System

Abstract

An object of a system according to an embodiment is to realize a flexible conversation in an online event.SOLUTION: A system according to an embodiment includes a generation AI, a prompt inputter, and a chat generator. The generation AI generates a chat. The prompt inputter inputs a prompt to the generated AI. The chat generation unit provides a chat generated by the generation AI.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, it was difficult to respond when unexpected communication arose during online events, and participants were less likely to chat.

[0005] The system according to the embodiment aims to realize flexible conversations during online events. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, a prompt input unit, and a chat generation unit. The generation AI generates a chat. The prompt input unit inputs a prompt to the generation AI. The chat generation unit provides the chat generated by the generation AI. [Effects of the Invention]

[0007] The system according to the embodiment can realize ad hoc conversations at online events. [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) An online event support system according to an embodiment of the present invention uses a generation AI to generate chats that participants can use as conversation partners. In this system, if there are few chats from participants during an online event or if a question about an unexpected topic arises, the generation AI automatically generates chats that participants can use as conversation partners. This allows the online event support system to promote dialogue with participants and maintain the excitement of the event.

[0029] An online event assistance system according to an embodiment includes a generation AI, a prompt input unit, and a chat generation unit. The generation AI can use specific models such as GPT-3 and BERT. The prompt input unit inputs prompts to the generation AI. For example, it can input text prompts including instructions regarding the theme and progress of the event. The prompt input unit can also input prompts based on the participant's profile and past participation history. The chat generation unit provides chat generated by the generation AI. For example, it displays text chat generated by the generation AI. The chat generation unit can also provide voice chat generated by the generation AI. This allows the online event assistance system to promote dialogue with participants and maintain excitement at the event.

[0030] The chat generation unit can generate questions or comments related to the theme of the event. For example, the chat generation unit sets character settings according to the theme of the event for the conversation partner generated by the generation AI. For example, a professional character is set for a business event, and a friendly character is set for an entertainment event. The character settings are also detailed so that the conversation partner has a specific backstory or personality. For example, the character may have a specific occupation or hobby to add depth to the conversation. Furthermore, the character's speaking style and language are adjusted according to the theme of the event. For example, polite language is set for a formal event, and friendly language is set for a casual event. This makes it possible to promote dialogue with participants by generating questions and comments related to the theme of the event.

[0031] The chat generation unit can generate chat content that is individually customized based on the participant's profile and past participation history. In the chat generation unit, for example, the generation AI retrieves the participant's past speech history from a database and generates an individually customized conversation based on that information. For example, it asks questions related to topics that the participant has shown interest in in the past. It also analyzes the participant's speech history, extracts specific keywords and phrases, and reflects them in the conversation. For example, it incorporates words that the participant frequently uses into the conversation. Furthermore, the generation AI generates an individually customized conversation scenario based on the participant's past speech history. For example, it follows up on questions that the participant has previously asked. In this way, it is possible to more easily attract the participant's interest by generating chat content that is customized based on the participant's profile and past participation history.

[0032] The chat generation unit can automatically generate conversations in different languages. For example, the chat generation unit may be equipped with a function that allows the generation AI to automatically generate conversations in different languages, making it possible to handle international events. For example, conversations in multiple languages ​​such as English, Japanese, and French may be generated. The generation AI may also automatically detect the language settings of participants and generate conversation content according to that language. For example, if a participant selects English, the conversation will be in English. Furthermore, when generating conversations in different languages, cultural nuances and expressions may be taken into consideration. For example, conversation content that reflects greetings and etiquette in a specific culture may be generated. This makes it possible to handle international events by automatically generating conversations in different languages.

[0033] The chat generation unit can support voice dialogue. For example, the chat generation unit is equipped with a function that allows the generation AI to support voice dialogue, making voice chat possible in addition to text chat. For example, participants can use a microphone to ask questions by voice. Furthermore, speech recognition technology is used to convert the participants' voice input into text, and the generation AI generates appropriate voice responses based on that text. For example, it answers the participants' questions by voice. Furthermore, the generation AI uses speech synthesis technology to achieve natural voice dialogue. For example, the generated conversation content is read aloud using speech synthesis technology. This support for voice dialogue makes it possible to enable voice chat in addition to text chat.

[0034] The generation AI can refer to participants' social media activity history, identify topics of interest, and generate chat content. For example, the generation AI can analyze participants' social media activity history and identify topics of interest. For example, it can generate chat content related to themes that participants frequently post about. It can also extract topics that participants are likely to be interested in based on their social media activity history, and generate questions and comments related to those topics. For example, it can provide information related to accounts that participants follow. Furthermore, the generation AI collects social media data in real time and generates chat content based on participants' latest interests. For example, it can provide topics related to posts that participants recently "liked." This makes it possible to identify topics of interest and generate chat content by referencing participants' social media activity history.

[0035] Generative AI can analyze real-time event data and instantly generate topics that participants will be most interested in. For example, generative AI analyzes real-time event data and identifies topics that participants are likely to be most interested in. For example, it generates chat content related to topics that participants respond to most. It also builds a system that instantly generates topics that will interest participants based on real-time data. For example, it provides information related to topics that participants have many questions about during the event. Furthermore, generative AI monitors the progress of the event and participant responses in real time, and generates topics that will attract attention based on that data. For example, it provides chat content related to topics that participants have many "likes." This makes it possible to instantly generate topics that participants are likely to be most interested in by analyzing real-time event data.

