System

Abstract

An object of the system according to the embodiment is to provide effective education and support to a user who does not want to use a generation AI.SOLUTION: The system according to the embodiment includes an explanation part, an introduction part, a hands-on session part, and a question-and-answer part. The explanation part explains the basic usage of the generated AI. The introduction unit introduces an application using the generated AI based on the content described by the description unit. The hands-on session unit uses the application introduced by the introduction unit. The question and answer unit performs a question and answer based on the experience obtained by the hands-on session unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced the challenge of lacking effective education and support for users who want to use generative AI but cannot.

[0005] The system according to the embodiment aims to provide effective education and support to users who want to use generative AI but are unable to do so. [Means for solving the problem]

[0006] The system according to the embodiment includes an explanation section, an introduction section, a hands-on session section, and a question and answer section. The explanation section explains the basic usage of the generative AI. The introduction section introduces an application that utilizes the generative AI based on the content explained by the explanation section. The hands-on session section uses the application introduced by the introduction section. The question and answer section conducts a question and answer session based on the experience gained by the hands-on session section. [Effects of the Invention]

[0007] The system according to the embodiment can provide effective education and support to users who want to use generative AI but are unable to do so. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A generative AI classroom system according to an embodiment of the present invention is a system that allows participants to learn everything from the basic usage of generative AI to its applications. The generative AI classroom system explains the basic usage of generative AI, introduces specific applications that utilize generative AI, and holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. For example, the generative AI classroom system explains the basic usage of generative AI. For example, the generative AI classroom system introduces specific applications that utilize generative AI. For example, the generative AI classroom system holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. In this way, the generative AI classroom system allows participants to learn everything from the basic usage of generative AI to its applications. For example, the generative AI classroom system explains the basic usage of generative AI, introduces specific applications that utilize generative AI, and holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. In this way, the generative AI classroom system allows participants to learn everything from the basic usage of generative AI to its applications.

[0029] A generative AI classroom system according to an embodiment includes an explanation unit, an introduction unit, a hands-on session unit, and a question-and-answer unit. The explanation unit explains the basic usage of the generative AI. For example, the explanation unit explains the basic operations, initial settings, and how to use the basic functions of the generative AI. The explanation unit can provide the explanation through oral explanation, video tutorials, text manuals, and other methods. The introduction unit introduces specific applications that utilize the generative AI. For example, the introduction unit introduces business applications, entertainment applications, educational applications, and other applications. The introduction unit is open to participants of all careers and teaches them how to utilize the generative AI. The hands-on session unit actually uses the generative AI. For example, the hands-on session unit conducts sessions in the form of actual operation experiences, simulations, and workshops. The hands-on session unit also develops human resources knowledgeable about generative AI. The question-and-answer unit conducts question-and-answer sessions. For example, the question-and-answer unit accepts questions in real time, answers questions collected in advance, an online forum, or other methods. The question-and-answer unit can also provide individual consultations. As a result, the generative AI classroom system according to the embodiment allows students to learn everything from the basic usage of generative AI to its applications.

[0030] The Q&A section can respond to individual questions. The Q&A section can respond to individual questions, such as technical questions, questions about operation methods, and questions about applications. For example, if a user asks about the basic operation of the generative AI, the Q&A section can explain the specific operation procedures. Furthermore, if a user asks about how to apply the generative AI, the Q&A section can introduce specific application usage examples. Furthermore, if a user asks about troubleshooting the generative AI, the Q&A section can provide specific solutions. This allows the Q&A section to respond to individual questions and concerns of users.

[0031] The explanation section can utilize existing technical knowledge. The explanation section can utilize existing technical knowledge, such as past research results, industry standards, and best practices. For example, the explanation section can explain the basic usage of the generative AI based on past research results. The explanation section can also explain how to initially configure the generative AI based on industry standards. The explanation section can also explain how to apply the generative AI based on best practices. This can improve operational efficiency.

[0032] The introduction section can be open to anyone regardless of work experience. The introduction section can be open to anyone regardless of work experience, for example, by providing content for beginners or a curriculum that does not require specialized knowledge. For example, the introduction section can explain the basic operations of generative AI to beginners. The introduction section can also provide a curriculum that does not require specialized knowledge. The introduction section can also explain how to apply generative AI to beginners. This allows many users to take the course.

[0033] The Hands-on Session Department can develop human resources with knowledge about generative AI. The Hands-on Session Department can develop human resources with knowledge about generative AI, for example, by obtaining specific qualifications, practical experience, or specialized training. For example, the Hands-on Session Department can provide training to obtain specific qualifications related to generative AI. The Hands-on Session Department can also provide practical sessions to gain practical experience with generative AI. The Hands-on Session Department can also provide specialized training related to generative AI. This will promote the spread of generative AI in each store.

[0034] The Q&A section can collect questions from users. The Q&A section collects questions from users by, for example, a questionnaire, an online form, or by accepting questions directly. For example, the Q&A section may conduct a questionnaire after the class to collect questions from users. The Q&A section can also collect questions from users through an online form. The Q&A section can also accept questions directly from users during the class. This enables the development of new services.

[0035] The explanation unit can select an appropriate explanation method by referring to the user's past learning history. The explanation unit selects an appropriate explanation method by referring to the user's learning history, such as past attendance history, test results, and learning progress. For example, the explanation unit provides an explanation that also serves as a review based on what the user has learned in the past. The explanation unit can also focus on areas in which the user has struggled in the past. The explanation unit can also provide an explanation by prioritizing the learning methods (videos, texts, etc.) that the user has preferred in the past. This makes it possible to provide the user with the optimal explanation method.

