System

Abstract

An object of a system according to an embodiment is to support class development that naturally prompts a student to "think by himself / herself".SOLUTION: A system includes an incorrect answer generation part, a reaction analysis part, an optimization part, and a summarization part. The incorrect-answer generation unit generates an intentionally incorrect answer to the question input by the teacher. The reaction analysis unit analyzes the reaction of the student to the incorrect answer generated by the incorrect answer generation unit. The optimization unit optimizes a characteristic of the class based on the reaction analyzed by the reaction analysis unit. The summarization unit summarizes the lesson content optimized by the optimization 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 does not adequately develop lessons that naturally encourage students to "think for themselves," and there is room for improvement.

[0005] The system according to the embodiment aims to support the development of lessons that naturally encourage students to "think for themselves." [Means for solving the problem]

[0006] The system according to the embodiment includes an incorrect answer generation unit, a response analysis unit, an optimization unit, and a summarization unit. The incorrect answer generation unit generates intentionally incorrect answers to questions entered by a teacher. The response analysis unit analyzes the responses of students to the incorrect answers generated by the incorrect answer generation unit. The optimization unit optimizes class characteristics based on the responses analyzed by the response analysis unit. The summarization unit summarizes the lesson content optimized by the optimization unit. [Effects of the Invention]

[0007] The system according to the embodiment can support the development of lessons that naturally encourage students to "think for themselves." [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The education support system according to the embodiment of the present invention is a system that supports teachers and naturally encourages students to "think for themselves." This allows teachers to effectively develop lessons that foster the ability to "think for themselves."

[0029] An educational support system according to an embodiment includes an incorrect answer generation unit, a response analysis unit, an optimization unit, and a summarization unit. The incorrect answer generation unit generates intentionally incorrect answers to questions entered by a teacher. For example, the generation AI generates an incorrect answer such as "2 + 2 = 5" for a math problem. The generation AI can also present an incorrect date for a history question. The generation AI can also present an incorrect experimental procedure for a science question. The response analysis unit analyzes students' responses to the incorrect answers generated by the incorrect answer generation unit. For example, the response analysis unit captures students' facial expressions with a camera and analyzes their responses using an emotion estimation algorithm. The response analysis unit can also record students' voices and analyze their responses using voice analysis technology. The response analysis unit can also collect students' behaviors using sensors and analyze their responses using a behavior analysis algorithm. The optimization unit optimizes class characteristics based on the responses analyzed by the response analysis unit. For example, the optimization unit analyzes the academic level of the class and provides lesson content appropriate to that level. The optimization unit can also analyze the interests of the class and provide lesson content that matches those interests. The optimization unit can also analyze the learning style of the class and provide lesson content that matches that style. The summarization unit summarizes the lesson content optimized by the optimization unit. For example, the summarization unit extracts main topics of the lesson and briefly summarizes them. The summarization unit can also list important points of the lesson. The summarization unit can also summarize the lesson content in the form of visual notes or mind maps. This allows the education support system according to the embodiment to effectively develop lessons that foster students' ability to "think for themselves." For example, a teacher can use incorrect answers generated by the generation AI to conduct lessons that encourage students to think. A teacher can also provide appropriate instruction based on the reactions of students analyzed by the response analysis unit. A teacher can use the lesson content optimized by the optimization unit to conduct lessons that match the characteristics of the class. A teacher can also use the lesson content summarized by the summarization unit to efficiently conduct lessons.

[0030] The incorrect answer generation unit can analyze a student's past answer history and generate the most effective incorrect answer for each student. For example, the generation AI stores a student's past answer history in a database and generates the most effective incorrect answer for each student based on that data. For example, it analyzes patterns of questions that have been answered incorrectly in the past and generates new questions containing similar mistakes. The incorrect answer generation unit also analyzes a student's answer history in real time and generates the most effective incorrect answer on the spot. For example, if a student frequently gets a particular type of question wrong, it generates incorrect answers mainly for questions of that type. The incorrect answer generation unit also tracks a student's answer history over the long term and generates optimal incorrect answers according to their learning progress. For example, it analyzes answer history each semester and prepares effective incorrect answers for the next semester. This allows it to provide the optimal incorrect answers for each student.

[0031] The incorrect answer generation unit can generate multiple incorrect answers and have students choose the correct one from among them. For example, the incorrect answer generation unit uses a generation AI to generate multiple incorrect answers for a single problem and have students choose the correct one from among them. For example, it could present three incorrect answers and one correct answer for a math problem. The incorrect answer generation unit also adds a function that allows the generation AI to generate multiple incorrect answers and explain the reason for each error. For example, it could display reasons such as "calculation error" or "conceptual misunderstanding" for each incorrect answer option. The incorrect answer generation unit also generates multiple incorrect answers and provides feedback for the answer chosen by the student. For example, if a student chooses an incorrect answer, it could explain the reason and how to lead to the correct answer. This improves learning effectiveness by allowing students to choose the correct answer from the options.