[0036] The generation AI can generate quiz- or game-style chat content to attract participants' attention. For example, the generation AI can generate quiz-style chat content to attract participants' attention. For example, a quiz related to the theme of the event can be posed and participants can answer it. The generation AI can also generate game-style chat content to attract participants' interest. For example, a mini-game can be provided within the chat in which participants can earn points. Furthermore, the generation AI can generate chat content with added interactive elements to encourage active participation by participants. For example, a story-style chat can be provided in which participants select options to progress. In this way, by generating quiz- or game-style chat content, it is possible to attract participants' attention and add interactive elements.

[0037] The generation AI can generate chat content that includes visual content to attract participants' attention. For example, the generation AI generates chat content that includes visual content to attract participants' attention. For example, images and videos related to the theme of the event are shared within the chat. The generation AI can also generate chat content using images and videos to attract participants' attention. For example, related visual content can be provided as the event progresses. Furthermore, the generation AI can generate chat content that utilizes visual content to attract participants' visual interest. For example, chat content using infographics and animations can be provided. In this way, generating chat content that includes visual content makes it easier to attract participants' visual interest.

[0038] Generative AI can learn from past event data and improve the accuracy of answers to unexpected questions. Generative AI can, for example, learn from past event data and improve the accuracy of answers to unexpected questions. For example, it can store past questions and their answers in a database and generate appropriate answers to similar questions. It can also analyze past event data and extract patterns for unexpected questions. For example, it can understand trends in frequently asked questions and generate answers based on those patterns. Furthermore, generative AI can increase the variety of answers to unexpected questions based on past event data. For example, it can generate multiple answers from different perspectives and select the most appropriate answer. In this way, by learning from past event data, it can improve the accuracy of answers to unexpected questions.

[0039] Generative AI can refer to the knowledge base of experts to enable it to respond to specialized questions. Generative AI can, for example, refer to the knowledge base of experts to enable it to respond to specialized questions. For example, it can utilize a database with specialized knowledge in a specific field. Furthermore, based on the expert knowledge base, generative AI can generate answers to specialized questions. For example, it can provide appropriate answers to questions related to specialized fields such as medicine or law. Furthermore, generative AI can refer to the expert knowledge base in real time to generate answers based on the latest information. For example, it can provide answers based on the latest research results or legal amendments. This makes it possible to respond to specialized questions by referring to the expert knowledge base.

[0040] Generative AI can automatically provide relevant materials and links in response to unexpected questions. For example, generative AI can share links to websites or papers related to the question in the chat. Based on the content of the question, generative AI can also search a database for relevant materials and provide links to those materials. For example, it can provide detailed information on a specific topic. Furthermore, generative AI can provide links to relevant videos or presentation materials in response to unexpected questions. For example, it can share materials that include visual explanations of the question. This allows participants' questions to be quickly resolved by automatically providing relevant materials and links in response to unexpected questions.

[0041] The generative AI can provide a voting function to solicit opinions from other participants on unexpected questions. For example, the generative AI can provide a voting function to solicit opinions from other participants on unexpected questions. For example, it can present multiple answers to a question and ask participants to choose the best answer. It can also use the voting function to collect participants' opinions on the unexpected question and generate an answer based on the results. For example, it can provide an answer that reflects the majority opinion of participants. Furthermore, the generative AI can use the voting function to collect participants' opinions on the unexpected question in real time. For example, it can tally up opinions for and against the question and generate an answer based on the results. In this way, by providing a voting function to solicit opinions from other participants on unexpected questions, it is possible to obtain answers from diverse perspectives.

[0042] The generation AI can monitor the progress of an event in real time and automatically update the chat content in line with the progress. For example, the generation AI can monitor the progress of an event in real time and automatically update the chat content based on that data. For example, it can generate a welcome message at the start of the event and change the content as the event progresses. The generation AI can also analyze the progress of the event in real time and update the chat content at the appropriate time. For example, it can provide information about the next session at the end of a session. Furthermore, the generation AI can generate chat content that will attract participants' attention as the event progresses. For example, it can provide event highlights and important points in real time. This makes it possible to smoothly support the progress of the event by monitoring the progress of the event in real time and automatically updating the chat content in line with the progress.

[0043] The generation AI can generate reminders and notifications to attract participants' attention as the event progresses. For example, the generation AI generates reminders to attract participants' attention as the event progresses. For example, it sends reminder messages before a session starts. The generation AI also generates important notifications for participants based on the progress of the event. For example, it notifies participants of session changes and important announcements in real time. Furthermore, the generation AI customizes reminders and notifications to attract participants' attention as the event progresses. For example, it provides personalized notifications based on participants' interests. This makes it possible to maintain participants' interest by generating reminders and notifications to attract participants' attention as the event progresses.