[0036] The explanation unit can change the content of the explanation based on the user's field of interest. The explanation unit can change the content of the explanation based on the user's field of interest, such as survey results, past behavior history, or topics of interest. For example, the explanation unit can provide an explanation that incorporates many specific examples related to the user's field of interest. The explanation unit can also provide the latest information related to the user's topic of interest. The explanation unit can also provide an explanation while introducing applications related to the user's field of interest. This makes it possible to provide an explanation that suits the user's interests.

[0037] The explanation unit can evaluate the user's level of understanding and supplement the explanation as necessary. The explanation unit can evaluate the user's level of understanding using methods such as quizzes, tests, and real-time feedback, and supplement the explanation as necessary. For example, if the explanation unit determines that the user does not understand, it can provide another explanation. If the user understands, the explanation unit can also proceed to the next step. If the user only partially understands, the explanation unit can also provide supplemental explanation. This makes it possible to provide an explanation that suits the user's level of understanding.

[0038] The explanation unit can introduce highly relevant cases based on the user's geographical location information. The explanation unit introduces highly relevant cases based on geographical location information such as GPS data, IP address, and user input information. For example, the explanation unit can introduce cases related to the area where the user lives. Furthermore, if the user is studying while traveling, the explanation unit can also introduce cases related to that area. Furthermore, if the user is interested in a particular area, the explanation unit can also introduce cases related to that area. This makes it possible to introduce optimal cases according to the user's geographical location.

[0039] The explanation unit can analyze the user's social media activity and provide related information. The explanation unit can analyze the user's social media activity by, for example, analyzing the content of posts, analyzing followers, evaluating engagement, etc., and provide related information. For example, the explanation unit can provide information related to topics in which the user has shown interest on social media. The explanation unit can also introduce the opinions of experts the user follows on social media. The explanation unit can also provide information related to articles the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activity.

[0040] The explanation unit can change the explanation method by reflecting the user's past feedback. The explanation unit collects the user's past feedback, for example, through methods such as questionnaires, reviews, and direct comments, and changes the explanation method by reflecting the feedback. For example, the explanation unit prioritizes the explanation method that the user previously preferred. The explanation unit can also provide an explanation by reflecting improvements that the user previously pointed out. The explanation unit can also provide an explanation based on the user's past evaluations. This makes it possible to provide an optimal explanation based on the user's past feedback.

[0041] The introduction unit can change the level of detail of the introduction based on the importance of the application. The introduction unit evaluates the importance of the application based on criteria such as user rating, frequency of use, and business impact, and changes the level of detail of the introduction based on the importance. For example, the introduction unit provides a detailed explanation for important applications. The introduction unit can also provide a concise explanation for applications with low importance. The introduction unit can also provide a detailed explanation for applications in which the user is particularly interested. This makes it possible to provide an optimal introduction based on the importance of the application.

[0042] The introduction unit can apply different introduction algorithms depending on the category of the application. For example, the introduction unit applies different introduction algorithms depending on categories such as business, entertainment, and education. For example, the introduction unit can introduce educational applications with an emphasis on learning effectiveness. Furthermore, the introduction unit can introduce entertainment applications with an emphasis on enjoyment. Furthermore, the introduction unit can introduce business applications with an emphasis on efficiency. This makes it possible to provide optimal introductions depending on the application category.

[0043] The introduction unit can improve the accuracy of the introductions based on the user's past usage history. The introduction unit improves the accuracy of the introductions by referring to the usage history, such as past usage data, frequency, and usage patterns. For example, the introduction unit can introduce related applications based on applications that the user has used in the past. The introduction unit can also introduce related applications based on applications that the user has given high ratings in the past. The introduction unit can also introduce related applications based on applications that the user has frequently used in the past. This makes it possible to make optimal introductions based on the user's past usage history.

[0044] The introduction unit may set the priority of introductions based on the release date of the application. The introduction unit may set the priority of introductions based on the release date, such as the release date, version information, and update history. For example, the introduction unit may prioritize introducing newly released applications. The introduction unit may also prioritize introducing update information of applications that the user has used in the past. The introduction unit may also prioritize introducing new applications in categories that the user is interested in. This allows for optimal introductions based on the release date of the application.

[0045] The introduction unit can change the order of introduction based on the relevance of the applications. The introduction unit can change the order of introduction based on the relevance of, for example, common functions, user interests, and purpose of use. For example, the introduction unit can first introduce applications in a category in which the user is interested. The introduction unit can also prioritize introducing applications related to applications that the user has used in the past. The introduction unit can also prioritize introducing applications that the user uses for a specific purpose. This enables the optimal introduction order based on the relevance of the applications.

[0046] The introduction unit can change the use of technical terms in the introduction depending on the user's level of expertise. The introduction unit can change the use of technical terms in the introduction depending on the level of expertise, such as beginner, intermediate, or advanced. For example, if the user is a beginner, the introduction unit can provide an introduction in simple terms, avoiding technical terms. If the user is an intermediate user, the introduction unit can provide an introduction using technical terms appropriately. If the user is an advanced user, the introduction unit can provide a detailed introduction using a lot of technical terms. This makes it possible to provide an optimal introduction depending on the user's level of expertise.

[0047] The hands-on session unit can select an appropriate teaching method by referring to the user's past operation history. The hands-on session unit selects an appropriate teaching method by referring to the operation history, such as past operation data, frequency of use, and success rate. For example, the hands-on session unit provides instruction that also serves as a review based on operations performed by the user in the past. The hands-on session unit can also focus instruction on operations that the user has had difficulty with in the past. The hands-on session unit can also provide instruction by prioritizing the operation method (touch, voice, etc.) that the user has preferred in the past. This makes it possible to provide optimal instruction based on the user's past operation history.

