a user based on user input. For example, if a user says, "Studying is difficult," the generation AI advises, "Try this method." The conversation generation unit can also provide training advice based on user input. For example, if a user says, "I can't keep up with exercise," the generation AI advises, "Try doing a little bit every day." The conversation generation unit can also generate specific study and training plans and provide them to the user. For example, the generation AI creates a study plan based on the user's goals and proposes it to the user. This makes it possible to provide study and training advice to the user.

[0063] The conversation generation unit can be equipped with a function that uses an emotion estimation function to analyze the emotion of the user's input, and the character suggests music and videos that correspond to the user's emotions. For example, the conversation generation unit uses the emotion estimation function to analyze the emotion of the user's input, and the character suggests music that corresponds to the user's emotions. For example, if the user speaks in a sad voice, the generation AI suggests, "Listen to this song." The conversation generation unit can also suggest videos that correspond to the user's emotions. For example, if the user says that they are tired, the generation AI suggests, "Watch this relaxing video." The conversation generation unit can also generate a playlist of music and videos based on the user's emotions and provide it to the user. For example, the generation AI creates a playlist that corresponds to the user's emotions and suggests it to the user. This makes it possible to suggest music and videos that correspond to the user's emotions.

[0064] The character learning unit can learn not only a character's tone of voice and personality, but also the character's history and background information, enabling deeper conversations. For example, the character learning unit allows the generation AI to learn not only a character's tone of voice and personality, but also the character's history and background information, enabling deeper conversations. For example, it can incorporate the character's past events and episodes into the conversation. The character learning unit can also learn the character's background story and generate conversations based on that. For example, it can reflect the character's upbringing and past experiences in the conversation. The character learning unit can also store the character's history and background information in a database and reference it as needed. This allows the character's history and background information to be learned, enabling deeper conversations.

[0065] The character learning unit can also learn the character's voice tone and accent to generate more realistic voice responses. For example, the character learning unit allows the generation AI to learn the character's voice tone and accent to generate more realistic voice responses. For example, the character speaks with an accent from a specific region. The character learning unit can also reproduce the character's voice tone and accent using voice synthesis technology. For example, the character's voice characteristics are reproduced using voice synthesis technology. The character learning unit can also store the character's voice tone and accent in a database and refer to it as needed. This allows the character's voice tone and accent to be learned, enabling more realistic voice responses.

[0066] The character learning unit can use the emotion estimation function to simulate the emotional state of the character and express an appropriate emotion according to the user's emotion. The character learning unit can, for example, use the emotion estimation function to simulate the emotional state of the character and express an appropriate emotion according to the user's emotion. For example, if the user speaks in a sad voice, the character responds in a gentle voice. The character learning unit can also simulate the emotional state of the character using an emotion model. For example, it can simulate changes in the character's facial expression and voice based on the emotion model. The character learning unit can also estimate the user's emotion using voice tone analysis and facial expression recognition technology and change the character's emotional expression accordingly. This makes it possible to simulate the emotional state of the character and express an appropriate emotion according to the user's emotion.

[0067] The character learning unit can have a function to generate a new character by combining the speech tones and personalities of different characters. In the character learning unit, for example, the generation AI combines the speech tones and personalities of different characters to generate a new character. For example, a character that combines humor and seriousness can be created. The character learning unit can also generate a new character by combining the characteristics of different characters. For example, a new character can be created by combining the speech tones and personalities of multiple characters. The character learning unit can also store the personalities and speech tones of the new character in a database and refer to them as needed. This makes it possible to generate a new character by combining the speech tones and personalities of different characters.

[0068] The character learning unit can provide a function for customizing a character's personality and tone of voice according to the user's preferences. In the character learning unit, for example, the generation AI customizes a character's personality and tone of voice according to the user's preferences. For example, if a user requests, "Speak more gently," the generation AI adjusts the character's tone. The character learning unit can also adjust a character's personality and tone of voice based on the user's preferences. For example, if a user requests, "Speak more entertainingly," the generation AI increases the character's humor. The character learning unit can also store the character settings customized based on the user's preferences in a database and refer to them as needed. This makes it possible to customize a character's personality and tone of voice according to the user's preferences.