[0044] The generation AI can generate chat content that includes visual content in line with the progress of the event. For example, the generation AI generates chat content that includes visual content in line with the progress of the event. For example, presentation slides and videos can be shared within the chat. The generation AI also provides visual content at appropriate times based on the progress of the event. For example, it can introduce session highlights in a video. Furthermore, the generation AI generates visual content that attracts the attention of participants in line with the progress of the event. For example, it can provide chat content that uses infographics and animations. In this way, by generating chat content that includes visual content in line with the progress of the event, it is possible to more easily attract the visual interest of participants.

[0045] Generative AI can collect participant opinions in real time as the event progresses and reflect them in the progress. Generative AI, for example, builds a system that collects participant opinions in real time as the event progresses. For example, it conducts surveys and polls within chat. It also collects participant opinions in real time and adjusts the progress of the event based on the results. For example, it changes the content of sessions based on participant opinions. Furthermore, generative AI generates chat content that reflects participant opinions as the event progresses. For example, it decides the theme of the next session based on participant feedback. This allows participant opinions to be collected in real time as the event progresses and reflected in the progress, making it possible to run a flexible event that reflects participant opinions.

[0046] The generation AI can analyze participant feedback in real time and generate chat content that instantly reflects it. For example, the generation AI can analyze participant feedback in real time and instantly generate chat content based on the results. For example, if a participant shows interest in a particular topic, it can provide information related to that topic. In addition, a system can be built in which the generation AI updates chat content in real time based on participant feedback. For example, it can change the chat theme based on participant opinions. Furthermore, the generation AI can analyze participant feedback in real time and generate customized chat content based on the results. For example, it can provide information that meets participant requests. In this way, participants' feedback can be analyzed in real time and chat content that instantly reflects it can be generated, thereby maintaining their interest.

[0047] The generative AI can generate proposals to flexibly change the progress and content of an event based on participant feedback. The generative AI, for example, generates proposals to flexibly change the progress and content of an event based on participant feedback. For example, it changes the order of sessions based on participant opinions. It also analyzes participant feedback in real time and generates proposals to adjust the progress of the event based on the results. For example, it proposes additional sessions on topics that participants showed interest in. The generative AI also generates proposals to flexibly change the content of an event based on participant feedback. For example, it adds new topics in response to participant requests. This makes it possible to run an event in accordance with participant requests by generating proposals to flexibly change the progress and content of an event based on participant feedback.

[0048] Generative AI can propose the content and format of the next event based on participant feedback. Generative AI can, for example, propose the content and format of the next event based on participant feedback. For example, it can incorporate topics that participants showed interest in into the next event. It can also analyze participant feedback and propose the format of the next event based on the results. For example, it can introduce a workshop format in response to participant requests. Furthermore, generative AI can generate suggestions to customize the content of the next event based on participant feedback. For example, it can invite speakers requested by participants. This makes it possible to plan events that meet participant requests by proposing the content and format of the next event based on participant feedback.

[0049] The generation AI can generate follow-up messages after the event ends based on participant feedback. For example, the generation AI generates follow-up messages after the event ends based on participant feedback. For example, it provides additional information on topics that participants showed interest in. It also analyzes participant feedback and customizes follow-up messages based on the results. For example, it provides materials or links that participants request. Furthermore, the generation AI generates follow-up messages based on participant feedback, including thank-you messages and information about the next event. For example, it provides information that participants requested. In this way, it is possible to continue attracting participants' interest by generating follow-up messages after the event ends based on participant feedback.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The online event support system can further include a health management unit that monitors the health of participants. For example, it can send messages encouraging participants to stretch and take breaks periodically to prevent them from sitting for long periods of time. It can also monitor participants' heart rates and stress levels and provide advice on how to relax as needed. Furthermore, the health management unit can analyze participants' health data and provide individually customized health advice. For example, it can provide advice to support healthy lifestyle habits based on participants' exercise history and food records.

[0052] The online event support system may further include a networking unit that supports networking among participants. For example, the system may automatically match participants with other participants who share common interests based on their profiles and interests. The networking unit may also provide chat room and video call functions so that participants can easily stay in touch with each other. Furthermore, the networking unit may provide a follow-up function to maintain connections between participants even after the event has ended. For example, the networking unit may send reminders for participants to reconnect after the event.

[0053] The online event support system can further include a learning support unit that supports participants' learning. For example, it can automatically organize materials and presentations provided during the event so that participants can easily access them later. The learning support unit can also monitor participants' learning progress and provide additional learning resources as needed. Furthermore, the learning support unit can provide customized learning plans based on participants' learning styles. For example, it can provide infographics and videos for visual learners and detailed text materials for text learners.

[0054] The online event support system may further include a feedback collection unit that collects participant feedback in real time and immediately reflects it. For example, it may provide a survey or voting function that allows participants to provide feedback in real time during the event. The feedback collection unit may also analyze participant feedback and adjust the progress of the event based on the results. Furthermore, the feedback collection unit may suggest content and format for the next event based on participant feedback. For example, it may incorporate topics that participants have shown interest in into the next event.