[0048] The hands-on session unit can change the session content based on the user's current skill level. The hands-on session unit can change the session content based on the user's skill level, such as beginner, intermediate, or advanced. For example, if the user is a beginner, the hands-on session unit can start by teaching basic operations. If the user is an intermediate user, the hands-on session unit can also teach advanced operations. If the user is an advanced user, the hands-on session unit can also teach specialized operations. This makes it possible to provide optimal session content according to the user's skill level.

[0049] The hands-on session unit can reflect user feedback in the progress of the session. The hands-on session unit collects user feedback, for example, through methods such as questionnaires, reviews, and direct comments, and reflects the feedback in real time in the progress of the session. For example, if the hands-on session unit determines that the user does not understand, it can provide another explanation. If the user understands, the hands-on session unit can also proceed to the next step. If the user only partially understands, the hands-on session unit can also provide supplementary explanation. This allows the session to proceed optimally based on user feedback.

[0050] The hands-on session unit can use highly relevant cases based on the user's geographical location information. The hands-on session unit can use highly relevant cases based on geographical location information such as GPS data, IP address, and user input information. For example, the hands-on session unit can use cases related to the area where the user lives. Also, if the user is studying while traveling, the hands-on session unit can use cases related to that area. Also, if the user is interested in a particular area, the hands-on session unit can use cases related to that area. This makes it possible to use optimal cases according to the user's geographical location.

[0051] The hands-on session unit can analyze a user's social media activities and provide related information. The hands-on session unit can analyze a user's social media activities by, for example, analyzing post content, analyzing followers, evaluating engagement, etc., and provide related information. For example, the hands-on session unit can provide information related to topics in which the user has shown interest on social media. The hands-on session unit can also introduce the opinions of experts the user follows on social media. The hands-on session unit can also provide information related to articles the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activities.

[0052] The hands-on session unit can change the session content by reflecting the user's past feedback. The hands-on session unit collects the user's past feedback by methods such as questionnaires, reviews, and direct comments, and changes the session content by reflecting the feedback. For example, the hands-on session unit prioritizes session content that the user previously preferred. The hands-on session unit can also conduct a session by reflecting points for improvement that the user previously pointed out. The hands-on session unit can also conduct a session based on content that the user previously evaluated. This makes it possible to provide an optimal session based on the user's past feedback.

[0053] The question and answer section can select an appropriate answering method by referring to the user's past question history. The question and answering section selects an appropriate answering method by referring to the question history, such as the past question content, frequency, and satisfaction level with the answer. For example, the question and answering section provides relevant answers based on questions the user has asked in the past. The question and answering section can also provide more detailed answers to questions that the user had difficulty understanding in the past. The question and answering section can also provide the optimal answer based on answering methods that the user has evaluated in the past. This makes it possible to provide the optimal answer based on the user's past question history.

[0054] The question and answer section can change the content of the answer based on the user's field of interest. The question and answer section can change the content of the answer based on the user's field of interest, such as survey results, past behavior history, or topics of interest. For example, the question and answer section can provide answers that incorporate many specific examples related to the user's field of interest. The question and answer section can also provide the latest information related to the user's topic of interest. The question and answer section can also provide answers while introducing applications related to the user's field of interest. This makes it possible to provide the most appropriate answer based on the user's interests.

[0055] The question and answer section can evaluate the user's level of understanding and supplement the answer as necessary. The question and answer section can evaluate the user's level of understanding by using methods such as quizzes, tests, and real-time feedback, and supplement the answer as necessary. For example, if the question and answer section determines that the user does not understand, it can explain again. If the user understands, the question and answer section can also proceed to the next step. If the user only partially understands, the question and answer section can also provide supplementary explanation. This makes it possible to provide the most appropriate answer according to the user's level of understanding.

[0056] The Q&A section can introduce relevant case studies based on the user's geographic location information. The Q&A section can introduce relevant case studies based on geographic location information such as GPS data, IP address, and user input information. For example, the Q&A section can introduce case studies related to the area where the user lives. If the user is studying while traveling, the Q&A section can also introduce case studies related to that area. If the user is interested in a particular area, the Q&A section can also introduce case studies related to that area. This makes it possible to introduce optimal case studies according to the user's geographic location.

[0057] The Q&A section can analyze a user's social media activity and provide related information. The Q&A section can analyze a user's social media activity by, for example, analyzing post content, analyzing followers, evaluating engagement, etc., and provide related information. For example, the Q&A section can provide information related to topics that the user has shown interest in on social media. The Q&A section can also introduce the opinions of experts that the user follows on social media. The Q&A section can also provide information related to articles that the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activity.

[0058] The Q&A section can change the answering method by reflecting the user's past feedback. The Q&A section collects the user's past feedback, for example, through methods such as questionnaires, reviews, and direct comments, and changes the answering method by reflecting the feedback. For example, the Q&A section prioritizes the answering method that the user previously preferred. The Q&A section can also provide answers by reflecting areas for improvement that the user previously pointed out. The Q&A section can also provide answers based on the user's past evaluations. This makes it possible to provide optimal answers based on the user's past feedback.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The generative AI classroom system can further include a feedback collection unit. The feedback collection unit can collect feedback from users and use it to improve the system. For example, the feedback collection unit can conduct a survey after the class to collect user satisfaction and areas for improvement. The feedback collection unit can also accept feedback in real time and respond immediately. The feedback collection unit can also collect user opinions through an online form. This allows the generative AI classroom system to provide optimal services that reflect user opinions.

[0061] The generative AI classroom system can further include a progress management unit. The progress management unit can manage the user's learning progress and provide an appropriate learning plan. For example, the progress management unit can record the user's learning history and visualize the progress. The progress management unit can also suggest the next content to be learned based on the user's learning pace. The progress management unit can also provide a function that allows the user to set goals and evaluate the degree of achievement. This allows the generative AI classroom system to maximize the user's learning effectiveness.

