System

Abstract

An object of a system according to an embodiment is to practice and improve communication without involving a person.SOLUTION: A system according to an embodiment includes an interaction unit, a face generation unit, and a voice generation unit. The dialoguer receives input from the user and generates an appropriate response. The face generation unit generates a face on the basis of the response generated by the interaction unit. The voice generation unit generates a voice based on the response generated by the interaction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional technology has the problem that it is difficult to practice and improve communication skills without interacting with people.

[0005] The system according to the embodiment aims to practice and improve communication skills without interacting with other people. [Means for solving the problem]

[0006] The system according to the embodiment includes a dialogue unit, a face generation unit, and a voice generation unit. The dialogue unit receives input from a user and generates an appropriate response. The face generation unit generates a face based on the response generated by the dialogue unit. The voice generation unit generates a voice based on the response generated by the dialogue unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to practice and improve their communication skills without interacting with other people. [Brief explanation of the drawings]

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

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

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

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A communication training system according to an embodiment of the present invention uses training AI to practice and improve communication skills without direct interaction with people. This system uses AI to generate facial and voice images and interact with users, enabling them to improve their ability to read emotions and improve their communication skills. This allows the communication training system to effectively practice and improve communication skills without direct interaction with people.

[0029] A communication training system according to an embodiment includes a dialogue unit, a face generation unit, and a voice generation unit. The dialogue unit receives input from a user and generates an appropriate response. For example, when a user asks, "Hello, what's the weather like today?", the dialogue unit responds with, "Hello, it's sunny today." The dialogue unit can also generate a response using a generation AI (e.g., a text generation AI or a multimodal generation AI) based on the user's input. The face generation unit generates a face based on the response generated by the dialogue unit. For example, when a user says, "Good morning," the face generation unit generates a face that responds with a smile, saying, "Good morning." The face generation unit can also generate an appropriate facial expression based on the user's input using the generation AI. The voice generation unit generates a voice based on the response generated by the dialogue unit. For example, when a user says, "I'm a little tired today," the voice generation unit generates a voice that responds with, "I'm a little tired today" in a sad voice. The voice generation unit can also generate an appropriate voice based on the user's input using the generation AI. As a result, the communication training system according to the embodiment allows users to improve their ability to read emotions and communication skills by interacting with the training AI.

[0030] The dialogue unit can analyze the user's past dialogue history and generate a dialogue scenario optimized for each individual user. For example, the dialogue unit analyzes the user's past dialogue history and identifies frequently used phrases and topics. Based on this, the dialogue unit generates a dialogue scenario that is likely to interest the user. The dialogue unit also learns the user's communication style from the past dialogue history and generates responses that match that style. For example, if the user prefers to use polite language, the dialogue unit can respond in a similar style. The dialogue unit also customizes responses for specific situations and scenarios based on the user's past dialogue history. For example, if the user prefers to talk about work, it can generate a dialogue scenario related to work. This allows for more effective communication practice by generating an optimized dialogue scenario based on the user's past dialogue history.

[0031] The dialogue unit generates dialogue scenarios corresponding to different languages ​​and cultures, and can accommodate global users. The dialogue unit generates dialogue scenarios corresponding to different languages, for example. For example, scenarios that allow dialogue in multiple languages, such as English, French, and Chinese, are prepared. The dialogue unit also generates dialogue scenarios corresponding to different cultures. For example, a dialogue scenario based on Japanese culture and a dialogue scenario based on American culture can be prepared. The dialogue unit also generates dialogue scenarios corresponding to both language and culture. For example, a dialogue scenario based on American culture can be prepared in English, and a dialogue scenario based on French culture can be prepared in French. In this way, dialogue scenarios corresponding to different languages ​​and cultures can be generated, making it possible to accommodate global users.

[0032] The dialogue unit can specialize the dialogue content for a specific field, such as education or medicine, to enable the practice of specialized communication skills. The dialogue unit generates, for example, a dialogue scenario specialized for the education field. For example, a dialogue scenario between a teacher and a student can be prepared to practice communication skills in an educational setting. The dialogue unit also generates a dialogue scenario specialized for the medical field. For example, a dialogue scenario between a doctor and a patient can be prepared to practice communication skills in a medical setting. The dialogue unit also generates a dialogue scenario specialized for the business field. For example, a dialogue scenario between a boss and a subordinate can be prepared to practice communication skills in a business setting. In this way, by providing dialogue content specialized for a specific field, such as education or medicine, it is possible to practice specialized communication skills.

[0033] The face generation unit and voice generation unit can customize the AI's facial and voice features according to the user's preferences. The face generation unit and voice generation unit provide, for example, an interface that allows the user to select their preferred facial features. For example, they can customize hairstyle, eye color, facial expression, etc. The face generation unit and voice generation unit also provide an interface that allows the user to select their preferred voice features. For example, they can customize voice tone, accent, speaking style, etc. The face generation unit and voice generation unit also provide an interface that allows the user to customize both the face and voice. For example, the AI's appearance and voice can be customized by combining facial features and voice features selected by the user. This allows the AI's facial and voice features to be customized according to the user's preferences, enabling a more personalized interaction experience.

[0034] The face generation unit and the voice generation unit can generate faces and voices of different age groups and genders to support a variety of dialogue scenarios. The face generation unit and the voice generation unit can generate, for example, faces and voices of different age groups. For example, faces and voices of children, young people, middle-aged people, and elderly people can be prepared and used depending on the dialogue scenario. The face generation unit and the voice generation unit can also generate faces and voices of different genders. For example, faces and voices of men and women can be prepared so that users can select according to their preferences. The face generation unit and the voice generation unit can also generate faces and voices that combine both age groups and genders. For example, various combinations such as young women and elderly men can be prepared. This makes it possible to support a variety of dialogue scenarios by generating faces and voices of different age groups and genders.

