System

Abstract

An object of the system according to the embodiment is to increase the time for questions and answers in an online or hybrid study meeting or lecture meeting.SOLUTION: A system includes a chat insertion part, a reaction analysis part, and a question generation part. The chat insertion unit automatically inserts a chat. The reaction analysis unit analyzes a reaction of the participant to the chat inserted by the chat insertion unit. The question generation unit automatically generates a question based on the reaction analyzed by the reaction analysis 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] With conventional technology, online or hybrid study groups and lectures had the problem of silence or a lack of excitement during the question and answer session.

[0005] The system according to the embodiment aims to liven up question and answer sessions in online or hybrid study groups and lectures. [Means for solving the problem]

[0006] The system according to the embodiment includes a chat insertion unit, a reaction analysis unit, and a question generation unit. The chat insertion unit automatically inserts chat. The reaction analysis unit analyzes participants' reactions to the chat inserted by the chat insertion unit. The question generation unit automatically generates questions based on the reactions analyzed by the reaction analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can liven up question and answer sessions in online or hybrid study groups and lectures. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​service according to an embodiment of the present invention is a system that automatically and appropriately inserts chat messages at online or hybrid events such as study groups and lectures, facilitating communication between participants and speakers and creating an environment that is conducive to learning. This enables the AI ​​service to resolve issues such as silence during question-and-answer sessions and a lack of enthusiasm, thereby facilitating communication between participants and speakers.

[0029] An AI service according to an embodiment includes a chat insertion unit, a reaction analysis unit, and a question generation unit. The chat insertion unit automatically inserts chat messages. For example, the generation AI analyzes the progress of a study group or lecture in real time and automatically inserts chat messages at appropriate times. The generation AI generates appropriate chat messages based on prompts related to the progress of the event and the content of the lecture. The reaction analysis unit analyzes participants' reactions to the chat messages inserted by the chat insertion unit. For example, the generation AI performs analysis based on data related to the content and reactions of the participants. The generation AI analyzes how participants are reacting to the chat messages and which parts of the chat messages are causing the most questions, and notifies the speaker in real time. The question generation unit automatically generates questions based on the reactions analyzed by the reaction analysis unit. For example, the generation AI generates questions based on prompts related to the content of the lecture. When a speaker is explaining a specific topic, the generation AI automatically generates questions related to the topic and inserts them into the chat messages. This allows the AI ​​service according to an embodiment to facilitate communication between participants and speakers and create an environment that is conducive to learning.

[0030] The chat insertion unit can analyze the past speech histories of participants and automatically generate personalized chats tailored to individual participants. For example, the chat insertion unit analyzes the past speech histories of participants and automatically generates chats related to a particular topic for participants who are interested in that topic. For example, technology-related questions are inserted for participants who are interested in technology. The chat insertion unit also identifies the interests and concerns of individual participants based on the past speech histories of participants and generates personalized chats tailored to those interests. For example, chats encouraging participants who have asked many questions in the past are inserted. The chat insertion unit also analyzes the past speech histories of participants and automatically generates chats on topics that are likely to interest specific participants. For example, chats related to a particular topic are inserted for participants who have made many comments on that topic in the past. In this way, the interest of participants can be attracted by providing personalized chats tailored to individual participants.

[0031] The chat insertion unit can analyze the speaker's speaking style and tone and automatically adjust the chat style and expressions accordingly. The chat insertion unit, for example, analyzes the speaker's speaking style and tone in real time and adjusts the chat style and expressions based on the results. For example, if the speaker speaks in a casual tone, the chat will also be written in a casual style. The chat insertion unit also analyzes the speaker's speaking style and tone and automatically generates chat that matches the speaker's style. For example, if the speaker uses a lot of technical terminology, the chat will also use technical expressions. The chat insertion unit also analyzes the speaker's tone and generates chat that matches that tone. For example, if the speaker speaks enthusiastically, the chat will also use expressions that convey enthusiasm. This makes it possible to increase the sense of unity in the lecture by providing chat that matches the speaker's speaking style and tone.

[0032] The chat insertion unit can provide the automatic chat insertion function not only as text but also as audio or video messages. For example, the chat insertion unit provides the automatic chat insertion function as audio messages, allowing participants to voice their questions or opinions. For example, after a speaker explains an important point, the audio may say, "Does anyone have any questions about this part?" The chat insertion unit also provides the automatic chat insertion function as video messages, allowing participants to voice their questions or opinions. For example, when a speaker is explaining a particular topic, the video may say, "What do you think about this content?" The chat insertion unit also automatically inserts audio or video messages in addition to text chat, allowing participants to use a variety of communication methods. For example, the speaker may announce the next topic by audio. This provides a variety of communication methods, thereby improving convenience for participants.