[0062] The generative AI classroom system can further include a community section. The community section can promote interaction between users and increase motivation to learn. For example, the community section can provide an online forum where users can share questions and opinions. The community section can also hold regular online events to deepen interactions between users. The community section can also provide opportunities for users to form teams and work on projects. In this way, the generative AI classroom system can increase users' motivation to learn.

[0063] The generative AI classroom system can further include a personalized learning unit. The personalized learning unit can provide optimal learning content based on the user's learning style and interests. For example, the personalized learning unit can analyze the user's past learning history and interests to create an individually customized learning plan. The personalized learning unit can also adjust the learning content appropriately based on user feedback. The personalized learning unit can also provide learning materials in the optimal format, such as video, text, or interactive content, depending on the user's learning style. This allows the generative AI classroom system to maximize the user's learning effectiveness.

[0064] The generative AI classroom system can further include a gamification unit. The gamification unit can incorporate game elements to make learning fun. For example, the gamification unit can award points or badges according to learning progress. The gamification unit can also provide a ranking function that allows users to compete with other users. The gamification unit can also provide benefits or rewards to users who achieve specific goals. This allows the generative AI classroom system to increase users' motivation to learn.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The explanation section explains the basic usage of the generative AI. For example, it explains the basic operations, initial settings, and how to use the basic functions of the generative AI. The explanation section can also be done through oral explanations, video tutorials, text manuals, etc. Step 2: The introductory section will introduce specific applications that utilize generative AI, such as business applications, entertainment applications, and educational applications. The introductory section is open to anyone, regardless of career, and will teach them how to utilize generative AI. Step 3: The hands-on session division will actually use the generative AI. For example, they will hold sessions in the form of actual operation experiences, simulations, and workshops. The hands-on session division will also train personnel who are knowledgeable about generative AI. Step 4: The Q&A department will answer questions. For example, the Q&A department will accept questions in real time, answer questions collected in advance, or use an online forum. The Q&A department can also provide individual consultations.

[0067] (Example 2) A generative AI classroom system according to an embodiment of the present invention is a system that allows participants to learn everything from the basic usage of generative AI to its applications. The generative AI classroom system explains the basic usage of generative AI, introduces specific applications that utilize generative AI, and holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. For example, the generative AI classroom system explains the basic usage of generative AI. For example, the generative AI classroom system introduces specific applications that utilize generative AI. For example, the generative AI classroom system holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. In this way, the generative AI classroom system allows participants to learn everything from the basic usage of generative AI to its applications. For example, the generative AI classroom system explains the basic usage of generative AI, introduces specific applications that utilize generative AI, and holds a hands-on session in which the generative AI is actually used, followed by a question-and-answer session. In this way, the generative AI classroom system allows participants to learn everything from the basic usage of generative AI to its applications.

[0068] A generative AI classroom system according to an embodiment includes an explanation unit, an introduction unit, a hands-on session unit, and a question-and-answer unit. The explanation unit explains the basic usage of the generative AI. For example, the explanation unit explains the basic operations, initial settings, and how to use the basic functions of the generative AI. The explanation unit can provide the explanation through oral explanation, video tutorials, text manuals, and other methods. The introduction unit introduces specific applications that utilize the generative AI. For example, the introduction unit introduces business applications, entertainment applications, educational applications, and other applications. The introduction unit is open to participants of all careers and teaches them how to utilize the generative AI. The hands-on session unit actually uses the generative AI. For example, the hands-on session unit conducts sessions in the form of actual operation experiences, simulations, and workshops. The hands-on session unit also develops human resources knowledgeable about generative AI. The question-and-answer unit conducts question-and-answer sessions. For example, the question-and-answer unit accepts questions in real time, answers questions collected in advance, an online forum, or other methods. The question-and-answer unit can also provide individual consultations. As a result, the generative AI classroom system according to the embodiment allows students to learn everything from the basic usage of generative AI to its applications.

[0069] The Q&A section can respond to individual questions. The Q&A section can respond to individual questions, such as technical questions, questions about operation methods, and questions about applications. For example, if a user asks about the basic operation of the generative AI, the Q&A section can explain the specific operation procedures. Furthermore, if a user asks about how to apply the generative AI, the Q&A section can introduce specific application usage examples. Furthermore, if a user asks about troubleshooting the generative AI, the Q&A section can provide specific solutions. This allows the Q&A section to respond to individual questions and concerns of users.

[0070] The explanation section can utilize existing technical knowledge. The explanation section can utilize existing technical knowledge, such as past research results, industry standards, and best practices. For example, the explanation section can explain the basic usage of the generative AI based on past research results. The explanation section can also explain how to initially configure the generative AI based on industry standards. The explanation section can also explain how to apply the generative AI based on best practices. This can improve operational efficiency.

[0071] The introduction section can be open to anyone regardless of work experience. The introduction section can be open to anyone regardless of work experience, for example, by providing content for beginners or a curriculum that does not require specialized knowledge. For example, the introduction section can explain the basic operations of generative AI to beginners. The introduction section can also provide a curriculum that does not require specialized knowledge. The introduction section can also explain how to apply generative AI to beginners. This allows many users to take the course.

[0072] The Hands-on Session Department can develop human resources with knowledge about generative AI. The Hands-on Session Department can develop human resources with knowledge about generative AI, for example, by obtaining specific qualifications, practical experience, or specialized training. For example, the Hands-on Session Department can provide training to obtain specific qualifications related to generative AI. The Hands-on Session Department can also provide practical sessions to gain practical experience with generative AI. The Hands-on Session Department can also provide specialized training related to generative AI. This will promote the spread of generative AI in each store.