[0035] In addition to generating a face and a voice, the face generation unit and the voice generation unit can also generate gestures and body language, thereby providing a more realistic dialogue experience. For example, in addition to generating a face and a voice, the face generation unit and the voice generation unit can generate gestures such as hand movements and postures. For example, a waving gesture can be added when greeting. The face generation unit and the voice generation unit can also generate body language and dynamically change it depending on the context of the dialogue. For example, a shrugging gesture can be added when surprised. The face generation unit and the voice generation unit can also combine gestures and body language to provide a more realistic dialogue experience. For example, a hand gesture can be added to explain an emphasis point in a conversation. In this way, a more realistic dialogue experience can be achieved by generating gestures and body language.

[0036] The dialogue unit can evaluate the user's emotion reading ability and customize the practice content based on the results. The dialogue unit, for example, conducts a test to evaluate the user's emotion reading ability and customizes the practice content based on the results. For example, it can conduct a test to read facial expressions and tone of voice. The dialogue unit also generates a scenario based on the evaluation results to focus on practicing emotional expressions that the user is not good at. For example, it can practice reading facial expressions of sadness and anger. The dialogue unit also periodically evaluates the user's emotion reading ability and updates the practice content based on the results. For example, it can adjust the practice content by difficulty level according to progress. In this way, more effective practice is possible by evaluating the user's emotion reading ability and customizing the practice content based on the results.

[0037] The dialogue unit can simultaneously express multiple emotions during a dialogue, enabling practice in reading complex emotions. The dialogue unit, for example, generates a scenario in which multiple emotions are simultaneously expressed during a dialogue. For example, complex emotions such as joy and surprise, or sadness and anger can be combined. Furthermore, by simultaneously expressing multiple emotions, the dialogue unit allows the user to practice reading subtle nuances of emotions. For example, the dialogue unit can practice reading sadness hidden in a smile. Furthermore, the dialogue unit dynamically changes the combination of emotions, allowing the user to practice reading various combinations of emotions. For example, the combination of emotions can be changed as the dialogue progresses. In this way, by simultaneously expressing multiple emotions, the user can practice reading complex emotions.

[0038] The dialogue unit can learn emotional expressions from different cultures and improve global emotional reading ability. The dialogue unit, for example, generates scenarios for learning emotional expressions from different cultures. For example, emotional expressions from countries such as Japan, the United States, and France can be learned. The dialogue unit also compares emotional expressions from different cultures and allows the user to practice understanding the differences. For example, the same emotion can be expressed in different ways depending on the culture. The dialogue unit also provides practice scenarios that combine emotional expressions from different cultures to improve global emotional reading ability. For example, emotional expressions from multiple cultures can be learned alternately. In this way, learning emotional expressions from different cultures can improve global emotional reading ability.

[0039] The dialogue unit incorporates game elements into emotion reading practice, allowing users to improve their skills while having fun. The dialogue unit, for example, incorporates game elements into emotion reading practice, allowing users to improve their skills while having fun. For example, it can provide a quiz-style game for reading emotions. The dialogue unit also provides a practice scenario incorporating game elements, allowing users to improve their emotion reading skills with a competitive spirit. For example, it can provide a game in which players compete for scores. The dialogue unit also introduces a reward system into emotion reading practice, motivating users to practice. For example, it can provide a system in which points are accumulated when the correct emotion is read. In this way, by incorporating game elements, users can improve their emotion reading skills while having fun.

[0040] The dialogue unit can point out misunderstandings and miscommunications that occur during a dialogue in real time and suggest areas for improvement. For example, the dialogue unit can detect misunderstandings and miscommunications that occur during a dialogue in real time and point them out to the user. For example, it can provide immediate feedback when a misleading expression is used. The dialogue unit can also analyze the cause of miscommunication and suggest areas for improvement to the user. For example, it can suggest appropriate expressions and phrases. The dialogue unit can also provide advice in real time to prevent misunderstandings and miscommunications as the dialogue progresses. For example, it can provide hints to make the dialogue flow more smoothly. In this way, by pointing out misunderstandings and miscommunications that occur during a dialogue in real time and suggesting areas for improvement, it is possible to improve communication skills.

[0041] The dialogue unit can provide communication practice exercises corresponding to different situations (business, casual, formal, etc.). The dialogue unit can provide, for example, communication practice exercises corresponding to business situations. For example, scenarios for meetings and presentations can be prepared. The dialogue unit can also provide communication practice exercises corresponding to casual situations. For example, scenarios for conversations with friends or everyday conversations can be prepared. The dialogue unit can also provide communication practice exercises corresponding to formal situations. For example, scenarios for speeches and greetings in formal settings can be prepared. In this way, by providing communication practice exercises corresponding to different situations, the user can improve their communication skills in a variety of situations.

[0042] The dialogue unit incorporates role-playing elements into the practice of communication skills, allowing the user to acquire practical skills. For example, the dialogue unit incorporates role-playing elements into the practice of communication skills, allowing the user to acquire practical skills. For example, it can provide scenarios in which roles are set and dialogue takes place. The dialogue unit also provides practice scenarios incorporating role-playing elements, allowing the user to practice communication skills in various situations. For example, roles can be set between a boss and a subordinate, or a customer and a sales representative. The dialogue unit also uses role-playing elements to allow the user to practice simulating actual dialogue situations. For example, the user can practically learn how a dialogue should proceed and how to respond appropriately. In this way, by incorporating role-playing elements, the user can acquire practical communication skills.

[0043] The dialogue unit can analyze the user's dialogue history and provide feedback on long-term skill improvement trends. The dialogue unit, for example, analyzes the user's dialogue history and provides feedback on long-term skill improvement trends. For example, it can evaluate skill progress based on past dialogue data. The dialogue unit also visualizes the user's skill improvement trends based on the dialogue history. For example, it can display skill changes using graphs or charts. The dialogue unit also provides feedback on long-term skill improvement trends and provides advice to help the user continuously improve their skills. For example, it can suggest the next skill to practice. In this way, continuous skill improvement is possible by analyzing the user's dialogue history and providing feedback on long-term skill improvement trends.