[0069] The character learning unit can use the emotion estimation function to analyze the emotions a user has toward a specific character and adjust the character's personality and tone of voice. For example, the character learning unit can use the emotion estimation function to analyze the emotions a user has toward a specific character and adjust the character's personality and tone of voice. For example, if a user has positive emotions toward a character, the generation AI makes that character appear more frequently. The character learning unit can also adjust the character's personality and tone of voice based on the user's emotions. For example, if a user has negative emotions toward a character, the generation AI adjusts the character's tone. The character learning unit can also use emotion scoring to evaluate the user's emotions and adjust the character's personality and tone of voice based on the evaluation. This makes it possible to adjust the character's personality and tone of voice based on the user's emotions toward that character.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The telephone conversation system can be equipped with a health management function that monitors the user's health condition and provides appropriate advice. For example, if a user says, "I've been feeling tired lately," the generation AI will advise, "It's important to get enough sleep." The conversation generation unit can also collect the user's health data and provide advice based on their health condition. For example, it can suggest, "Try walking a little more today," based on the user's step count data. The conversation generation unit can also provide reminders based on the user's health condition. For example, it can remind the user to "stay hydrated." This can support the user's health management.

[0072] A telephone conversation system can be equipped with a function that suggests related events and activities based on the user's hobbies and interests. For example, if a user says, "I like music," the generation AI can suggest, "There's a concert happening nearby." The conversation generation unit can also refer to the user's past conversation history and suggest events based on their interests. For example, if a user says, "I like movies," the AI ​​can suggest, "A new movie will be released this weekend." The conversation generation unit can also suggest activities based on the user's interests. For example, the AI ​​can suggest, "Why not go hiking this weekend?" This makes it possible to make suggestions based on the user's hobbies and interests.

[0073] The telephone conversation system can be equipped with a function to estimate the user's emotions and suggest relaxation methods according to the emotions. For example, if the user is feeling stressed, the generation AI can suggest, "Try taking a deep breath." The conversation generation unit can also estimate the user's emotions using voice tone analysis and facial expression recognition technology and suggest relaxation methods according to the emotions. For example, if the user is feeling anxious, the conversation generation unit can suggest, "Why not try meditation?" The conversation generation unit can also suggest relaxation music or videos based on the user's emotions. For example, it can suggest, "Try listening to this relaxing music." This makes it possible to suggest relaxation methods according to the user's emotions.

[0074] The telephone conversation system can be equipped with a function to estimate the user's emotions and suggest exercises according to their emotions. For example, if the user is tired, the generation AI can suggest, "Let's try some light stretching." The conversation generation unit can also estimate the user's emotions using voice tone analysis and facial expression recognition technology and suggest appropriate exercises. For example, if the user is irritated, the conversation generation unit can suggest, "Why not try yoga?" The conversation generation unit can also adjust the type and intensity of exercise based on the user's emotions. For example, it can suggest, "Let's do some light exercise today to relax." This makes it possible to suggest exercises according to the user's emotions.

[0075] The telephone conversation system can be equipped with a function to estimate the user's emotions and provide dietary advice according to the emotion. For example, if the user is tired, the generation AI can suggest, "Why don't you try eating a banana to replenish your energy?" The conversation generation unit can also estimate the user's emotions using voice tone analysis and facial expression recognition technology and provide dietary advice according to the emotion. For example, if the user is feeling stressed, the conversation generation unit can suggest, "Why don't you try drinking herbal tea to relax?" The conversation generation unit can also adjust the type and timing of meals based on the user's emotions. For example, it can suggest, "Try to eat a light meal today." This makes it possible to provide dietary advice according to the user's emotions.