[0073] The Q&A section can collect questions from users. The Q&A section collects questions from users by, for example, a questionnaire, an online form, or by accepting questions directly. For example, the Q&A section may conduct a questionnaire after the class to collect questions from users. The Q&A section can also collect questions from users through an online form. The Q&A section can also accept questions directly from users during the class. This enables the development of new services.

[0074] The explanation unit can estimate the user's emotions and change the content and method of explanation based on the estimated user emotions. The explanation unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the content and method of explanation based on the estimated user emotions. For example, if the user is nervous, the explanation unit can provide an explanation at a slower pace to help the user relax. If the user is excited, the explanation unit can provide an explanation that incorporates many interesting concrete examples. If the user is tired, the explanation unit can provide a concise and to-the-point explanation. This enables an optimal explanation to be provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0075] The explanation unit can select an appropriate explanation method by referring to the user's past learning history. The explanation unit selects an appropriate explanation method by referring to the user's learning history, such as past attendance history, test results, and learning progress. For example, the explanation unit provides an explanation that also serves as a review based on what the user has learned in the past. The explanation unit can also focus on areas in which the user has struggled in the past. The explanation unit can also provide an explanation by prioritizing the learning methods (videos, texts, etc.) that the user has preferred in the past. This makes it possible to provide the user with the optimal explanation method.

[0076] The explanation unit can change the content of the explanation based on the user's field of interest. The explanation unit can change the content of the explanation based on the user's field of interest, such as survey results, past behavior history, or topics of interest. For example, the explanation unit can provide an explanation that incorporates many specific examples related to the user's field of interest. The explanation unit can also provide the latest information related to the user's topic of interest. The explanation unit can also provide an explanation while introducing applications related to the user's field of interest. This makes it possible to provide an explanation that suits the user's interests.

[0077] The explanation unit can evaluate the user's level of understanding and supplement the explanation as necessary. The explanation unit can evaluate the user's level of understanding using methods such as quizzes, tests, and real-time feedback, and supplement the explanation as necessary. For example, if the explanation unit determines that the user does not understand, it can provide another explanation. If the user understands, the explanation unit can also proceed to the next step. If the user only partially understands, the explanation unit can also provide supplemental explanation. This makes it possible to provide an explanation that suits the user's level of understanding.

[0078] The explanation unit can estimate the user's emotions and change the order of explanations based on the estimated user emotions. The explanation unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the order of explanations based on the estimated user emotions. For example, if the user is nervous, the explanation unit can start the explanation with content that will relax the user. Also, if the user is excited, the explanation unit can start the explanation with content that will interest the user. Also, if the user is tired, the explanation unit can start the explanation with concise content that focuses on the main points. This enables the optimal explanation order to be determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0079] The explanation unit can introduce highly relevant cases based on the user's geographical location information. The explanation unit introduces highly relevant cases based on geographical location information such as GPS data, IP address, and user input information. For example, the explanation unit can introduce cases related to the area where the user lives. Furthermore, if the user is studying while traveling, the explanation unit can also introduce cases related to that area. Furthermore, if the user is interested in a particular area, the explanation unit can also introduce cases related to that area. This makes it possible to introduce optimal cases according to the user's geographical location.

[0080] The explanation unit can analyze the user's social media activity and provide related information. The explanation unit can analyze the user's social media activity by, for example, analyzing the content of posts, analyzing followers, evaluating engagement, etc., and provide related information. For example, the explanation unit can provide information related to topics in which the user has shown interest on social media. The explanation unit can also introduce the opinions of experts the user follows on social media. The explanation unit can also provide information related to articles the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activity.

[0081] The explanation unit can change the explanation method by reflecting the user's past feedback. The explanation unit collects the user's past feedback, for example, through methods such as questionnaires, reviews, and direct comments, and changes the explanation method by reflecting the feedback. For example, the explanation unit prioritizes the explanation method that the user previously preferred. The explanation unit can also provide an explanation by reflecting improvements that the user previously pointed out. The explanation unit can also provide an explanation based on the user's past evaluations. This makes it possible to provide an optimal explanation based on the user's past feedback.

[0082] The introduction unit can estimate the user's emotions and change the way the application is introduced based on the estimated user emotions. The introduction unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the way the application is introduced based on the estimated user emotions. For example, if the user is nervous, the introduction unit can introduce the application at a slower pace to help the user relax. If the user is excited, the introduction unit can also provide an introduction that incorporates many interesting examples. If the user is tired, the introduction unit can also provide a concise and to-the-point introduction. This enables the optimal application introduction to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0083] The introduction unit can change the level of detail of the introduction based on the importance of the application. The introduction unit evaluates the importance of the application based on criteria such as user rating, frequency of use, and business impact, and changes the level of detail of the introduction based on the importance. For example, the introduction unit provides a detailed explanation for important applications. The introduction unit can also provide a concise explanation for applications with low importance. The introduction unit can also provide a detailed explanation for applications in which the user is particularly interested. This makes it possible to provide an optimal introduction based on the importance of the application.

[0084] The introduction unit can apply different introduction algorithms depending on the category of the application. For example, the introduction unit applies different introduction algorithms depending on categories such as business, entertainment, and education. For example, the introduction unit can introduce educational applications with an emphasis on learning effectiveness. Furthermore, the introduction unit can introduce entertainment applications with an emphasis on enjoyment. Furthermore, the introduction unit can introduce business applications with an emphasis on efficiency. This makes it possible to provide optimal introductions depending on the application category.

[0085] The introduction unit can improve the accuracy of the introductions based on the user's past usage history. The introduction unit improves the accuracy of the introductions by referring to the usage history, such as past usage data, frequency, and usage patterns. For example, the introduction unit can introduce related applications based on applications that the user has used in the past. The introduction unit can also introduce related applications based on applications that the user has given high ratings in the past. The introduction unit can also introduce related applications based on applications that the user has frequently used in the past. This makes it possible to make optimal introductions based on the user's past usage history.