[0044] The dialogue unit can customize the feedback content to suit the user's learning style. For example, the dialogue unit analyzes the user's learning style and provides feedback content that matches it. For example, it can provide feedback using graphs and diagrams to a user who prefers visual learning. The dialogue unit also customizes the format and content of the feedback based on the learning style. For example, it can provide text-based feedback to a user who prefers detailed explanations. The dialogue unit also periodically evaluates the user's learning style and updates the feedback content based on the evaluation results. For example, it can change the format of the feedback according to progress. In this way, customizing the feedback content to suit the user's learning style enables more effective learning.

[0045] The dialogue unit can visually display the feedback content, allowing the user to intuitively understand it. The dialogue unit, for example, provides an interface that visually displays the feedback content. For example, it can display skill progress using graphs or charts. The dialogue unit also provides visual feedback, allowing the user to intuitively understand it. For example, it can emphasize the feedback content using colors or icons. The dialogue unit also visually displays the feedback content, allowing the user to grasp the progress of their skill improvement at a glance. For example, it can display the feedback content in a dashboard format. In this way, visually displaying the feedback content makes it easier for the user to intuitively understand.

[0046] The dialogue unit can share the feedback with other users and promote community-based learning. The dialogue unit, for example, provides a function for sharing the feedback content with other users. For example, the dialogue unit can enable the feedback content to be posted on a social networking site or a forum. The dialogue unit also provides a platform for sharing the feedback content to promote community-based learning. For example, the dialogue unit can provide a space where users can share the feedback content and exchange opinions. The dialogue unit can also receive advice and opinions from other users by sharing the feedback content. For example, the dialogue unit can provide a comment function for the feedback content. This makes it possible to share the feedback with other users and promote community-based learning.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The dialogue unit can analyze the user's dialogue history and generate dialogue scenarios based on the user's interests. For example, it can identify topics that the user has frequently discussed in the past and provide new dialogue scenarios related to those topics. The dialogue unit can also learn the user's dialogue style and generate responses that match it. For example, if the user prefers to use polite language, the dialogue unit can respond in a similar style. Furthermore, the dialogue unit can customize responses for specific situations or scenarios based on the user's dialogue history. For example, if the user prefers to talk about work, it can generate dialogue scenarios related to work. This allows for more effective communication practice by generating optimized dialogue scenarios based on the user's past dialogue history.

[0049] The dialogue unit generates dialogue scenarios that correspond to different languages ​​and cultures, making it possible to accommodate global users. For example, dialogue scenarios that correspond to different languages ​​are generated. For example, scenarios that allow dialogue in multiple languages, such as English, French, and Chinese, are prepared. The dialogue unit also generates dialogue scenarios that correspond to different cultures. For example, a dialogue scenario based on Japanese culture and a dialogue scenario based on American culture can be prepared. The dialogue unit also generates dialogue scenarios that correspond to both language and culture. For example, a dialogue scenario based on American culture can be prepared in English, and a dialogue scenario based on French culture can be prepared in French. In this way, dialogue scenarios that correspond to different languages ​​and cultures can be generated, making it possible to accommodate global users.

[0050] The dialogue unit can specialize the dialogue content for a specific field, such as education or medicine, to enable the practice of specialized communication skills. For example, a dialogue scenario specialized for the education field is generated. For example, a dialogue scenario between a teacher and a student can be prepared to practice communication skills in an educational setting. The dialogue unit can also generate a dialogue scenario specialized for the medical field. For example, a dialogue scenario between a doctor and a patient can be prepared to practice communication skills in a medical setting. The dialogue unit can also generate a dialogue scenario specialized for the business field. For example, a dialogue scenario between a boss and a subordinate can be prepared to practice communication skills in a business setting. In this way, by providing dialogue content specialized for a specific field, such as education or medicine, it is possible to practice specialized communication skills.

[0051] The face generation unit and voice generation unit can customize the AI's facial and voice features according to the user's preferences. For example, they provide an interface that allows the user to select their preferred facial features. For example, they can customize hairstyle, eye color, facial expressions, etc. The face generation unit and voice generation unit also provide an interface that allows the user to select their preferred voice features. For example, they can customize voice tone, accent, speaking style, etc. The face generation unit and voice generation unit also provide an interface that allows the user to customize both the face and voice. For example, the user can customize the AI's appearance and voice by combining facial features and voice features selected by the user. This allows the AI's facial and voice features to be customized according to the user's preferences, enabling a more personalized interaction experience.

[0052] The face generation unit and the voice generation unit can generate faces and voices of different age groups and genders to support a variety of dialogue scenarios. For example, faces and voices of different age groups can be generated. For example, faces and voices of children, young people, middle-aged people, and elderly people can be prepared and used depending on the dialogue scenario. The face generation unit and the voice generation unit can also generate faces and voices of different genders. For example, faces and voices of men and women can be prepared so that users can select according to their preferences. The face generation unit and the voice generation unit can also generate faces and voices that combine both age groups and genders. For example, various combinations such as young women and elderly men can be prepared. This makes it possible to support a variety of dialogue scenarios by generating faces and voices of different age groups and genders.

[0053] In addition to generating a face and a voice, the face generation unit and the voice generation unit can also generate gestures and body language, providing a more realistic conversation experience. For example, in addition to generating a face and a voice, gestures such as hand movements and postures can be generated. For example, a waving gesture can be added when greeting. The face generation unit and the voice generation unit also generate body language and dynamically change it depending on the context of the conversation. For example, a shrugging gesture can be added when surprised. The face generation unit and the voice generation unit also combine gestures and body language to provide a more realistic conversation experience. For example, a hand gesture can be added to explain an emphasis point in a conversation. In this way, a more realistic conversation experience can be achieved by generating gestures and body language.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The dialogue unit receives input from the user and generates an appropriate response. For example, if the user asks, "Hello, what's the weather like today?", the dialogue unit responds with, "Hello, it's sunny today." The dialogue unit can also generate a response based on the user's input using a generative AI (e.g., text generation AI or multimodal generation AI). Step 2: The face generation unit generates a face based on the response generated by the dialogue unit. For example, if the user says "Good morning," the face generation unit generates a face that responds with a smile, saying "Good morning." The face generation unit can also use generation AI to generate appropriate facial expressions based on the user's input. Step 3: The speech generation unit generates speech based on the response generated by the dialogue unit. For example, if the user says, "I'm a little tired today," the speech generation unit generates a speech that responds, "I'm a little tired today," in a sad voice. The speech generation unit can also use generation AI to generate appropriate speech based on the user's input.