[0033] The chat insertion unit can add a function for automatically inserting chat in different languages, making it usable at international events. For example, the chat insertion unit makes the automatic chat insertion function multilingual and automatically generates chat in different languages. For example, chat is inserted in multiple languages, such as English, French, and Chinese. In addition, to accommodate international events, the chat insertion unit translates chat in real time so that participants can receive chat in their own language. For example, if a speaker speaks in English, the chat is automatically translated and inserted. In addition, the chat insertion unit adds a function for automatically inserting chat in different languages, making it possible for international participants to ask questions or express opinions in their own language. For example, if a speaker speaks in Japanese, the chat is translated and inserted into English or Chinese. This makes it possible to accommodate the diversity of participants by making it usable at international events.

[0034] The reaction analysis unit uses generative AI to analyze participants' facial expressions and gestures and provide comprehensive feedback that includes non-verbal reactions. For example, the reaction analysis unit analyzes participants' facial expressions in real time and provides feedback to the speaker. For example, if a participant smiles, it provides feedback such as "The participant is enjoying themselves." The reaction analysis unit also analyzes participants' gestures and notifies the speaker of their non-verbal reactions. For example, if a participant nods, it provides feedback such as "The participant understands." The reaction analysis unit also comprehensively analyzes participants' facial expressions and gestures and provides feedback to the speaker in real time. For example, if a participant looks confused, it provides feedback such as "The participant is having trouble understanding." This allows the speaker to provide comprehensive feedback that includes non-verbal reactions, allowing them to more accurately understand participants' reactions.

[0035] The reaction analysis unit analyzes participant reaction data over time to understand changes in reactions to specific time periods or topics. The reaction analysis unit, for example, analyzes participant reaction data over time to understand changes in reactions during specific time periods. For example, it compares reactions at the start and end of a lecture. The reaction analysis unit also analyzes participant reaction data to understand changes in reactions to specific topics. For example, it compares reactions to technical topics with reactions to marketing topics. The reaction analysis unit also analyzes participant reaction data over time to understand changes in reactions as the lecture progresses. For example, it identifies points during the lecture where participants' interest increases. This makes it possible to understand changes in reactions to specific time periods or topics, thereby optimizing the progress of the lecture.

[0036] The reaction analysis unit can visualize the participant reaction analysis results in real time and provide a dashboard that the speaker can intuitively understand. The reaction analysis unit, for example, visualizes the participant reaction analysis results in real time and provides a dashboard that the speaker can intuitively understand. For example, it displays the participant's emotion scores in a graph. The reaction analysis unit also visualizes the participant reaction analysis results so that the speaker can intuitively understand. For example, it displays the participant's reactions in a color-coded manner. The reaction analysis unit also updates the participant reaction analysis results in real time and provides a dashboard that the speaker can intuitively understand. For example, it displays the participant's reaction data in real time. In this way, by providing reaction analysis results visualized in real time, the speaker can intuitively grasp the participant's reactions.

[0037] The reaction analysis unit can integrate the reaction analysis results with other event data to provide more detailed insights. For example, the reaction analysis unit integrates the participant reaction analysis results with participant profile data to provide more detailed insights. For example, it analyzes the reactions of participants in specific occupations or age groups. The reaction analysis unit also integrates the participant reaction analysis results with past participation history to understand changes in participant reactions. For example, it compares reactions at past events with reactions at the current event. The reaction analysis unit also integrates the participant reaction analysis results with other event data to provide more detailed insights. For example, it analyzes reactions based on participants' interests and concerns. This allows speakers to gain a deeper understanding of participant reactions by providing detailed insights integrated with other event data.

[0038] The question generation unit can use generation AI to analyze participants' past question history and automatically generate personalized questions tailored to each individual participant. For example, the question generation unit analyzes participants' past question history and automatically generates questions related to that topic for participants who are interested in a particular topic. For example, it generates technology-related questions for participants who are interested in technology. The question generation unit also identifies the interests and concerns of each individual participant based on the participants' past question history and generates personalized questions tailored to those interests. For example, it generates in-depth questions for participants who have asked many questions in the past. The question generation unit also analyzes participants' past question history and automatically generates questions related to topics that are likely to interest a particular participant. For example, it generates questions related to that topic for participants who have asked many questions about a particular topic in the past. In this way, it is possible to pique the participants' interest by providing them with personalized questions tailored to that individual participant.

[0039] The question generation unit can extract keywords and important points from the content of the lecture and automatically generate in-depth questions based on them. The question generation unit, for example, extracts keywords from the content of the lecture and automatically generates in-depth questions based on those keywords. For example, detailed technical questions are generated based on keywords related to technical topics. The question generation unit also extracts important points from the content of the lecture and automatically generates in-depth questions based on those points. For example, questions are generated related to points emphasized by the speaker. The question generation unit also analyzes keywords and important points and automatically generates in-depth questions based on them. For example, questions are generated to help participants deepen their understanding based on the main points of the content of the lecture. This makes it possible to deepen participants' understanding by providing in-depth questions based on the content of the lecture.

[0040] The question generation unit can provide the automatic question generation function not only as text but also as audio or video messages. For example, the question generation unit provides the automatic question generation function as audio messages, allowing participants to ask questions by audio. For example, after a speaker explains an important point, the audio may say, "Does anyone have any questions about this part?" The question generation unit also provides the automatic question generation function as video messages, allowing participants to ask questions by video. For example, when a speaker is explaining a specific topic, the video may say, "What do you think about this content?" The question generation unit also automatically generates audio and video messages in addition to text questions, allowing participants to use a variety of means to ask questions. For example, the speaker may announce the next topic by audio. This provides a variety of ways to ask questions, thereby improving convenience for participants.