[0086] The introduction unit can estimate the user's emotions and change the length of the introduction based on the estimated user emotions. The introduction unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the length of the introduction based on the estimated user emotions. For example, if the user is nervous, the introduction unit can provide a short, to-the-point introduction. If the user is relaxed, the introduction unit can provide a longer introduction with detailed explanations. If the user is in a hurry, the introduction unit can provide a quick, concise introduction. This allows the introduction length to be optimized according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0087] The introduction unit may set the priority of introductions based on the release date of the application. The introduction unit may set the priority of introductions based on the release date, such as the release date, version information, and update history. For example, the introduction unit may prioritize introducing newly released applications. The introduction unit may also prioritize introducing update information of applications that the user has used in the past. The introduction unit may also prioritize introducing new applications in categories that the user is interested in. This allows for optimal introductions based on the release date of the application.

[0088] The introduction unit can change the order of introduction based on the relevance of the applications. The introduction unit can change the order of introduction based on the relevance of, for example, common functions, user interests, and purpose of use. For example, the introduction unit can first introduce applications in a category in which the user is interested. The introduction unit can also prioritize introducing applications related to applications that the user has used in the past. The introduction unit can also prioritize introducing applications that the user uses for a specific purpose. This enables the optimal introduction order based on the relevance of the applications.

[0089] The introduction unit can change the use of technical terms in the introduction depending on the user's level of expertise. The introduction unit can change the use of technical terms in the introduction depending on the level of expertise, such as beginner, intermediate, or advanced. For example, if the user is a beginner, the introduction unit can provide an introduction in simple terms, avoiding technical terms. If the user is an intermediate user, the introduction unit can provide an introduction using technical terms appropriately. If the user is an advanced user, the introduction unit can provide a detailed introduction using a lot of technical terms. This makes it possible to provide an optimal introduction depending on the user's level of expertise.

[0090] The hands-on session unit can estimate the user's emotions and change the way the hands-on session proceeds based on the estimated user emotions. The hands-on session unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the way the hands-on session proceeds based on the estimated user emotions. For example, if the user is nervous, the hands-on session unit can proceed at a slower pace to allow the user to relax. If the user is excited, the hands-on session unit can proceed by incorporating many interesting concrete examples. If the user is tired, the hands-on session unit can proceed in a concise and to-the-point manner. This enables the hands-on session to proceed optimally according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0091] The hands-on session unit can select an appropriate teaching method by referring to the user's past operation history. The hands-on session unit selects an appropriate teaching method by referring to the operation history, such as past operation data, frequency of use, and success rate. For example, the hands-on session unit provides instruction that also serves as a review based on operations performed by the user in the past. The hands-on session unit can also focus instruction on operations that the user has had difficulty with in the past. The hands-on session unit can also provide instruction by prioritizing the operation method (touch, voice, etc.) that the user has preferred in the past. This makes it possible to provide optimal instruction based on the user's past operation history.

[0092] The hands-on session unit can change the session content based on the user's current skill level. The hands-on session unit can change the session content based on the user's skill level, such as beginner, intermediate, or advanced. For example, if the user is a beginner, the hands-on session unit can start by teaching basic operations. If the user is an intermediate user, the hands-on session unit can also teach advanced operations. If the user is an advanced user, the hands-on session unit can also teach specialized operations. This makes it possible to provide optimal session content according to the user's skill level.

[0093] The hands-on session unit can reflect user feedback in the progress of the session. The hands-on session unit collects user feedback, for example, through methods such as questionnaires, reviews, and direct comments, and reflects the feedback in real time in the progress of the session. For example, if the hands-on session unit determines that the user does not understand, it can provide another explanation. If the user understands, the hands-on session unit can also proceed to the next step. If the user only partially understands, the hands-on session unit can also provide supplementary explanation. This allows the session to proceed optimally based on user feedback.

[0094] The hands-on session unit can estimate the user's emotions and change the content of the hands-on session based on the estimated user emotions. The hands-on session unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the content of the hands-on session based on the estimated user emotions. For example, if the user is nervous, the hands-on session unit can start the session with relaxing content. Also, if the user is excited, the hands-on session unit can start the session with interesting content. Also, if the user is tired, the hands-on session unit can start the session with concise and to-the-point content. This enables optimal session content to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0095] The hands-on session unit can use highly relevant cases based on the user's geographical location information. The hands-on session unit can use highly relevant cases based on geographical location information such as GPS data, IP address, and user input information. For example, the hands-on session unit can use cases related to the area where the user lives. Also, if the user is studying while traveling, the hands-on session unit can use cases related to that area. Also, if the user is interested in a particular area, the hands-on session unit can use cases related to that area. This makes it possible to use optimal cases according to the user's geographical location.

[0096] The hands-on session unit can analyze a user's social media activities and provide related information. The hands-on session unit can analyze a user's social media activities by, for example, analyzing post content, analyzing followers, evaluating engagement, etc., and provide related information. For example, the hands-on session unit can provide information related to topics in which the user has shown interest on social media. The hands-on session unit can also introduce the opinions of experts the user follows on social media. The hands-on session unit can also provide information related to articles the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activities.

[0097] The hands-on session unit can change the session content by reflecting the user's past feedback. The hands-on session unit collects the user's past feedback by methods such as questionnaires, reviews, and direct comments, and changes the session content by reflecting the feedback. For example, the hands-on session unit prioritizes session content that the user previously preferred. The hands-on session unit can also conduct a session by reflecting points for improvement that the user previously pointed out. The hands-on session unit can also conduct a session based on content that the user previously evaluated. This makes it possible to provide an optimal session based on the user's past feedback.