[0056] (Example 2) A communication training system according to an embodiment of the present invention uses training AI to practice and improve communication skills without direct interaction with people. This system uses AI to generate facial and voice images and interact with users, enabling them to improve their ability to read emotions and improve their communication skills. This allows the communication training system to effectively practice and improve communication skills without direct interaction with people.

[0057] A communication training system according to an embodiment includes a dialogue unit, a face generation unit, and a voice generation unit. The dialogue unit receives input from a user and generates an appropriate response. For example, when a user asks, "Hello, what's the weather like today?", the dialogue unit responds with, "Hello, it's sunny today." The dialogue unit can also generate a response using a generation AI (e.g., a text generation AI or a multimodal generation AI) based on the user's input. The face generation unit generates a face based on the response generated by the dialogue unit. For example, when a user says, "Good morning," the face generation unit generates a face that responds with a smile, saying, "Good morning." The face generation unit can also generate an appropriate facial expression based on the user's input using the generation AI. The voice generation unit generates a voice based on the response generated by the dialogue unit. For example, when a user says, "I'm a little tired today," the voice generation unit generates a voice that responds with, "I'm a little tired today" in a sad voice. The voice generation unit can also generate an appropriate voice based on the user's input using the generation AI. As a result, the communication training system according to the embodiment allows users to improve their ability to read emotions and communication skills by interacting with the training AI.

[0058] The dialogue unit can analyze the user's past dialogue history and generate a dialogue scenario optimized for each individual user. For example, the dialogue unit analyzes the user's past dialogue history and identifies frequently used phrases and topics. Based on this, the dialogue unit generates a dialogue scenario that is likely to interest the user. The dialogue unit also learns the user's communication style from the past dialogue history and generates responses that match that style. For example, if the user prefers to use polite language, the dialogue unit can respond in a similar style. The dialogue unit also customizes responses for specific situations and scenarios based on the user's past dialogue history. For example, if the user prefers to talk about work, it can generate a dialogue scenario related to work. This allows for more effective communication practice by generating an optimized dialogue scenario based on the user's past dialogue history.

[0059] The dialogue unit can analyze the user's facial expression and tone of voice in real time during a dialogue and generate a response accordingly. The dialogue unit, for example, captures the user's facial expression with a camera and analyzes it in real time. For example, if the user is smiling, the dialogue unit can also respond with a smile. The dialogue unit also captures the user's tone of voice with a microphone and analyzes it in real time. For example, if the user is excited, the dialogue unit can also respond with an excited tone. The dialogue unit also analyzes a combination of facial expression and tone of voice to generate a more natural response. For example, if the user has a sad expression and speaks in a low tone, the dialogue unit can generate a response showing empathy in a similar tone. This enables a more natural dialogue experience by generating responses according to the user's facial expression and tone of voice.

[0060] The dialogue unit can use the emotion estimation function to dynamically change the dialogue content according to the user's emotional state. The dialogue unit, for example, estimates the user's emotional state in real time and dynamically changes the dialogue content. For example, if the user is feeling stressed, the dialogue content can be changed to one that relaxes the user. The dialogue unit also uses the emotion estimation function to provide more positive dialogue content when the user is feeling positive. For example, if the user is happy, the dialogue unit can provide a fun topic. The dialogue unit also adjusts the tone and content of the dialogue according to the user's emotional state. For example, if the user is tired, the dialogue content can be changed to one that offers words of encouragement. This allows for more effective communication practice by dynamically changing the dialogue content according to the user's emotional state.

[0061] The dialogue unit generates dialogue scenarios corresponding to different languages ​​and cultures, and can accommodate global users. The dialogue unit generates dialogue scenarios corresponding to different languages, for example. For example, scenarios that allow dialogue in multiple languages, such as English, French, and Chinese, are prepared. The dialogue unit also generates dialogue scenarios corresponding to different cultures. For example, a dialogue scenario based on Japanese culture and a dialogue scenario based on American culture can be prepared. The dialogue unit also generates dialogue scenarios corresponding to both language and culture. For example, a dialogue scenario based on American culture can be prepared in English, and a dialogue scenario based on French culture can be prepared in French. In this way, dialogue scenarios corresponding to different languages ​​and cultures can be generated, making it possible to accommodate global users.

[0062] The dialogue unit can specialize the dialogue content for a specific field, such as education or medicine, to enable the practice of specialized communication skills. The dialogue unit generates, for example, a dialogue scenario specialized for the education field. For example, a dialogue scenario between a teacher and a student can be prepared to practice communication skills in an educational setting. The dialogue unit also generates a dialogue scenario specialized for the medical field. For example, a dialogue scenario between a doctor and a patient can be prepared to practice communication skills in a medical setting. The dialogue unit also generates a dialogue scenario specialized for the business field. For example, a dialogue scenario between a boss and a subordinate can be prepared to practice communication skills in a business setting. In this way, by providing dialogue content specialized for a specific field, such as education or medicine, it is possible to practice specialized communication skills.