[0055] The online event support system may further include a schedule management unit that supports participant schedule management. For example, the schedule management unit may send reminders to participants so that they can join each session of the event on time. The schedule management unit may also provide reminders customized to each participant's individual schedule. For example, if a participant plans to attend a specific session, the schedule management unit may send a reminder before the session starts. Furthermore, the schedule management unit may update participants' schedules in real time and immediately notify them of any changes. For example, if the time of a session is changed, the schedule management unit may promptly notify participants of that information.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: Generative AI generates chats based on prompts using specific models such as GPT-3 or BERT. Step 2: The prompt input unit inputs prompts to the generation AI, such as text prompts containing instructions about the event theme and progress, or prompts based on the participant's profile and past participation history. Step 3: The chat generation unit provides the chat generated by the generation AI, for example, by displaying the text chat generated by the generation AI or by providing the voice chat generated by the generation AI.

[0058] (Example 2) An online event support system according to an embodiment of the present invention uses a generation AI to generate chats that participants can use as conversation partners. In this system, if there are few chats from participants during an online event or if a question about an unexpected topic arises, the generation AI automatically generates chats that participants can use as conversation partners. This allows the online event support system to promote dialogue with participants and maintain the excitement of the event.

[0059] An online event assistance system according to an embodiment includes a generation AI, a prompt input unit, and a chat generation unit. The generation AI can use specific models such as GPT-3 and BERT. The prompt input unit inputs prompts to the generation AI. For example, it can input text prompts including instructions regarding the theme and progress of the event. The prompt input unit can also input prompts based on the participant's profile and past participation history. The chat generation unit provides chat generated by the generation AI. For example, it displays text chat generated by the generation AI. The chat generation unit can also provide voice chat generated by the generation AI. This allows the online event assistance system to promote dialogue with participants and maintain excitement at the event.

[0060] The chat generation unit can generate questions or comments related to the theme of the event. For example, the chat generation unit sets character settings according to the theme of the event for the conversation partner generated by the generation AI. For example, a professional character is set for a business event, and a friendly character is set for an entertainment event. The character settings are also detailed so that the conversation partner has a specific backstory or personality. For example, the character may have a specific occupation or hobby to add depth to the conversation. Furthermore, the character's speaking style and language are adjusted according to the theme of the event. For example, polite language is set for a formal event, and friendly language is set for a casual event. This makes it possible to promote dialogue with participants by generating questions and comments related to the theme of the event.

[0061] The chat generation unit can generate chat content that is individually customized based on the participant's profile and past participation history. In the chat generation unit, for example, the generation AI retrieves the participant's past speech history from a database and generates an individually customized conversation based on that information. For example, it asks questions related to topics that the participant has shown interest in in the past. It also analyzes the participant's speech history, extracts specific keywords and phrases, and reflects them in the conversation. For example, it incorporates words that the participant frequently uses into the conversation. Furthermore, the generation AI generates an individually customized conversation scenario based on the participant's past speech history. For example, it follows up on questions that the participant has previously asked. In this way, it is possible to more easily attract the participant's interest by generating chat content that is customized based on the participant's profile and past participation history.

[0062] The chat generation unit can generate conversation content according to the emotional state of the participants. For example, the chat generation unit uses an emotion estimation function to analyze the emotional state of the participants in real time and adjust the conversation content based on the results. For example, if a participant is nervous, the unit will engage in conversation that will relax them. The generation AI also analyzes the emotional state of the participants and generates conversation content that will elicit positive emotions. For example, it will use words of praise and encouragement that will make the participant feel happy. Furthermore, the emotion estimation function is used to generate a conversation scenario according to the emotional state of the participants. For example, if a participant is sad, it will use words of comfort. In this way, by generating conversation content according to the emotional state of the participants, it is possible to realize a dialogue that is sensitive to the participants' emotions.

[0063] The chat generation unit can automatically generate conversations in different languages. For example, the chat generation unit may be equipped with a function that allows the generation AI to automatically generate conversations in different languages, making it possible to handle international events. For example, conversations in multiple languages ​​such as English, Japanese, and French may be generated. The generation AI may also automatically detect the language settings of participants and generate conversation content according to that language. For example, if a participant selects English, the conversation will be in English. Furthermore, when generating conversations in different languages, cultural nuances and expressions may be taken into consideration. For example, conversation content that reflects greetings and etiquette in a specific culture may be generated. This makes it possible to handle international events by automatically generating conversations in different languages.

[0064] The chat generation unit can support voice dialogue. For example, the chat generation unit is equipped with a function that allows the generation AI to support voice dialogue, making voice chat possible in addition to text chat. For example, participants can use a microphone to ask questions by voice. Furthermore, speech recognition technology is used to convert the participants' voice input into text, and the generation AI generates appropriate voice responses based on that text. For example, it answers the participants' questions by voice. Furthermore, the generation AI uses speech synthesis technology to achieve natural voice dialogue. For example, the generated conversation content is read aloud using speech synthesis technology. This support for voice dialogue makes it possible to enable voice chat in addition to text chat.

[0065] The chat generation unit can change the voice tone or speaking style according to the emotional state of the participants. The chat generation unit, for example, uses an emotion estimation function to adjust the voice tone and speaking style according to the emotional state of the participants. For example, if a participant is excited, it will speak in a calm tone. The generation AI also analyzes the emotional state of the participants and changes the voice tone and speaking style based on the results. For example, if a participant is sad, it will speak in a gentle tone. Furthermore, the emotion estimation function is used to realize voice dialogue that is in tune with the emotions of the participants. For example, if a participant is happy, it will speak in a bright tone. This makes it possible to realize a more natural dialogue by changing the voice tone and speaking style according to the emotional state of the participants.