[0041] The question generation unit can add a function for automatically generating questions in different languages, making it usable at international events. For example, the question generation unit makes the automatic question generation function multilingual and automatically generates questions in different languages. For example, questions are generated in multiple languages, such as English, French, and Chinese. In addition, to accommodate international events, the question generation unit translates questions in real time so that participants can receive questions in their own language. For example, if a speaker is speaking in English, the question is automatically translated and inserted. In addition, the question generation unit can add a function for automatically generating questions in different languages, making it possible for international participants to ask questions in their own language. For example, if a speaker is speaking in Japanese, the question is translated into English or Chinese and inserted. This makes it possible to accommodate the diversity of participants by making it usable at international events.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The chat insertion unit can analyze the past speech history of participants and automatically generate personalized chats tailored to each individual participant. For example, by analyzing the past speech history of participants, it can automatically generate chats related to a particular topic for participants who are interested in that topic. For participants who are interested in technology, it can insert technology-related questions. The chat insertion unit can also identify the interests and concerns of individual participants based on the past speech history of participants and generate personalized chats tailored to those interests. For participants who have asked many questions in the past, it can insert chats encouraging them to ask questions. It can also automatically generate chats on topics that are likely to interest specific participants. For participants who have made many comments on a particular topic in the past, it can insert chats related to that topic. In this way, it is possible to attract the participants' interest by providing personalized chats tailored to each individual participant.

[0044] The chat insertion unit can analyze the speaker's speaking style and tone and automatically adjust the chat style and expressions accordingly. For example, it can analyze the speaker's speaking style and tone in real time and adjust the chat style and expressions based on the results. If the speaker speaks in a casual tone, the chat will also be written in a casual style. It can also analyze the speaker's speaking style and tone and automatically generate chat that matches the speaker's style. If the speaker uses a lot of technical terminology, the chat will also use technical expressions. It can also analyze the speaker's tone and generate chat that matches that tone. If the speaker speaks enthusiastically, the chat will also use expressions that convey enthusiasm. This can increase the sense of unity in the lecture by providing chat that matches the speaker's speaking style and tone.

[0045] The chat insertion unit can provide the automatic chat insertion function not only as text but also as audio or video messages. For example, the automatic chat insertion function can be provided as an audio message, allowing participants to voice their questions or opinions. After a speaker explains an important point, the audio can say, "Does anyone have any questions about this part?" The chat insertion unit can also provide the automatic chat insertion function as a video message, allowing participants to voice their questions or opinions. When a speaker is explaining a particular topic, the video can say, "What do you think about this content?" Furthermore, by automatically inserting audio or video messages in addition to text chat, participants can be provided with a variety of communication methods. The speaker can announce the next thing they want to say by audio. This can improve convenience for participants by providing a variety of communication methods.

[0046] The chat insertion unit can add a function for automatically inserting chat in different languages, making it usable at international events. For example, the automatic chat insertion function can be made multilingual, automatically generating chat in different languages. Chat can be inserted in multiple languages, such as English, French, and Chinese. Furthermore, to accommodate international events, chat can be translated in real time so that participants can receive chat in their own language. If a speaker speaks in English, the chat can be automatically translated and inserted. Furthermore, a function for automatically inserting chat in different languages ​​can be added, allowing international participants to ask questions or express their opinions in their own language. If a speaker speaks in Japanese, the chat can be translated and inserted into English or Chinese. This makes it possible to accommodate the diversity of participants at international events.

[0047] The reaction analysis unit uses generative AI to analyze participants' facial expressions and gestures and provide comprehensive feedback, including non-verbal reactions. For example, it can analyze participants' facial expressions in real time and provide feedback to the speaker. If a participant smiles, it can provide feedback such as "The participant is enjoying themselves." It can also analyze participants' gestures and notify the speaker of their non-verbal reactions. If a participant nods, it can provide feedback such as "The participant understands." It can also comprehensively analyze participants' facial expressions and gestures and provide feedback to the speaker in real time. If a participant looks confused, it can provide feedback such as "The participant is having trouble understanding." This allows the speaker to provide comprehensive feedback, including non-verbal reactions, more accurately grasp the participants' reactions.

[0048] The reaction analysis unit analyzes participant reaction data over time to understand changes in reactions to specific time periods or topics. For example, participant reaction data can be analyzed over time to understand changes in reactions during specific time periods, comparing reactions at the start and end of a lecture. It can also analyze participant reaction data to understand changes in reactions to specific topics, comparing reactions to technical topics with reactions to marketing topics. It can also analyze participant reaction data over time to understand changes in reactions as the lecture progresses, identifying points during the lecture where participant interest increases. This allows it to understand changes in reactions to specific time periods or topics, thereby optimizing the progress of the lecture.