[0063] The dialogue unit can use the emotion estimation function to monitor the stress level felt by the user during the dialogue and provide a dialogue that helps the user relax. For example, the dialogue unit can monitor the user's stress level in real time and provide dialogue content that helps the user relax. For example, if the user is feeling high stress, the dialogue unit can provide a topic that helps the user relax. The dialogue unit can also use the emotion estimation function to change the dialogue content to a more relaxing one if the user is feeling stressed. For example, if the user is feeling tense, the dialogue unit can suggest relaxing music. The dialogue unit can also monitor the user's stress level and adjust the tone and content of the dialogue. For example, if the user is tired, the dialogue unit can provide a topic that helps the user relax or words of encouragement. This allows for more effective communication practice by monitoring the user's stress level and providing a dialogue that helps the user relax.

[0064] The face generation unit and voice generation unit can customize the AI's facial and voice features according to the user's preferences. The face generation unit and voice generation unit provide, for example, an interface that allows the user to select their preferred facial features. For example, they can customize hairstyle, eye color, facial expression, etc. The face generation unit and voice generation unit also provide an interface that allows the user to select their preferred voice features. For example, they can customize voice tone, accent, speaking style, etc. The face generation unit and voice generation unit also provide an interface that allows the user to customize both the face and voice. For example, the AI's appearance and voice can be customized by combining facial features and voice features selected by the user. This allows the AI's facial and voice features to be customized according to the user's preferences, enabling a more personalized interaction experience.

[0065] The face generation unit and voice generation unit can dynamically change the AI's facial expression and tone of voice according to the context of the conversation. The face generation unit and voice generation unit dynamically change the AI's facial expression according to the context of the conversation. For example, if the user is talking about something fun, the AI ​​can respond with a smile. The face generation unit and voice generation unit also dynamically change the AI's tone of voice according to the context of the conversation. For example, if the user is talking about something sad, the AI ​​can respond in a calm tone. The face generation unit and voice generation unit also dynamically change the combination of facial expression and tone of voice. For example, if the user is talking about something surprising, the AI ​​can respond with a surprised facial expression and tone. This allows the AI's facial expression and tone of voice to dynamically change according to the context of the conversation, enabling a more natural conversation experience.

[0066] The face generation unit and the voice generation unit can generate faces and voices of different age groups and genders to support a variety of dialogue scenarios. The face generation unit and the voice generation unit can generate, for example, faces and voices of different age groups. For example, faces and voices of children, young people, middle-aged people, and elderly people can be prepared and used depending on the dialogue scenario. The face generation unit and the voice generation unit can also generate faces and voices of different genders. For example, faces and voices of men and women can be prepared so that users can select according to their preferences. The face generation unit and the voice generation unit can also generate faces and voices that combine both age groups and genders. For example, various combinations such as young women and elderly men can be prepared. This makes it possible to support a variety of dialogue scenarios by generating faces and voices of different age groups and genders.

[0067] In addition to generating a face and a voice, the face generation unit and the voice generation unit can also generate gestures and body language, thereby providing a more realistic dialogue experience. For example, in addition to generating a face and a voice, the face generation unit and the voice generation unit can generate gestures such as hand movements and postures. For example, a waving gesture can be added when greeting. The face generation unit and the voice generation unit can also generate body language and dynamically change it depending on the context of the dialogue. For example, a shrugging gesture can be added when surprised. The face generation unit and the voice generation unit can also combine gestures and body language to provide a more realistic dialogue experience. For example, a hand gesture can be added to explain an emphasis point in a conversation. In this way, a more realistic dialogue experience can be achieved by generating gestures and body language.

[0068] The face generation unit and the voice generation unit can use the emotion estimation function to provide a face and voice combination that makes the user most relaxed. For example, the face generation unit and the voice generation unit can use the emotion estimation function to identify facial features that make the user most relaxed and generate that face. For example, a face with a calm expression and gentle eye features can be generated. The face generation unit and the voice generation unit can also use the emotion estimation function to identify a voice tone that makes the user most relaxed and generate that voice. For example, a voice with a calm tone and soft speaking style can be generated. The face generation unit and the voice generation unit can also optimize the face and voice combination to provide the user with the most relaxing interaction experience. For example, a calm expression can be combined with a calm voice tone. This allows for more effective communication practice by providing a face and voice combination that makes the user feel relaxed.

[0069] The dialogue unit can evaluate the user's emotion reading ability and customize the practice content based on the results. The dialogue unit, for example, conducts a test to evaluate the user's emotion reading ability and customizes the practice content based on the results. For example, it can conduct a test to read facial expressions and tone of voice. The dialogue unit also generates a scenario based on the evaluation results to focus on practicing emotional expressions that the user is not good at. For example, it can practice reading facial expressions of sadness and anger. The dialogue unit also periodically evaluates the user's emotion reading ability and updates the practice content based on the results. For example, it can adjust the practice content by difficulty level according to progress. In this way, more effective practice is possible by evaluating the user's emotion reading ability and customizing the practice content based on the results.

[0070] The dialogue unit can simultaneously express multiple emotions during a dialogue, enabling practice in reading complex emotions. The dialogue unit, for example, generates a scenario in which multiple emotions are simultaneously expressed during a dialogue. For example, complex emotions such as joy and surprise, or sadness and anger can be combined. Furthermore, by simultaneously expressing multiple emotions, the dialogue unit allows the user to practice reading subtle nuances of emotions. For example, the dialogue unit can practice reading sadness hidden in a smile. Furthermore, the dialogue unit dynamically changes the combination of emotions, allowing the user to practice reading various combinations of emotions. For example, the combination of emotions can be changed as the dialogue progresses. In this way, by simultaneously expressing multiple emotions, the user can practice reading complex emotions.

[0071] The dialogue unit can use the emotion estimation function to provide feedback on the accuracy of the user's emotion reading in real time. For example, the dialogue unit can use the emotion estimation function to provide feedback on the accuracy of the emotion read by the user in real time. For example, instant feedback can be provided when the user reads the correct emotion. The dialogue unit can also evaluate the accuracy of the user's emotion reading and adjust the practice content based on the evaluation result. For example, the dialogue unit can focus practice on emotional expressions that the user has difficulty expressing. The dialogue unit can also use the emotion estimation function to monitor the progress of the user's emotion reading in real time and provide feedback. For example, the dialogue unit can provide advice to help the user improve their emotion reading skills. In this way, the effectiveness of practice can be enhanced by providing feedback on the accuracy of the user's emotion reading in real time.