[0066] The generation AI can refer to participants' social media activity history, identify topics of interest, and generate chat content. For example, the generation AI can analyze participants' social media activity history and identify topics of interest. For example, it can generate chat content related to themes that participants frequently post about. It can also extract topics that participants are likely to be interested in based on their social media activity history, and generate questions and comments related to those topics. For example, it can provide information related to accounts that participants follow. Furthermore, the generation AI collects social media data in real time and generates chat content based on participants' latest interests. For example, it can provide topics related to posts that participants recently "liked." This makes it possible to identify topics of interest and generate chat content by referencing participants' social media activity history.

[0067] Generative AI can analyze real-time event data and instantly generate topics that participants will be most interested in. For example, generative AI analyzes real-time event data and identifies topics that participants are likely to be most interested in. For example, it generates chat content related to topics that participants respond to most. It also builds a system that instantly generates topics that will interest participants based on real-time data. For example, it provides information related to topics that participants have many questions about during the event. Furthermore, generative AI monitors the progress of the event and participant responses in real time, and generates topics that will attract attention based on that data. For example, it provides chat content related to topics that participants have many "likes." This makes it possible to instantly generate topics that participants are likely to be most interested in by analyzing real-time event data.

[0068] The generation AI can use the emotion estimation function to emotionally analyze topics that interest participants and generate chat content that will elicit a positive response. For example, the generation AI can use the emotion estimation function to emotionally analyze topics that interest participants and generate chat content that will elicit a positive response. For example, it can provide topics that will make participants feel happy. The generation AI can also analyze the emotional state of participants and, based on the results, identify topics that will elicit a positive response. For example, it can provide news or information that will excite participants. Furthermore, it can use the emotion estimation function to generate chat content that is in line with the emotions of participants. For example, it can provide stories or episodes that will move participants. In this way, the emotion estimation function can emotionally analyze topics that interest participants and generate chat content that will elicit a positive response.

[0069] The generation AI can generate quiz- or game-style chat content to attract participants' attention. For example, the generation AI can generate quiz-style chat content to attract participants' attention. For example, a quiz related to the theme of the event can be posed and participants can answer it. The generation AI can also generate game-style chat content to attract participants' interest. For example, a mini-game can be provided within the chat in which participants can earn points. Furthermore, the generation AI can generate chat content with added interactive elements to encourage active participation by participants. For example, a story-style chat can be provided in which participants select options to progress. In this way, by generating quiz- or game-style chat content, it is possible to attract participants' attention and add interactive elements.

[0070] The generation AI can generate chat content that includes visual content to attract participants' attention. For example, the generation AI generates chat content that includes visual content to attract participants' attention. For example, images and videos related to the theme of the event are shared within the chat. The generation AI can also generate chat content using images and videos to attract participants' attention. For example, related visual content can be provided as the event progresses. Furthermore, the generation AI can generate chat content that utilizes visual content to attract participants' visual interest. For example, chat content using infographics and animations can be provided. In this way, generating chat content that includes visual content makes it easier to attract participants' visual interest.

[0071] The generation AI can use the emotion estimation function to incorporate stories that participants can easily empathize with emotionally into the chat content in order to attract the interest of participants. For example, the generation AI uses the emotion estimation function to incorporate stories that participants can easily empathize with emotionally into the chat content. For example, by sharing moving episodes or success stories. The generation AI can also analyze the emotional state of participants and generate stories that participants can easily empathize with based on the results. For example, by providing stories that will move participants. Furthermore, the emotion estimation function can be used to incorporate stories that are in line with the emotions of participants into the chat content. For example, by setting themes and characters that participants can easily empathize with. In this way, the emotion estimation function can be used to incorporate stories that participants can easily empathize with emotionally into the chat content.

[0072] Generative AI can learn from past event data and improve the accuracy of answers to unexpected questions. Generative AI can, for example, learn from past event data and improve the accuracy of answers to unexpected questions. For example, it can store past questions and their answers in a database and generate appropriate answers to similar questions. It can also analyze past event data and extract patterns for unexpected questions. For example, it can understand trends in frequently asked questions and generate answers based on those patterns. Furthermore, generative AI can increase the variety of answers to unexpected questions based on past event data. For example, it can generate multiple answers from different perspectives and select the most appropriate answer. In this way, by learning from past event data, it can improve the accuracy of answers to unexpected questions.

[0073] Generative AI can refer to the knowledge base of experts to enable it to respond to specialized questions. Generative AI can, for example, refer to the knowledge base of experts to enable it to respond to specialized questions. For example, it can utilize a database with specialized knowledge in a specific field. Furthermore, based on the expert knowledge base, generative AI can generate answers to specialized questions. For example, it can provide appropriate answers to questions related to specialized fields such as medicine or law. Furthermore, generative AI can refer to the expert knowledge base in real time to generate answers based on the latest information. For example, it can provide answers based on the latest research results or legal amendments. This makes it possible to respond to specialized questions by referring to the expert knowledge base.