[0076] The telephone conversation system can be equipped with a function in which a character suggests travel plans to the user based on the user's input. For example, if the user says, "I want to go on a trip," the generation AI will suggest, "How about this place?" The conversation generation unit can also suggest travel plans based on the user's interests and budget. For example, it could suggest, "Here are some travel destinations that you can enjoy within your budget." The conversation generation unit can also refer to the user's past travel history and suggest travel plans based on that. For example, it could suggest, "I also recommend this place, which is close to places you've visited before." This makes it possible to suggest travel plans to the user.

[0077] The telephone conversation system can be equipped with a function in which a character suggests new hobby ideas to the user based on the user's input. For example, if the user says, "I want to find a new hobby," the generation AI will suggest, "What do you think of this hobby?" The conversation generation unit can also suggest hobby ideas based on the user's interests and skills. For example, it could suggest, "Why not try this hobby that's easy to start?" The conversation generation unit can also refer to the user's past conversation history about hobbies and suggest new hobby ideas based on that. For example, it could suggest, "I also recommend this hobby that you talked about before." This makes it possible to suggest new hobby ideas to the user.

[0078] The telephone conversation system can be equipped with a function in which a character manages the user's learning progress based on the user's input. For example, if the user says, "I'm not making progress in my studies," the generation AI can suggest, "Let's try this section today." The conversation generation unit can also manage progress based on the user's learning goals and provide appropriate advice. For example, it can suggest, "Let's review this section for the next test." The conversation generation unit can also refer to the user's learning history and manage progress based on that. For example, it can suggest, "Let's focus on reviewing this section, which you struggled with in the last test." This makes it possible to manage the user's learning progress and provide appropriate advice.

[0079] The telephone conversation system can be equipped with a function to estimate a user's emotions and provide reading advice according to the user's emotions. For example, if a user wants to relax, the generation AI can suggest, "Why not try reading this book?" The conversation generation unit can also estimate the user's emotions using voice tone analysis and facial expression recognition technology and provide reading advice according to the user's emotions. For example, if a user wants to cheer up, the conversation generation unit can suggest, "Why not try reading this encouraging book?" The conversation generation unit can also suggest reading genres and titles based on the user's emotions. For example, the conversation generation unit can suggest, "Let's try reading this mystery novel today." This makes it possible to provide reading advice according to the user's emotions.

[0080] The telephone conversation system can be equipped with a function in which a character suggests cooking recipes to the user based on the user's input. For example, if the user says, "I want to make something delicious," the generation AI will suggest, "How about this recipe?" The conversation generation unit can also suggest recipes based on the user's preferences and ingredients. For example, it could suggest, "Why not try this recipe that can be made with the ingredients in your refrigerator?" The conversation generation unit can also refer to the user's past cooking history and suggest recipes based on that. For example, it could suggest, "I also recommend this dish that I made before." This makes it possible to suggest cooking recipes to the user.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The user input unit accepts input from the user, such as text input, voice input, or gesture input. Step 2: The conversation generation unit generates conversation based on the input received by the user input unit. For example, the conversation generation unit can generate text-based conversation or voice-based conversation, taking into account the character's tone of voice and personality. Step 3: The character learning unit learns the tone and personality of a specific character. For example, it can learn the characteristics of a character who has a friendly tone, a strict personality, or a humorous personality.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0096] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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]

[0150] 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. Equipped with generative AI, a user input unit that accepts input from a user; a conversation generation unit that generates a conversation based on the input received by the user input unit; A character learning unit that learns the tone and personality of a specific character. A system characterized by:

2. The conversation generation unit Simulating the emotional state of the character and varying the reaction of the character depending on the emotions of the user. The system of claim 1 .

3. The conversation generation unit The character has the function of understanding the user's schedule and plans and providing reminders and advice at appropriate times. The system of claim 1 .

4. The character learning unit Learning not only the character's tone and personality, but also the character's history and background information, allowing for deeper conversations The system of claim 1 .

5. The conversation generation unit Using an emotion estimation function, the emotion of the user's input is analyzed and an appropriate response is generated according to the emotion. The system of claim 1 .

Images