[0098] The Q&A section can estimate the user's emotions and change the way the Q&A session proceeds based on the estimated user emotions. The Q&A section can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the way the Q&A session proceeds based on the estimated user emotions. For example, if the user is nervous, the Q&A section can proceed at a slower pace to allow the user to relax. If the user is excited, the Q&A section can proceed by incorporating many interesting concrete examples. If the user is tired, the Q&A section can proceed in a concise and to-the-point manner. This enables the Q&A session to proceed optimally according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0099] The question and answer section can select an appropriate answering method by referring to the user's past question history. The question and answering section selects an appropriate answering method by referring to the question history, such as the past question content, frequency, and satisfaction level with the answer. For example, the question and answering section provides relevant answers based on questions the user has asked in the past. The question and answering section can also provide more detailed answers to questions that the user had difficulty understanding in the past. The question and answering section can also provide the optimal answer based on answering methods that the user has evaluated in the past. This makes it possible to provide the optimal answer based on the user's past question history.

[0100] The question and answer section can change the content of the answer based on the user's field of interest. The question and answer section can change the content of the answer based on the user's field of interest, such as survey results, past behavior history, or topics of interest. For example, the question and answer section can provide answers that incorporate many specific examples related to the user's field of interest. The question and answer section can also provide the latest information related to the user's topic of interest. The question and answer section can also provide answers while introducing applications related to the user's field of interest. This makes it possible to provide the most appropriate answer based on the user's interests.

[0101] The question and answer section can evaluate the user's level of understanding and supplement the answer as necessary. The question and answer section can evaluate the user's level of understanding by using methods such as quizzes, tests, and real-time feedback, and supplement the answer as necessary. For example, if the question and answer section determines that the user does not understand, it can explain again. If the user understands, the question and answer section can also proceed to the next step. If the user only partially understands, the question and answer section can also provide supplementary explanation. This makes it possible to provide the most appropriate answer according to the user's level of understanding.

[0102] The question and answer unit can estimate the user's emotions and change the order of questions and answers based on the estimated user emotions. The question and answer unit can estimate the user's emotions using methods such as facial expression recognition, voice analysis, and text analysis, and change the order of questions and answers based on the estimated user emotions. For example, if the user is nervous, the question and answer unit can start the questions and answers with relaxing content. Also, if the user is excited, the question and answer unit can start the questions and answers with interesting content. Also, if the user is tired, the question and answer unit can start the questions and answers with concise and to-the-point content. This enables the optimal order of questions and answers to be determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0103] The Q&A section can introduce relevant case studies based on the user's geographic location information. The Q&A section can introduce relevant case studies based on geographic location information such as GPS data, IP address, and user input information. For example, the Q&A section can introduce case studies related to the area where the user lives. If the user is studying while traveling, the Q&A section can also introduce case studies related to that area. If the user is interested in a particular area, the Q&A section can also introduce case studies related to that area. This makes it possible to introduce optimal case studies according to the user's geographic location.

[0104] The Q&A section can analyze a user's social media activity and provide related information. The Q&A section can analyze a user's social media activity by, for example, analyzing post content, analyzing followers, evaluating engagement, etc., and provide related information. For example, the Q&A section can provide information related to topics that the user has shown interest in on social media. The Q&A section can also introduce the opinions of experts that the user follows on social media. The Q&A section can also provide information related to articles that the user has shared on social media. This makes it possible to provide optimal information based on the user's social media activity.

[0105] The Q&A section can change the answering method by reflecting the user's past feedback. The Q&A section collects the user's past feedback, for example, through methods such as questionnaires, reviews, and direct comments, and changes the answering method by reflecting the feedback. For example, the Q&A section prioritizes the answering method that the user previously preferred. The Q&A section can also provide answers by reflecting areas for improvement that the user previously pointed out. The Q&A section can also provide answers based on the user's past evaluations. This makes it possible to provide optimal answers based on the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the explanation section, introduction section, hands-on session section, and question and answer section, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the explanation section explains the basic usage of the generated AI using the display 40A and speaker 40B of the smart device 14. The introduction section introduces specific applications utilizing the generated AI using, for example, the specific processing unit 290 of the data processing device 12. The hands-on session section provides an actual operation experience of the generated AI using, for example, the touch panel 38A of the smart device 14. The question and answer section realizes, for example, real-time question reception and an online forum using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the explanation section, introduction section, hands-on session section, and question and answer section, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the explanation section explains the basic usage of the generated AI using the display and speaker 240 of the smart glasses 214. The introduction section introduces specific applications utilizing the generated AI using, for example, the specific processing unit 290 of the data processing device 12. The hands-on session section provides an actual operation experience of the generated AI using, for example, the touch panel of the smart glasses 214. The question and answer section realizes, for example, real-time question reception and an online forum using, for example, the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the explanation section, introduction section, hands-on session section, and question and answer section described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the explanation section explains the basic usage of the generating AI using the display 343 and speaker 240 of the headset-type terminal 314. The introduction section introduces specific applications that utilize the generating AI using, for example, the specific processing unit 290 of the data processing device 12. The hands-on session section provides an actual operation experience of the generating AI using, for example, the touch panel of the headset-type terminal 314. The question and answer section realizes, for example, real-time question reception and an online forum using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the explanation section, introduction section, hands-on session section, and question and answer section, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the explanation section explains the basic usage of the generative AI using the display and speaker 240 of the robot 414. The introduction section introduces specific applications that utilize the generative AI using, for example, the specific processing unit 290 of the data processing device 12. The hands-on session section provides an actual operation experience of the generative AI using, for example, the touch panel of the robot 414. The question and answer section realizes, for example, real-time question reception and an online forum using the specific processing unit 290 of the data processing device 12.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The generative AI classroom system can further include a feedback collection unit. The feedback collection unit can collect feedback from users and use it to improve the system. For example, the feedback collection unit can conduct a survey after the class to collect user satisfaction and areas for improvement. The feedback collection unit can also accept feedback in real time and respond immediately. The feedback collection unit can also collect user opinions through an online form. This allows the generative AI classroom system to provide optimal services that reflect user opinions.