[0074] The generation AI can use the emotion estimation function to analyze the impact that answers to unexpected questions have on participants' emotions and generate the optimal answer. For example, the generation AI can use the emotion estimation function to analyze the impact that answers to unexpected questions have on participants' emotions. For example, it can take care not to make participants feel anxious by providing answers that do not make them feel anxious. The generation AI can also analyze the emotional state of participants and generate the optimal answer based on the results. For example, it can provide an answer that makes participants feel reassured. Furthermore, it can use the emotion estimation function to adjust the tone and expression of answers to unexpected questions. For example, it can generate answers that make participants feel positive. In this way, the emotion estimation function can analyze the impact that answers to unexpected questions have on participants' emotions and generate the optimal answer.

[0075] Generative AI can automatically provide relevant materials and links in response to unexpected questions. For example, generative AI can share links to websites or papers related to the question in the chat. Based on the content of the question, generative AI can also search a database for relevant materials and provide links to those materials. For example, it can provide detailed information on a specific topic. Furthermore, generative AI can provide links to relevant videos or presentation materials in response to unexpected questions. For example, it can share materials that include visual explanations of the question. This allows participants' questions to be quickly resolved by automatically providing relevant materials and links in response to unexpected questions.

[0076] The generative AI can provide a voting function to solicit opinions from other participants on unexpected questions. For example, the generative AI can provide a voting function to solicit opinions from other participants on unexpected questions. For example, it can present multiple answers to a question and ask participants to choose the best answer. It can also use the voting function to collect participants' opinions on the unexpected question and generate an answer based on the results. For example, it can provide an answer that reflects the majority opinion of participants. Furthermore, the generative AI can use the voting function to collect participants' opinions on the unexpected question in real time. For example, it can tally up opinions for and against the question and generate an answer based on the results. In this way, by providing a voting function to solicit opinions from other participants on unexpected questions, it is possible to obtain answers from diverse perspectives.

[0077] The generation AI can use the emotion estimation function to adjust the tone and expression of answers to unexpected questions so that they are more likely to evoke emotional empathy. For example, the generation AI uses the emotion estimation function to adjust the tone and expression of answers to unexpected questions. For example, it may provide an answer in a gentle tone so that participants can easily empathize. The generation AI can also analyze the emotional state of participants and adjust the tone and expression of answers based on the results. For example, it may use expressions that make participants feel at ease. Furthermore, the emotion estimation function can be used to devise ways to make answers to unexpected questions more likely to evoke emotional empathy. For example, it may generate answers that evoke positive emotions in participants. In this way, the emotion estimation function can be used to adjust the tone and expression of answers to unexpected questions so that they are more likely to evoke emotional empathy.

[0078] The generation AI can monitor the progress of an event in real time and automatically update the chat content in line with the progress. For example, the generation AI can monitor the progress of an event in real time and automatically update the chat content based on that data. For example, it can generate a welcome message at the start of the event and change the content as the event progresses. The generation AI can also analyze the progress of the event in real time and update the chat content at the appropriate time. For example, it can provide information about the next session at the end of a session. Furthermore, the generation AI can generate chat content that will attract participants' attention as the event progresses. For example, it can provide event highlights and important points in real time. This makes it possible to smoothly support the progress of the event by monitoring the progress of the event in real time and automatically updating the chat content in line with the progress.

[0079] The generation AI can generate reminders and notifications to attract participants' attention as the event progresses. For example, the generation AI generates reminders to attract participants' attention as the event progresses. For example, it sends reminder messages before a session starts. The generation AI also generates important notifications for participants based on the progress of the event. For example, it notifies participants of session changes and important announcements in real time. Furthermore, the generation AI customizes reminders and notifications to attract participants' attention as the event progresses. For example, it provides personalized notifications based on participants' interests. This makes it possible to maintain participants' interest by generating reminders and notifications to attract participants' attention as the event progresses.

[0080] The generation AI uses the emotion estimation function to analyze the impact that chat content that matches the progress of the event has on participants' emotions, and can generate chat messages at the optimal timing. For example, the generation AI uses the emotion estimation function to analyze the impact that chat content that matches the progress of the event has on participants' emotions. For example, it provides positive messages when participants are excited. The generation AI also analyzes the emotional state of participants in real time and generates chat messages at the optimal timing based on the results. For example, it provides important information when participants are relaxed. Furthermore, the emotion estimation function is used to consider the impact that chat content that matches the progress of the event has on participants' emotions, and generate chat messages at the optimal timing. For example, it provides reminders when participants are concentrating. In this way, the emotion estimation function can be used to analyze the impact that chat content that matches the progress of the event has on participants' emotions, and generate chat messages at the optimal timing.

[0081] The generation AI can generate chat content that includes visual content in line with the progress of the event. For example, the generation AI generates chat content that includes visual content in line with the progress of the event. For example, presentation slides and videos can be shared within the chat. The generation AI also provides visual content at appropriate times based on the progress of the event. For example, it can introduce session highlights in a video. Furthermore, the generation AI generates visual content that attracts the attention of participants in line with the progress of the event. For example, it can provide chat content that uses infographics and animations. In this way, by generating chat content that includes visual content in line with the progress of the event, it is possible to more easily attract the visual interest of participants.