[0072] The dialogue unit can learn emotional expressions from different cultures and improve global emotional reading ability. The dialogue unit, for example, generates scenarios for learning emotional expressions from different cultures. For example, emotional expressions from countries such as Japan, the United States, and France can be learned. The dialogue unit also compares emotional expressions from different cultures and allows the user to practice understanding the differences. For example, the same emotion can be expressed in different ways depending on the culture. The dialogue unit also provides practice scenarios that combine emotional expressions from different cultures to improve global emotional reading ability. For example, emotional expressions from multiple cultures can be learned alternately. In this way, learning emotional expressions from different cultures can improve global emotional reading ability.

[0073] The dialogue unit incorporates game elements into emotion reading practice, allowing users to improve their skills while having fun. The dialogue unit, for example, incorporates game elements into emotion reading practice, allowing users to improve their skills while having fun. For example, it can provide a quiz-style game for reading emotions. The dialogue unit also provides a practice scenario incorporating game elements, allowing users to improve their emotion reading skills with a competitive spirit. For example, it can provide a game in which players compete for scores. The dialogue unit also introduces a reward system into emotion reading practice, motivating users to practice. For example, it can provide a system in which points are accumulated when the correct emotion is read. In this way, by incorporating game elements, users can improve their emotion reading skills while having fun.

[0074] The dialogue unit uses the emotion estimation function to identify the emotional expression that the user is most difficult to express and can focus on practicing that expression. The dialogue unit, for example, uses the emotion estimation function to identify the emotional expression that the user is most difficult to express. For example, it can analyze emotions that the user cannot accurately read. The dialogue unit also provides a scenario for focusing on practicing the emotional expression that the user is least able to express. For example, it can repeatedly practice the specific emotional expression. The dialogue unit also uses the emotion estimation function to monitor the user's progress and continuously practice the emotional expression that the user is least able to express. For example, it can periodically evaluate and update the practice content. In this way, it is possible to identify the emotional expression that the user is most difficult to express and focus on practicing that expression, thereby improving emotion reading skills.

[0075] The dialogue unit can point out misunderstandings and miscommunications that occur during a dialogue in real time and suggest areas for improvement. For example, the dialogue unit can detect misunderstandings and miscommunications that occur during a dialogue in real time and point them out to the user. For example, it can provide immediate feedback when a misleading expression is used. The dialogue unit can also analyze the cause of miscommunication and suggest areas for improvement to the user. For example, it can suggest appropriate expressions and phrases. The dialogue unit can also provide advice in real time to prevent misunderstandings and miscommunications as the dialogue progresses. For example, it can provide hints to make the dialogue flow more smoothly. In this way, by pointing out misunderstandings and miscommunications that occur during a dialogue in real time and suggesting areas for improvement, it is possible to improve communication skills.

[0076] The dialogue unit can quantitatively evaluate the degree of improvement of the user's communication skills using the emotion estimation function. The dialogue unit, for example, uses the emotion estimation function to quantitatively evaluate the degree of improvement of the user's communication skills. For example, it can score the accuracy and appropriateness of emotional expression during a conversation. The dialogue unit also quantitatively evaluates the progress of the user's communication skills and adjusts the practice content based on the evaluation result. For example, it can change the difficulty of the practice depending on the degree of skill improvement. The dialogue unit also uses the emotion estimation function to monitor the improvement of the user's communication skills in real time and provide feedback. For example, it can provide advice according to the skill improvement. In this way, by quantitatively evaluating the degree of improvement of the user's communication skills, it is possible to objectively grasp the effectiveness of the practice.

[0077] The dialogue unit can provide communication practice exercises corresponding to different situations (business, casual, formal, etc.). The dialogue unit can provide, for example, communication practice exercises corresponding to business situations. For example, scenarios for meetings and presentations can be prepared. The dialogue unit can also provide communication practice exercises corresponding to casual situations. For example, scenarios for conversations with friends or everyday conversations can be prepared. The dialogue unit can also provide communication practice exercises corresponding to formal situations. For example, scenarios for speeches and greetings in formal settings can be prepared. In this way, by providing communication practice exercises corresponding to different situations, the user can improve their communication skills in a variety of situations.

[0078] The dialogue unit incorporates role-playing elements into the practice of communication skills, allowing the user to acquire practical skills. For example, the dialogue unit incorporates role-playing elements into the practice of communication skills, allowing the user to acquire practical skills. For example, it can provide scenarios in which roles are set and dialogue takes place. The dialogue unit also provides practice scenarios incorporating role-playing elements, allowing the user to practice communication skills in various situations. For example, roles can be set between a boss and a subordinate, or a customer and a sales representative. The dialogue unit also uses role-playing elements to allow the user to practice simulating actual dialogue situations. For example, the user can practically learn how a dialogue should proceed and how to respond appropriately. In this way, by incorporating role-playing elements, the user can acquire practical communication skills.

[0079] The dialogue unit can use the emotion estimation function to identify the communication style in which the user is most confident and strengthen that style. The dialogue unit, for example, uses the emotion estimation function to identify the communication style in which the user is most confident. For example, it can analyze the style in which the user has positive emotions. The dialogue unit also provides practice scenarios to strengthen the communication style in which the user is confident. For example, it can repeatedly practice dialogue in a specific style. The dialogue unit also uses the emotion estimation function to monitor the user's progress and continuously strengthen the communication style in which the user is confident. For example, it can periodically evaluate and update the practice content. In this way, it is possible to identify the communication style in which the user is most confident and strengthen that style, thereby improving communication skills.