[0049] The reaction analysis unit can visualize the participant reaction analysis results in real time, providing a dashboard that the speaker can intuitively understand. For example, the participant reaction analysis results can be visualized in real time, providing a dashboard that the speaker can intuitively understand. Participant emotion scores can be displayed in a graph. The participant reaction analysis results can also be visualized, allowing the speaker to intuitively understand. Participant reactions can be displayed in color-coded. Furthermore, the participant reaction analysis results can be updated in real time, providing a dashboard that the speaker can intuitively understand. Participant reaction data is displayed in real time. This allows the speaker to intuitively grasp the participants' reactions by providing reaction analysis results visualized in real time.

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

[0051] Step 1: The chat insertion unit automatically inserts chat. For example, the generation AI analyzes the progress of a study group or lecture in real time and automatically inserts chat at the appropriate time. The generation AI generates appropriate chat based on prompts related to the progress of the event and the content of the lecture. Step 2: The reaction analysis unit analyzes the participants' reactions to the chat inserted by the chat insertion unit. For example, the generation AI performs analysis based on data on the participants' chat content and reactions. The generation AI analyzes how participants are reacting to the chat and which parts are causing the most questions, and notifies the speaker in real time. Step 3: The question generator automatically generates questions based on the reactions analyzed by the reaction analyzer. For example, the generation AI generates questions based on prompts related to the content of the lecture. When a speaker is explaining a specific topic, the generation AI automatically generates questions related to that topic and inserts them into the chat.

[0052] (Example 2) The AI ​​service according to an embodiment of the present invention is a system that automatically and appropriately inserts chat messages at online or hybrid events such as study groups and lectures, facilitating communication between participants and speakers and creating an environment that is conducive to learning. This enables the AI ​​service to resolve issues such as silence during question-and-answer sessions and a lack of enthusiasm, thereby facilitating communication between participants and speakers.

[0053] An AI service according to an embodiment includes a chat insertion unit, a reaction analysis unit, and a question generation unit. The chat insertion unit automatically inserts chat messages. For example, the generation AI analyzes the progress of a study group or lecture in real time and automatically inserts chat messages at appropriate times. The generation AI generates appropriate chat messages based on prompts related to the progress of the event and the content of the lecture. The reaction analysis unit analyzes participants' reactions to the chat messages inserted by the chat insertion unit. For example, the generation AI performs analysis based on data related to the content and reactions of the participants. The generation AI analyzes how participants are reacting to the chat messages and which parts of the chat messages are causing the most questions, and notifies the speaker in real time. The question generation unit automatically generates questions based on the reactions analyzed by the reaction analysis unit. For example, the generation AI generates questions based on prompts related to the content of the lecture. When a speaker is explaining a specific topic, the generation AI automatically generates questions related to the topic and inserts them into the chat messages. This allows the AI ​​service according to an embodiment to facilitate communication between participants and speakers and create an environment that is conducive to learning.

[0054] The chat insertion unit can analyze the past speech histories of participants and automatically generate personalized chats tailored to individual participants. For example, the chat insertion unit analyzes the past speech histories of participants and automatically generates chats related to a particular topic for participants who are interested in that topic. For example, technology-related questions are inserted for participants who are interested in technology. The chat insertion unit also identifies the interests and concerns of individual participants based on the past speech histories of participants and generates personalized chats tailored to those interests. For example, chats encouraging participants who have asked many questions in the past are inserted. The chat insertion unit also analyzes the past speech histories of participants and automatically generates chats on topics that are likely to interest specific participants. For example, chats related to a particular topic are inserted for participants who have made many comments on that topic in the past. In this way, the interest of participants can be attracted by providing personalized chats tailored to individual participants.

[0055] The chat insertion unit can analyze the speaker's speaking style and tone and automatically adjust the chat style and expressions accordingly. The chat insertion unit, for example, analyzes the speaker's speaking style and tone in real time and adjusts the chat style and expressions based on the results. For example, if the speaker speaks in a casual tone, the chat will also be written in a casual style. The chat insertion unit also analyzes the speaker's speaking style and tone and automatically generates chat that matches the speaker's style. For example, if the speaker uses a lot of technical terminology, the chat will also use technical expressions. The chat insertion unit also analyzes the speaker's tone and generates chat that matches that tone. For example, if the speaker speaks enthusiastically, the chat will also use expressions that convey enthusiasm. This makes it possible to increase the sense of unity in the lecture by providing chat that matches the speaker's speaking style and tone.

[0056] The chat insertion unit can use the emotion estimation function to analyze the emotional state of the speaker in real time and automatically insert chat messages according to the speaker's emotions. For example, the chat insertion unit can use the emotion estimation function to analyze the emotional state of the speaker in real time, and if the speaker is excited, insert chat messages that will engage the participants. For example, it generates chat messages such as, "What do you all think about this point?" The chat insertion unit can also analyze the emotional state of the speaker, and if the speaker is speaking calmly, it inserts chat messages with a calm tone. For example, it generates chat messages such as, "Does anyone have any questions about this part?" The chat insertion unit can also use the emotion estimation function to insert chat messages that empathize with the speaker's emotions when the speaker is emotional. For example, it generates chat messages such as, "This talk was really moving." This makes it possible to adjust the atmosphere of the lecture by providing chat messages according to the speaker's emotions.