[0082] Generative AI can collect participant opinions in real time as the event progresses and reflect them in the progress. Generative AI, for example, builds a system that collects participant opinions in real time as the event progresses. For example, it conducts surveys and polls within chat. It also collects participant opinions in real time and adjusts the progress of the event based on the results. For example, it changes the content of sessions based on participant opinions. Furthermore, generative AI generates chat content that reflects participant opinions as the event progresses. For example, it decides the theme of the next session based on participant feedback. This allows participant opinions to be collected in real time as the event progresses and reflected in the progress, making it possible to run a flexible event that reflects participant opinions.

[0083] The generation AI can use the emotion estimation function to adjust the expression and tone of the chat content as the event progresses so that it is easy to empathize emotionally. For example, the generation AI uses the emotion estimation function to adjust the expression and tone of the chat content as the event progresses so that it is easy to empathize emotionally. For example, it uses expressions that will move participants. The generation AI also analyzes the emotional state of the participants and adjusts the expression and tone of the chat content based on the results. For example, it provides messages in a tone that makes participants feel relaxed. Furthermore, the emotion estimation function is used to devise ways to make the chat content as the event progresses so that it is easy to empathize emotionally. For example, it uses expressions that will make participants feel positive emotions. In this way, the emotion estimation function can be used to adjust the expression and tone of the chat content as the event progresses so that it is easy to empathize emotionally.

[0084] The generation AI can analyze participant feedback in real time and generate chat content that instantly reflects it. For example, the generation AI can analyze participant feedback in real time and instantly generate chat content based on the results. For example, if a participant shows interest in a particular topic, it can provide information related to that topic. In addition, a system can be built in which the generation AI updates chat content in real time based on participant feedback. For example, it can change the chat theme based on participant opinions. Furthermore, the generation AI can analyze participant feedback in real time and generate customized chat content based on the results. For example, it can provide information that meets participant requests. In this way, participants' feedback can be analyzed in real time and chat content that instantly reflects it can be generated, thereby maintaining their interest.

[0085] The generative AI can generate proposals to flexibly change the progress and content of an event based on participant feedback. The generative AI, for example, generates proposals to flexibly change the progress and content of an event based on participant feedback. For example, it changes the order of sessions based on participant opinions. It also analyzes participant feedback in real time and generates proposals to adjust the progress of the event based on the results. For example, it proposes additional sessions on topics that participants showed interest in. The generative AI also generates proposals to flexibly change the content of an event based on participant feedback. For example, it adds new topics in response to participant requests. This makes it possible to run an event in accordance with participant requests by generating proposals to flexibly change the progress and content of an event based on participant feedback.

[0086] The generation AI can use the emotion estimation function to adjust the chat content so that participants' feedback has a positive emotional impact. For example, the generation AI uses the emotion estimation function to adjust the chat content so that participants' feedback has a positive emotional impact. For example, it reflects feedback that makes participants feel happy. The generation AI also analyzes the emotional state of participants and adjusts the feedback content based on the results. For example, it provides feedback that makes participants feel reassured. Furthermore, the emotion estimation function is used to devise ways to ensure that participants' feedback has a positive emotional impact. For example, it reflects feedback that makes participants feel moved. In this way, by using the emotion estimation function, the chat content can be adjusted so that participants' feedback has a positive emotional impact.

[0087] Generative AI can propose the content and format of the next event based on participant feedback. Generative AI can, for example, propose the content and format of the next event based on participant feedback. For example, it can incorporate topics that participants showed interest in into the next event. It can also analyze participant feedback and propose the format of the next event based on the results. For example, it can introduce a workshop format in response to participant requests. Furthermore, generative AI can generate suggestions to customize the content of the next event based on participant feedback. For example, it can invite speakers requested by participants. This makes it possible to plan events that meet participant requests by proposing the content and format of the next event based on participant feedback.

[0088] The generation AI can generate follow-up messages after the event ends based on participant feedback. For example, the generation AI generates follow-up messages after the event ends based on participant feedback. For example, it provides additional information on topics that participants showed interest in. It also analyzes participant feedback and customizes follow-up messages based on the results. For example, it provides materials or links that participants request. Furthermore, the generation AI generates follow-up messages based on participant feedback, including thank-you messages and information about the next event. For example, it provides information that participants requested. In this way, it is possible to continue attracting participants' interest by generating follow-up messages after the event ends based on participant feedback.

[0089] The generation AI can use the emotion estimation function to reflect the feedback content in the chat so that participants' feedback is more likely to be emotionally empathetic. The generation AI, for example, uses the emotion estimation function to reflect the feedback content in the chat so that participants' feedback is more likely to be emotionally empathetic. For example, it provides feedback that moves participants. The generation AI also analyzes the emotional state of participants and adjusts the feedback content based on the results. For example, it provides feedback that makes participants feel reassured. Furthermore, it uses the emotion estimation function to devise ways to make participants' feedback more likely to be emotionally empathetic. For example, it reflects feedback that makes participants feel happy. In this way, by using the emotion estimation function, the feedback content can be reflected in the chat so that participants' feedback is more likely to be emotionally empathetic.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The online event support system can further include a health management unit that monitors the health of participants. For example, it can send messages encouraging participants to stretch and take breaks periodically to prevent them from sitting for long periods of time. It can also monitor participants' heart rates and stress levels and provide advice on how to relax as needed. Furthermore, the health management unit can analyze participants' health data and provide individually customized health advice. For example, it can provide advice to support healthy lifestyle habits based on participants' exercise history and food records.