[0080] The dialogue unit can analyze the user's dialogue history and provide feedback on long-term skill improvement trends. The dialogue unit, for example, analyzes the user's dialogue history and provides feedback on long-term skill improvement trends. For example, it can evaluate skill progress based on past dialogue data. The dialogue unit also visualizes the user's skill improvement trends based on the dialogue history. For example, it can display skill changes using graphs or charts. The dialogue unit also provides feedback on long-term skill improvement trends and provides advice to help the user continuously improve their skills. For example, it can suggest the next skill to practice. In this way, continuous skill improvement is possible by analyzing the user's dialogue history and providing feedback on long-term skill improvement trends.

[0081] The dialogue unit can customize the feedback content to suit the user's learning style. For example, the dialogue unit analyzes the user's learning style and provides feedback content that matches it. For example, it can provide feedback using graphs and diagrams to a user who prefers visual learning. The dialogue unit also customizes the format and content of the feedback based on the learning style. For example, it can provide text-based feedback to a user who prefers detailed explanations. The dialogue unit also periodically evaluates the user's learning style and updates the feedback content based on the evaluation results. For example, it can change the format of the feedback according to progress. In this way, customizing the feedback content to suit the user's learning style enables more effective learning.

[0082] The dialogue unit can use the emotion estimation function to select an expression that is most acceptable to the user when providing feedback. For example, the dialogue unit can use the emotion estimation function to identify an expression that is most acceptable to the user and provide feedback using that expression. For example, the dialogue unit can select an expression that indicates a positive emotion for the user. The dialogue unit can also analyze the user's emotional state in real time and adjust the expression of the feedback based on the results. For example, if the user is feeling stressed, a gentle expression can be used. The dialogue unit can also use the emotion estimation function to dynamically change the expression that is most acceptable to the user when providing feedback. For example, the tone and content of the feedback can be adjusted according to changes in the user's emotions. This can increase the effectiveness of the feedback by selecting an expression that is most acceptable to the user.

[0083] The dialogue unit can visually display the feedback content, allowing the user to intuitively understand it. The dialogue unit, for example, provides an interface that visually displays the feedback content. For example, it can display skill progress using graphs or charts. The dialogue unit also provides visual feedback, allowing the user to intuitively understand it. For example, it can emphasize the feedback content using colors or icons. The dialogue unit also visually displays the feedback content, allowing the user to grasp the progress of their skill improvement at a glance. For example, it can display the feedback content in a dashboard format. In this way, visually displaying the feedback content makes it easier for the user to intuitively understand.

[0084] The dialogue unit can share the feedback with other users and promote community-based learning. The dialogue unit, for example, provides a function for sharing the feedback content with other users. For example, the dialogue unit can enable the feedback content to be posted on a social networking site or a forum. The dialogue unit also provides a platform for sharing the feedback content to promote community-based learning. For example, the dialogue unit can provide a space where users can share the feedback content and exchange opinions. The dialogue unit can also receive advice and opinions from other users by sharing the feedback content. For example, the dialogue unit can provide a comment function for the feedback content. This makes it possible to share the feedback with other users and promote community-based learning.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The dialogue unit can analyze the user's dialogue history and generate dialogue scenarios based on the user's interests. For example, it can identify topics that the user has frequently discussed in the past and provide new dialogue scenarios related to those topics. The dialogue unit can also learn the user's dialogue style and generate responses that match it. For example, if the user prefers to use polite language, the dialogue unit can respond in a similar style. Furthermore, the dialogue unit can customize responses for specific situations or scenarios based on the user's dialogue history. For example, if the user prefers to talk about work, it can generate dialogue scenarios related to work. This allows for more effective communication practice by generating optimized dialogue scenarios based on the user's past dialogue history.

[0087] The dialogue unit can analyze the user's facial expression and tone of voice in real time and generate a response accordingly. For example, if the user is smiling, the dialogue unit can also respond with a smile. The dialogue unit also captures the user's tone of voice with a microphone and analyzes it in real time. For example, if the user is excited, the dialogue unit can also respond with an excited tone. The dialogue unit also analyzes a combination of facial expression and tone of voice to generate a more natural response. For example, if the user has a sad expression and speaks in a low tone, the dialogue unit can generate a response showing empathy in a similar tone. This allows for a more natural dialogue experience by generating responses according to the user's facial expression and tone of voice.

[0088] The dialogue unit can use the emotion estimation function to dynamically change the dialogue content according to the user's emotional state. For example, if the user is feeling stressed, the dialogue content can be changed to one that is relaxing. The dialogue unit can also use the emotion estimation function to provide more positive dialogue content if the user is feeling positive. For example, if the user is happy, the dialogue unit can provide a fun topic. The dialogue unit can also adjust the tone and content of the dialogue according to the user's emotional state. For example, if the user is tired, the dialogue content can be changed to one that offers words of encouragement. This allows for more effective communication practice by dynamically changing the dialogue content according to the user's emotional state.

[0089] The dialogue unit generates dialogue scenarios that correspond to different languages ​​and cultures, making it possible to accommodate global users. For example, dialogue scenarios that correspond to different languages ​​are generated. For example, scenarios that allow dialogue in multiple languages, such as English, French, and Chinese, are prepared. The dialogue unit also generates dialogue scenarios that correspond to different cultures. For example, a dialogue scenario based on Japanese culture and a dialogue scenario based on American culture can be prepared. The dialogue unit also generates dialogue scenarios that correspond to both language and culture. For example, a dialogue scenario based on American culture can be prepared in English, and a dialogue scenario based on French culture can be prepared in French. In this way, dialogue scenarios that correspond to different languages ​​and cultures can be generated, making it possible to accommodate global users.