[0057] The chat insertion unit can provide the automatic chat insertion function not only as text but also as audio or video messages. For example, the chat insertion unit provides the automatic chat insertion function as audio messages, allowing participants to voice their questions or opinions. For example, after a speaker explains an important point, the audio may say, "Does anyone have any questions about this part?" The chat insertion unit also provides the automatic chat insertion function as video messages, allowing participants to voice their questions or opinions. For example, when a speaker is explaining a particular topic, the video may say, "What do you think about this content?" The chat insertion unit also automatically inserts audio or video messages in addition to text chat, allowing participants to use a variety of communication methods. For example, the speaker may announce the next topic by audio. This provides a variety of communication methods, thereby improving convenience for participants.

[0058] The chat insertion unit can add a function for automatically inserting chat in different languages, making it usable at international events. For example, the chat insertion unit makes the automatic chat insertion function multilingual and automatically generates chat in different languages. For example, chat is inserted in multiple languages, such as English, French, and Chinese. In addition, to accommodate international events, the chat insertion unit translates chat in real time so that participants can receive chat in their own language. For example, if a speaker speaks in English, the chat is automatically translated and inserted. In addition, the chat insertion unit adds a function for automatically inserting chat in different languages, making it possible for international participants to ask questions or express opinions in their own language. For example, if a speaker speaks in Japanese, the chat is translated and inserted into English or Chinese. This makes it possible to accommodate the diversity of participants by making it usable at international events.

[0059] The chat insertion unit can use the emotion estimation function to analyze the emotional state of participants and automatically insert chat that elicits positive emotions. The chat insertion unit, for example, uses the emotion estimation function to analyze the emotional state of participants in real time and insert chat that elicits positive emotions. For example, if a participant is excited, it generates a chat such as, "This story is really interesting!". The chat insertion unit also analyzes the emotional state of participants and inserts chat that elicits positive emotions from participants who are feeling negative emotions. For example, if a participant is bored, it generates a chat such as, "What do you think about this part?" The chat insertion unit also uses the emotion estimation function to analyze the emotional state of participants and automatically generate chat that elicits positive emotions. For example, if a participant is feeling anxious, it generates a chat such as, "Please feel free to ask any questions." This makes it possible to elicit positive emotions and improve participant satisfaction.

[0060] The reaction analysis unit uses generative AI to analyze participants' facial expressions and gestures and provide comprehensive feedback that includes non-verbal reactions. For example, the reaction analysis unit analyzes participants' facial expressions in real time and provides feedback to the speaker. For example, if a participant smiles, it provides feedback such as "The participant is enjoying themselves." The reaction analysis unit also analyzes participants' gestures and notifies the speaker of their non-verbal reactions. For example, if a participant nods, it provides feedback such as "The participant understands." The reaction analysis unit also comprehensively analyzes participants' facial expressions and gestures and provides feedback to the speaker in real time. For example, if a participant looks confused, it provides feedback such as "The participant is having trouble understanding." This allows the speaker to provide comprehensive feedback that includes non-verbal reactions, allowing them to more accurately understand participants' reactions.

[0061] The reaction analysis unit analyzes participant reaction data over time to understand changes in reactions to specific time periods or topics. The reaction analysis unit, for example, analyzes participant reaction data over time to understand changes in reactions during specific time periods. For example, it compares reactions at the start and end of a lecture. The reaction analysis unit also analyzes participant reaction data to understand changes in reactions to specific topics. For example, it compares reactions to technical topics with reactions to marketing topics. The reaction analysis unit also analyzes participant reaction data over time to understand changes in reactions as the lecture progresses. For example, it identifies points during the lecture where participants' interest increases. This makes it possible to understand changes in reactions to specific time periods or topics, thereby optimizing the progress of the lecture.

[0062] The reaction analysis unit can use the emotion estimation function to analyze the emotional state of the participants and provide the speaker with feedback according to changes in their emotions. For example, the reaction analysis unit uses the emotion estimation function to analyze the emotional state of the participants in real time and provide the speaker with feedback according to changes in their emotions. For example, if a participant is excited, the reaction analysis unit provides feedback such as "The participant is excited." The reaction analysis unit also analyzes the emotional state of the participants and provides the speaker with feedback according to changes in their emotions. For example, if a participant is bored, the reaction analysis unit provides feedback such as "The participant is bored." The reaction analysis unit also uses the emotion estimation function to analyze the emotional state of the participants and provide the speaker with feedback according to changes in their emotions. For example, if a participant is feeling anxious, the reaction analysis unit provides feedback such as "The participant is feeling anxious." In this way, by providing feedback according to changes in the participants' emotions, the speaker can more easily understand the emotions of the participants.