[0108] The generative AI classroom system can further include a progress management unit. The progress management unit can manage the user's learning progress and provide an appropriate learning plan. For example, the progress management unit can record the user's learning history and visualize the progress. The progress management unit can also suggest the next content to be learned based on the user's learning pace. The progress management unit can also provide a function that allows the user to set goals and evaluate the degree of achievement. This allows the generative AI classroom system to maximize the user's learning effectiveness.

[0109] The generative AI classroom system can further include a community section. The community section can promote interaction between users and increase motivation to learn. For example, the community section can provide an online forum where users can share questions and opinions. The community section can also hold regular online events to deepen interactions between users. The community section can also provide opportunities for users to form teams and work on projects. In this way, the generative AI classroom system can increase users' motivation to learn.

[0110] The generative AI classroom system can further include a personalized learning unit. The personalized learning unit can provide optimal learning content based on the user's learning style and interests. For example, the personalized learning unit can analyze the user's past learning history and interests to create an individually customized learning plan. The personalized learning unit can also adjust the learning content appropriately based on user feedback. The personalized learning unit can also provide learning materials in the optimal format, such as video, text, or interactive content, depending on the user's learning style. This allows the generative AI classroom system to maximize the user's learning effectiveness.

[0111] The generative AI classroom system can further include a gamification unit. The gamification unit can incorporate game elements to make learning fun. For example, the gamification unit can award points or badges according to learning progress. The gamification unit can also provide a ranking function that allows users to compete with other users. The gamification unit can also provide benefits or rewards to users who achieve specific goals. This allows the generative AI classroom system to increase users' motivation to learn.

[0112] The explanation unit can estimate the user's emotions and change the tone of the explanation based on the estimated user's emotions. For example, if the user is feeling anxious, the explanation unit can provide an explanation in a gentle tone that gives a sense of security. If the user is excited, the explanation unit can also provide an explanation in an energetic tone. If the user is tired, the explanation unit can also provide an explanation in a calm tone. This makes it possible to provide an optimal explanation according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0113] The question and answer unit can estimate the user's emotions and adjust the content of the answer based on the estimated user emotions. For example, if the user is confused, the question and answer unit can provide a more detailed and easy-to-understand answer. If the user is excited, the question and answer unit can also provide interesting additional information. If the user is tired, the question and answer unit can also provide a concise and to-the-point answer. This enables the optimal answer to be provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0114] The hands-on session unit can estimate the user's emotions and adjust the difficulty of the session based on the estimated user emotions. For example, if the user is nervous, the hands-on session unit can start with an easy task. If the user is excited, the hands-on session unit can also provide a challenging task. If the user is tired, the hands-on session unit can also provide a task that can be completed in a short time. This enables an optimal session according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0115] The introduction unit can estimate the user's emotions and change the order in which applications are introduced based on the estimated user emotions. For example, if the user is nervous, the introduction unit can start by introducing applications that are relaxing. Also, if the user is excited, the introduction unit can start by introducing applications that are interesting. Also, if the user is tired, the introduction unit can start by introducing applications that are concise and to the point. This makes it possible to introduce optimal applications according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0116] The explanation unit can estimate the user's emotions and adjust the timing of the explanation based on the estimated user emotions. For example, if the explanation unit is nervous, it can take a break during the explanation to allow the user to relax. Furthermore, if the user is excited, the explanation unit can provide continuous explanations. Furthermore, if the user is tired, the explanation unit can divide the explanation into shorter sessions. This enables optimal explanation timing according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The explanation section explains the basic usage of the generative AI. For example, it explains the basic operations, initial settings, and how to use the basic functions of the generative AI. The explanation section can also be done through oral explanations, video tutorials, text manuals, etc. Step 2: The introductory section will introduce specific applications that utilize generative AI, such as business applications, entertainment applications, and educational applications. The introductory section is open to anyone, regardless of career, and will teach them how to utilize generative AI. Step 3: The hands-on session division will actually use the generative AI. For example, they will hold sessions in the form of actual operation experiences, simulations, and workshops. The hands-on session division will also train personnel who are knowledgeable about generative AI. Step 4: The Q&A department will answer questions. For example, the Q&A department will accept questions in real time, answer questions collected in advance, or use an online forum. The Q&A department can also provide individual consultations.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system comprising an explanation section that explains the basic usage of generative AI, an introduction section that introduces applications that utilize generative AI based on the content explained by the explanation section, a hands-on session section that uses the applications introduced by the introduction section, and a question and answer section that conducts questions and answers based on the experience gained by the hands-on session section.

2. The system of claim 1 , wherein the question and answer section responds to individual questions.

3. The system of claim 1 , wherein the explanation component leverages existing technical knowledge.

4. The system according to claim 1 , wherein the introduction section allows students to take the course regardless of their work history.

5. The system of claim 1, wherein the hands-on session section develops human resources with knowledge about generative AI.

6. 2. The system of claim 1, wherein the question and answer section collects questions from users.

7. The system according to claim 1 , wherein the explanation unit estimates the user's emotion and changes the content and method of the explanation based on the estimated user's emotion.

8. 2. The system according to claim 1, wherein the explanation section selects an appropriate explanation method by referring to the user's past learning history.

Images