[0092] The online event support system may further include a networking unit that supports networking among participants. For example, the system may automatically match participants with other participants who share common interests based on their profiles and interests. The networking unit may also provide chat room and video call functions so that participants can easily stay in touch with each other. Furthermore, the networking unit may provide a follow-up function to maintain connections between participants even after the event has ended. For example, the networking unit may send reminders for participants to reconnect after the event.

[0093] The online event support system can further include a learning support unit that supports participants' learning. For example, it can automatically organize materials and presentations provided during the event so that participants can easily access them later. The learning support unit can also monitor participants' learning progress and provide additional learning resources as needed. Furthermore, the learning support unit can provide customized learning plans based on participants' learning styles. For example, it can provide infographics and videos for visual learners and detailed text materials for text learners.

[0094] The online event support system may further include a feedback collection unit that collects participant feedback in real time and immediately reflects it. For example, it may provide a survey or voting function that allows participants to provide feedback in real time during the event. The feedback collection unit may also analyze participant feedback and adjust the progress of the event based on the results. Furthermore, the feedback collection unit may suggest content and format for the next event based on participant feedback. For example, it may incorporate topics that participants have shown interest in into the next event.

[0095] The online event support system may further include a music providing unit that provides music according to the emotional state of the participants. For example, music that helps participants relax may be provided. Furthermore, an emotion estimation function may be used to select music according to the emotional state of the participants. For example, relaxing music may be provided if the participants are nervous, and calming music may be provided if the participants are excited. Furthermore, the music providing unit may change the music as the event progresses. For example, energetic music may be provided at the beginning of a session, and relaxing music may be provided at the end.

[0096] The online event support system can further include a visual provision unit that provides visual content according to the emotional state of the participants. For example, it provides scenery images or animations that help participants relax. It can also use an emotion estimation function to select visual content according to the emotional state of the participants. For example, it can provide relaxing scenery images if the participants are nervous, and calming animations if the participants are excited. Furthermore, the visual provision unit can change the visual content as the event progresses. For example, it can provide energetic visuals at the start of a session and relaxing visuals at the end.

[0097] The online event support system may further include an avatar providing unit that provides an avatar according to the emotional state of a participant. For example, an avatar that makes the participant feel relaxed may be provided. An emotion estimation function may also be used to select an avatar according to the emotional state of a participant. For example, if a participant is nervous, a relaxed avatar may be provided, and if the participant is excited, a calm avatar may be provided. Furthermore, the avatar providing unit may change the avatar as the event progresses. For example, an energetic avatar may be provided at the start of a session, and a relaxed avatar may be provided at the end.

[0098] The online event support system may further include a message providing unit that provides messages according to the emotional state of the participants. For example, a message that helps participants relax may be provided. A message according to the emotional state of the participants may also be selected using an emotion estimation function. For example, a relaxing message may be provided if the participants are nervous, and a calming message may be provided if the participants are excited. Furthermore, the message providing unit may change the message as the event progresses. For example, an energetic message may be provided at the start of a session and a relaxing message may be provided at the end.

[0099] The online event support system may further include an exercise provider that provides exercises according to the emotional state of the participants. For example, it may provide stretching or yoga exercises that help participants relax. It may also use an emotion estimation function to select exercises according to the emotional state of the participants. For example, it may provide relaxing stretching exercises if the participants are nervous, or calming yoga exercises if the participants are excited. Furthermore, the exercise provider may change exercises as the event progresses. For example, it may provide energetic exercises at the beginning of a session and relaxing exercises at the end.

[0100] The online event support system may further include a schedule management unit that supports participant schedule management. For example, the schedule management unit may send reminders to participants so that they can join each session of the event on time. The schedule management unit may also provide reminders customized to each participant's individual schedule. For example, if a participant plans to attend a specific session, the schedule management unit may send a reminder before the session starts. Furthermore, the schedule management unit may update participants' schedules in real time and immediately notify them of any changes. For example, if the time of a session is changed, the schedule management unit may promptly notify participants of that information.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: Generative AI generates chats based on prompts using specific models such as GPT-3 or BERT. Step 2: The prompt input unit inputs prompts to the generation AI, such as text prompts containing instructions about the event theme and progress, or prompts based on the participant's profile and past participation history. Step 3: The chat generation unit provides the chat generated by the generation AI, for example, by displaying the text chat generated by the generation AI or by providing the voice chat generated by the generation AI.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The 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.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 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.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the 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.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The 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.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 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. Generative AI and a prompt input unit for inputting a prompt to the generation AI; a chat generation unit that provides chats generated by the generation AI; A system characterized by:

2. The chat generation unit Generate questions or comments related to the theme of the event 2. The system of claim 1.

3. The chat generation unit Generate personalized chat content based on participants' profiles and past participation history 2. The system of claim 1.

4. The chat generation unit Generate conversation content according to participants' emotional states 2. The system of claim 1.

5. The chat generation unit Automatically generating conversations in the different languages 2. The system of claim 1.

6. The chat generation unit Supporting voice interaction 2. The system of claim 1.

Images