[0063] The reaction analysis unit can visualize the participant reaction analysis results in real time and provide a dashboard that the speaker can intuitively understand. The reaction analysis unit, for example, visualizes the participant reaction analysis results in real time and provides a dashboard that the speaker can intuitively understand. For example, it displays the participant's emotion scores in a graph. The reaction analysis unit also visualizes the participant reaction analysis results so that the speaker can intuitively understand. For example, it displays the participant's reactions in a color-coded manner. The reaction analysis unit also updates the participant reaction analysis results in real time and provides a dashboard that the speaker can intuitively understand. For example, it displays the participant's reaction data in real time. In this way, by providing reaction analysis results visualized in real time, the speaker can intuitively grasp the participant's reactions.

[0064] The reaction analysis unit can integrate the reaction analysis results with other event data to provide more detailed insights. For example, the reaction analysis unit integrates the participant reaction analysis results with participant profile data to provide more detailed insights. For example, it analyzes the reactions of participants in specific occupations or age groups. The reaction analysis unit also integrates the participant reaction analysis results with past participation history to understand changes in participant reactions. For example, it compares reactions at past events with reactions at the current event. The reaction analysis unit also integrates the participant reaction analysis results with other event data to provide more detailed insights. For example, it analyzes reactions based on participants' interests and concerns. This allows speakers to gain a deeper understanding of participant reactions by providing detailed insights integrated with other event data.

[0065] The reaction analysis unit can use the emotion estimation function to analyze the emotional reactions of participants and identify topics and approaches that are likely to resonate emotionally. The reaction analysis unit, for example, uses the emotion estimation function to analyze the emotional reactions of participants in real time and identify topics that are likely to resonate emotionally. For example, it identifies topics that excite participants. The reaction analysis unit also analyzes the emotional reactions of participants and identifies approaches that are likely to resonate emotionally. For example, it identifies approaches that move participants. The reaction analysis unit also uses the emotion estimation function to analyze the emotional reactions of participants and identify topics and approaches that are likely to resonate emotionally. For example, it identifies topics that interest participants. In this way, by identifying topics and approaches that are likely to resonate emotionally, the effectiveness of the lecture can be increased.

[0066] The question generation unit can use generation AI to analyze participants' past question history and automatically generate personalized questions tailored to each individual participant. For example, the question generation unit analyzes participants' past question history and automatically generates questions related to that topic for participants who are interested in a particular topic. For example, it generates technology-related questions for participants who are interested in technology. The question generation unit also identifies the interests and concerns of each individual participant based on the participants' past question history and generates personalized questions tailored to those interests. For example, it generates in-depth questions for participants who have asked many questions in the past. The question generation unit also analyzes participants' past question history and automatically generates questions related to topics that are likely to interest a particular participant. For example, it generates questions related to that topic for participants who have asked many questions about a particular topic in the past. In this way, it is possible to pique the participants' interest by providing them with personalized questions tailored to that individual participant.

[0067] The question generation unit can extract keywords and important points from the content of the lecture and automatically generate in-depth questions based on them. The question generation unit, for example, extracts keywords from the content of the lecture and automatically generates in-depth questions based on those keywords. For example, detailed technical questions are generated based on keywords related to technical topics. The question generation unit also extracts important points from the content of the lecture and automatically generates in-depth questions based on those points. For example, questions are generated related to points emphasized by the speaker. The question generation unit also analyzes keywords and important points and automatically generates in-depth questions based on them. For example, questions are generated to help participants deepen their understanding based on the main points of the content of the lecture. This makes it possible to deepen participants' understanding by providing in-depth questions based on the content of the lecture.

[0068] The question generation unit can use the emotion estimation function to analyze the emotional state of the participants and automatically generate questions that are likely to resonate emotionally. The question generation unit, for example, uses the emotion estimation function to analyze the emotional state of the participants in real time and automatically generate questions that are likely to resonate emotionally. For example, if a participant is excited, the question generation unit generates questions that will elicit that excitement. The question generation unit also analyzes the emotional state of the participants and automatically generates questions that are likely to resonate emotionally. For example, if a participant is moved, the question generation unit generates questions that will deepen that emotion. The question generation unit also uses the emotion estimation function to analyze the emotional state of the participants and automatically generate questions that are likely to resonate emotionally. For example, questions related to topics that interest the participants are generated. This makes it possible to attract the interest of the participants by providing questions that are likely to resonate emotionally.

[0069] The question generation unit can provide the automatic question generation function not only as text but also as audio or video messages. For example, the question generation unit provides the automatic question generation function as audio messages, allowing participants to ask questions by audio. For example, after a speaker explains an important point, the audio may say, "Does anyone have any questions about this part?" The question generation unit also provides the automatic question generation function as video messages, allowing participants to ask questions by video. For example, when a speaker is explaining a specific topic, the video may say, "What do you think about this content?" The question generation unit also automatically generates audio and video messages in addition to text questions, allowing participants to use a variety of means to ask questions. For example, the speaker may announce the next topic by audio. This provides a variety of ways to ask questions, thereby improving convenience for participants.