[0090] The dialogue unit can specialize the dialogue content for a specific field, such as education or medicine, to enable the practice of specialized communication skills. For example, a dialogue scenario specialized for the education field is generated. For example, a dialogue scenario between a teacher and a student can be prepared to practice communication skills in an educational setting. The dialogue unit can also generate a dialogue scenario specialized for the medical field. For example, a dialogue scenario between a doctor and a patient can be prepared to practice communication skills in a medical setting. The dialogue unit can also generate a dialogue scenario specialized for the business field. For example, a dialogue scenario between a boss and a subordinate can be prepared to practice communication skills in a business setting. In this way, by providing dialogue content specialized for a specific field, such as education or medicine, it is possible to practice specialized communication skills.

[0091] The dialogue unit can use the emotion estimation function to monitor the stress level felt by the user during the dialogue and provide a dialogue that helps them relax. For example, the dialogue unit can monitor the user's stress level in real time and provide dialogue content that helps them relax. For example, if the user is feeling high stress, it can provide a topic that helps them relax. The dialogue unit can also use the emotion estimation function to change the dialogue content to something that helps them relax when the user is feeling stressed. For example, if the user is feeling tense, it can suggest relaxing music. The dialogue unit can also monitor the user's stress level and adjust the tone and content of the dialogue. For example, if the user is tired, it can provide a topic that helps them relax or words of encouragement. This allows for more effective communication practice by monitoring the user's stress level and providing a dialogue that helps them relax.

[0092] The face generation unit and voice generation unit can customize the AI's facial and voice features according to the user's preferences. For example, they provide an interface that allows the user to select their preferred facial features. For example, they can customize hairstyle, eye color, facial expressions, etc. The face generation unit and voice generation unit also provide an interface that allows the user to select their preferred voice features. For example, they can customize voice tone, accent, speaking style, etc. The face generation unit and voice generation unit also provide an interface that allows the user to customize both the face and voice. For example, the user can customize the AI's appearance and voice by combining facial features and voice features selected by the user. This allows the AI's facial and voice features to be customized according to the user's preferences, enabling a more personalized interaction experience.

[0093] The face generation unit and voice generation unit can dynamically change the AI's facial expression and tone of voice according to the context of the conversation. For example, the AI's facial expression can be dynamically changed according to the context of the conversation. For example, if the user is talking about something fun, the AI ​​can respond with a smile. The face generation unit and voice generation unit also dynamically change the AI's tone of voice according to the context of the conversation. For example, if the user is talking about something sad, the AI ​​can respond in a calm tone. The face generation unit and voice generation unit also dynamically change the combination of facial expression and tone of voice. For example, if the user is talking about something surprising, the AI ​​can respond with a surprised facial expression and tone. This allows the AI's facial expression and tone of voice to be dynamically changed according to the context of the conversation, enabling a more natural conversation experience.

[0094] The face generation unit and the voice generation unit can generate faces and voices of different age groups and genders to support a variety of dialogue scenarios. For example, faces and voices of different age groups can be generated. For example, faces and voices of children, young people, middle-aged people, and elderly people can be prepared and used depending on the dialogue scenario. The face generation unit and the voice generation unit can also generate faces and voices of different genders. For example, faces and voices of men and women can be prepared so that users can select according to their preferences. The face generation unit and the voice generation unit can also generate faces and voices that combine both age groups and genders. For example, various combinations such as young women and elderly men can be prepared. This makes it possible to support a variety of dialogue scenarios by generating faces and voices of different age groups and genders.

[0095] In addition to generating a face and a voice, the face generation unit and the voice generation unit can also generate gestures and body language, providing a more realistic conversation experience. For example, in addition to generating a face and a voice, gestures such as hand movements and postures can be generated. For example, a waving gesture can be added when greeting. The face generation unit and the voice generation unit also generate body language and dynamically change it depending on the context of the conversation. For example, a shrugging gesture can be added when surprised. The face generation unit and the voice generation unit also combine gestures and body language to provide a more realistic conversation experience. For example, a hand gesture can be added to explain an emphasis point in a conversation. In this way, a more realistic conversation experience can be achieved by generating gestures and body language.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The dialogue unit receives input from the user and generates an appropriate response. For example, if the user asks, "Hello, what's the weather like today?", the dialogue unit responds with, "Hello, it's sunny today." The dialogue unit can also generate a response based on the user's input using a generative AI (e.g., text generation AI or multimodal generation AI). Step 2: The face generation unit generates a face based on the response generated by the dialogue unit. For example, if the user says "Good morning," the face generation unit generates a face that responds with a smile, saying "Good morning." The face generation unit can also use generation AI to generate appropriate facial expressions based on the user's input. Step 3: The speech generation unit generates speech based on the response generated by the dialogue unit. For example, if the user says, "I'm a little tired today," the speech generation unit generates a speech that responds, "I'm a little tired today," in a sad voice. The speech generation unit can also use generation AI to generate appropriate speech based on the user's input.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[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 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.

[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. 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.

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

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[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 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.

[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 AI 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 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.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[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 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.

[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 (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).

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

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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 AI 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.

[0130] 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.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] 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.

[0144] 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.

[0145] 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 AI 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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]

[0165] 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. Using training AI, The training AI is a dialogue unit that receives input from a user and generates an appropriate response; a face generation unit that generates a face based on the response generated by the dialogue unit; a voice generating unit that generates a voice based on the response generated by the dialogue unit; A system characterized by:

2. The dialogue unit The user's past dialogue history is analyzed to generate a dialogue scenario optimized for each individual user.

2. The system of claim 1.

3. The dialogue unit Analyze the user's facial expressions and tone of voice in real time during the conversation and generate responses accordingly.

2. The system of claim 1.

4. The dialogue unit Dynamically changing the dialogue content according to the emotional state of the user.

2. The system of claim 1.

5. The dialogue unit Generate dialogue scenarios that correspond to different languages ​​and cultures to accommodate global users 2. The system of claim 1.

6. The dialogue unit The dialogue content can be tailored to specific fields such as education and medicine, allowing for the practice of specialized communication skills.

2. The system of claim 1.

7. The dialogue unit Monitor the stress level felt by the user during the interaction and provide a relaxing interaction 2. The system of claim 1.

Images