[0070] The question generation unit can add a function for automatically generating questions in different languages, making it usable at international events. For example, the question generation unit makes the automatic question generation function multilingual and automatically generates questions in different languages. For example, questions are generated in multiple languages, such as English, French, and Chinese. In addition, to accommodate international events, the question generation unit translates questions in real time so that participants can receive questions in their own language. For example, if a speaker is speaking in English, the question is automatically translated and inserted. In addition, the question generation unit can add a function for automatically generating questions in different languages, making it possible for international participants to ask questions in their own language. For example, if a speaker is speaking in Japanese, the question is translated into English or Chinese and inserted. This makes it possible to accommodate the diversity of participants by making it usable at international events.

[0071] The question generation unit can use the emotion estimation function to analyze the emotional reactions of participants and automatically generate questions that are likely to resonate emotionally. The question generation unit, for example, uses the emotion estimation function to analyze the emotional reactions of participants in real time and automatically generate questions that are likely to resonate emotionally. For example, if a participant is excited, the question generation unit generates questions that will elicit that excitement. The question generation unit also analyzes the emotional reactions of participants and automatically generates questions that are likely to resonate emotionally. For example, if a participant is moved, the question generation unit generates questions that will deepen that emotion. The question generation unit also uses the emotion estimation function to analyze the emotional reactions of participants and automatically generate questions that are likely to resonate emotionally. For example, questions related to topics that interest participants are generated. This makes it possible to attract the interest of participants by providing questions that are likely to resonate emotionally.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The chat insertion unit can analyze the past speech history of participants and automatically generate personalized chats tailored to each individual participant. For example, by analyzing the past speech history of participants, it can automatically generate chats related to a particular topic for participants who are interested in that topic. For participants who are interested in technology, it can insert technology-related questions. The chat insertion unit can also identify the interests and concerns of individual participants based on the past speech history of participants and generate personalized chats tailored to those interests. For participants who have asked many questions in the past, it can insert chats encouraging them to ask questions. It can also automatically generate chats on topics that are likely to interest specific participants. For participants who have made many comments on a particular topic in the past, it can insert chats related to that topic. In this way, it is possible to attract the participants' interest by providing personalized chats tailored to each individual participant.

[0074] The chat insertion unit can analyze the speaker's speaking style and tone and automatically adjust the chat style and expressions accordingly. For example, it can analyze the speaker's speaking style and tone in real time and adjust the chat style and expressions based on the results. If the speaker speaks in a casual tone, the chat will also be written in a casual style. It can also analyze the speaker's speaking style and tone and automatically generate chat that matches the speaker's style. If the speaker uses a lot of technical terminology, the chat will also use technical expressions. It can also analyze the speaker's tone and generate chat that matches that tone. If the speaker speaks enthusiastically, the chat will also use expressions that convey enthusiasm. This can increase the sense of unity in the lecture by providing chat that matches the speaker's speaking style and tone.

[0075] The chat insertion unit can use the emotion estimation function to analyze the emotional state of the speaker in real time and automatically insert chat messages according to the speaker's emotions. For example, the emotion estimation function can be used to analyze the emotional state of the speaker in real time, and if the speaker is excited, chat messages that will engage the participants can be inserted. For example, chat messages such as "What do you all think about this point?" can be generated. The emotional state of the speaker can also be analyzed, and if the speaker is speaking calmly, chat messages with a calm tone can be inserted. For example, chat messages such as "Does anyone have any questions about this part?" can be generated. Furthermore, if the speaker is emotional, the emotion estimation function can be used to insert chat messages that empathize with the speaker's emotions. For example, chat messages such as "This talk was really moving" can be generated. In this way, the atmosphere of the lecture can be adjusted by providing chat messages according to the speaker's emotions.

[0076] The chat insertion unit can provide the automatic chat insertion function not only as text but also as audio or video messages. For example, the automatic chat insertion function can be provided as an audio message, allowing participants to voice their questions or opinions. After a speaker explains an important point, the audio can say, "Does anyone have any questions about this part?" The chat insertion unit can also provide the automatic chat insertion function as a video message, allowing participants to voice their questions or opinions. When a speaker is explaining a particular topic, the video can say, "What do you think about this content?" Furthermore, by automatically inserting audio or video messages in addition to text chat, participants can be provided with a variety of communication methods. The speaker can announce the next thing they want to say by audio. This can improve convenience for participants by providing a variety of communication methods.

[0077] The chat insertion unit can add a function for automatically inserting chat in different languages, making it usable at international events. For example, the automatic chat insertion function can be made multilingual, automatically generating chat in different languages. Chat can be inserted in multiple languages, such as English, French, and Chinese. Furthermore, to accommodate international events, chat can be translated in real time so that participants can receive chat in their own language. If a speaker speaks in English, the chat can be automatically translated and inserted. Furthermore, a function for automatically inserting chat in different languages ​​can be added, allowing international participants to ask questions or express their opinions in their own language. If a speaker speaks in Japanese, the chat can be translated and inserted into English or Chinese. This makes it possible to accommodate the diversity of participants at international events.

[0078] The chat insertion unit can use the emotion estimation function to analyze the emotional state of participants and automatically insert chat that elicits positive emotions. For example, the emotion estimation function can be used to analyze the emotional state of participants in real time and insert chat that elicits positive emotions. If a participant is excited, a chat such as "This story is really interesting!" can be generated. The emotional state of participants can also be analyzed and chat that elicits positive emotions can be inserted for participants who are feeling negative emotions. If a participant is bored, a chat such as "What do you think about this part?" can be generated. Furthermore, the emotion estimation function can be used to analyze the emotional state of participants and automatically generate chat that elicits positive emotions. If a participant is feeling anxious, a chat such as "Please feel free to ask any questions" can be generated. This can elicit positive emotions and improve participant satisfaction.

[0079] The reaction analysis unit uses generative AI to analyze participants' facial expressions and gestures and provide comprehensive feedback, including non-verbal reactions. For example, it can analyze participants' facial expressions in real time and provide feedback to the speaker. If a participant smiles, it can provide feedback such as "The participant is enjoying themselves." It can also analyze participants' gestures and notify the speaker of their non-verbal reactions. If a participant nods, it can provide feedback such as "The participant understands." It can also comprehensively analyze participants' facial expressions and gestures and provide feedback to the speaker in real time. If a participant looks confused, it can provide feedback such as "The participant is having trouble understanding." This allows the speaker to provide comprehensive feedback, including non-verbal reactions, more accurately grasp the participants' reactions.

[0080] The reaction analysis unit analyzes participant reaction data over time to understand changes in reactions to specific time periods or topics. For example, participant reaction data can be analyzed over time to understand changes in reactions during specific time periods, comparing reactions at the start and end of a lecture. It can also analyze participant reaction data to understand changes in reactions to specific topics, comparing reactions to technical topics with reactions to marketing topics. It can also analyze participant reaction data over time to understand changes in reactions as the lecture progresses, identifying points during the lecture where participant interest increases. This allows it to understand changes in reactions to specific time periods or topics, thereby optimizing the progress of the lecture.

[0081] The reaction analysis unit can use the emotion estimation function to analyze the emotional state of the participants and provide the speaker with feedback according to changes in their emotions. For example, the emotion estimation function can be used to analyze the emotional state of the participants in real time and provide the speaker with feedback according to changes in their emotions. If a participant is excited, feedback such as "The participant is excited" can be provided. The reaction analysis unit can also analyze the emotional state of the participants and provide the speaker with feedback according to changes in their emotions. If a participant is bored, feedback such as "The participant is bored" can be provided. The emotion estimation function can also be used to analyze the emotional state of the participants and provide the speaker with feedback according to changes in their emotions. If a participant is feeling anxious, feedback such as "The participant is feeling anxious" can be provided. In this way, providing feedback according to changes in the participants' emotions makes it easier for the speaker to understand the emotions of the participants.

[0082] The reaction analysis unit can visualize the participant reaction analysis results in real time, providing a dashboard that the speaker can intuitively understand. For example, the participant reaction analysis results can be visualized in real time, providing a dashboard that the speaker can intuitively understand. Participant emotion scores can be displayed in a graph. The participant reaction analysis results can also be visualized, allowing the speaker to intuitively understand. Participant reactions can be displayed in color-coded. Furthermore, the participant reaction analysis results can be updated in real time, providing a dashboard that the speaker can intuitively understand. Participant reaction data is displayed in real time. This allows the speaker to intuitively grasp the participants' reactions by providing reaction analysis results visualized in real time.

[0083] The processing flow of the second embodiment will be briefly explained below.

[0084] Step 1: The chat insertion unit automatically inserts chat. For example, the generation AI analyzes the progress of a study group or lecture in real time and automatically inserts chat at the appropriate time. The generation AI generates appropriate chat based on prompts related to the progress of the event and the content of the lecture. Step 2: The reaction analysis unit analyzes the participants' reactions to the chat inserted by the chat insertion unit. For example, the generation AI performs analysis based on data on the participants' chat content and reactions. The generation AI analyzes how participants are reacting to the chat and which parts are causing the most questions, and notifies the speaker in real time. Step 3: The question generator automatically generates questions based on the reactions analyzed by the reaction analyzer. For example, the generation AI generates questions based on prompts related to the content of the lecture. When a speaker is explaining a specific topic, the generation AI automatically generates questions related to that topic and inserts them into the chat.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] 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.

[0103] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0104] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] 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.

[0118] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0130] 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.

[0131] 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.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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."

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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]

[0152] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A chat insertion section that automatically inserts chats, a reaction analysis unit that analyzes participants' reactions to the chat inserted by the chat insertion unit; a question generation unit that automatically generates a question based on the reaction analyzed by the reaction analysis unit. A system characterized by:

2. The chat insertion unit Analyze the participant's past speech history and automatically generate personalized chats tailored to each individual participant.

2. The system of claim 1.

3. The chat insertion unit Analyzes the speaker's speaking style and tone and automatically adjusts chat style and expressions accordingly 2. The system of claim 1.

4. The chat insertion unit Analyze the speaker's emotional state in real time and automatically insert chat messages according to the speaker's emotions.

2. The system of claim 1.

5. The chat insertion unit The chat auto-insertion feature will be available not only as text, but also as voice and video messages.

2. The system of claim 1.

Images