[0032] The incorrect answer generation unit can be made to support different subjects and courses. For example, the incorrect answer generation unit enables the generation AI to support not only mathematics but also different subjects and courses such as Japanese, science, and social studies. For example, it generates intentionally incorrect options for Japanese reading comprehension questions. In addition, in order for the generation AI to support different subjects and courses, the incorrect answer generation unit registers specialized knowledge of each subject in a database and generates incorrect answers based on that. For example, it presents incorrect procedures in science experiment questions. In addition, in order for the generation AI to support different subjects and courses, the incorrect answer generation unit analyzes the question format and question trends of each subject and generates incorrect answers based on that. For example, it presents the wrong date in a history question in social studies. This allows it to support different subjects and courses, enabling a wide range of learning support.

[0033] The incorrect answer generation unit can generate incorrect answers of a level of difficulty appropriate to the age and grade of the student. For example, the generation AI of the incorrect answer generation unit generates incorrect answers of a level of difficulty appropriate to the age and grade of the student. For example, it presents easy incorrect answers to first-grade elementary school students and more difficult incorrect answers to third-grade junior high school students. The incorrect answer generation unit also generates incorrect answers of an appropriate level of difficulty based on the curriculum appropriate to the student's grade. For example, it generates incorrect answers by referencing the curriculum guidelines for each grade. The incorrect answer generation unit also analyzes the learning progress appropriate to the student's age and grade, and generates incorrect answers of the optimal level of difficulty based on that. For example, it presents difficult incorrect answers as a general review at the end of the school year. This makes it possible to provide incorrect answers of an appropriate level of difficulty appropriate to the student's age and grade.

[0034] When analyzing students' responses, generative AI can provide more detailed feedback by taking into account the speed and frequency of responses. For example, generative AI can analyze students' response speed and frequency and provide detailed feedback based on that data. For example, it can analyze how quickly students respond to questions and evaluate their level of understanding. Generative AI can also analyze students' response frequency and provide individualized feedback based on that data. For example, it can provide additional practice questions for questions that students frequently get wrong. Generative AI can also analyze students' response speed and frequency in real time and build a system that reports the results to teachers. For example, if a student responds slowly to a particular question, it can provide an explanation for that question. This allows for more detailed feedback to be provided by taking response speed and frequency into account.

[0035] When analyzing student responses, generative AI can also analyze responses in group activities and discussions. For example, generative AI can analyze responses in group activities and discussions and provide feedback based on that data. For example, it can analyze the frequency and content of comments within a group to evaluate the group's dynamics. Generative AI can also analyze responses in group activities and discussions in real time and build a system that reports the results to teachers. For example, it can analyze the level of cooperation and agreement within a group and notify the teacher. Generative AI can also analyze responses in group activities and discussions and provide individual feedback based on that data. For example, if a particular student does not speak up, it can identify the cause and provide a solution. This allows for more detailed feedback to be provided by analyzing responses in group activities and discussions.

[0036] When analyzing students' responses, generative AI can provide feedback tailored to different learning styles (visual, auditory, tactile). For example, generative AI can analyze students' learning styles and provide visual, auditory, and tactile feedback based on that data. For example, visual learners can be provided with feedback using diagrams and graphs. Generative AI can also analyze students' learning styles in real time and provide individualized feedback based on the results. For example, auditory learners can be provided with audio explanations. Generative AI can also analyze students' learning styles and provide practical feedback to tactile learners based on that data. For example, helping them understand the learning content through experiments and practical training. This makes it possible to provide feedback tailored to different learning styles.

[0037] When analyzing class characteristics, the generative AI can also take into account data such as past test results and attendance rates. For example, when analyzing class characteristics, the generative AI stores past test results in a database and optimizes lesson content based on that data. For example, it provides lessons that focus on areas where test results are low. The generative AI can also analyze class attendance rates and optimize lesson content based on that data. For example, it can provide lessons that focus on review on days when attendance is low. The generative AI can also analyze past test results and attendance rates in real time and build a system that optimizes lesson content based on the results. For example, it can provide additional practice questions for areas where test results are low. In this way, by taking past test results and attendance rates into consideration, it is possible to provide optimal lesson content according to the characteristics of a class.

[0038] When analyzing class characteristics, generative AI can also take into account the teacher's teaching style and the pace of the lesson. For example, generative AI can analyze a teacher's teaching style and provide lesson content tailored to the class's characteristics based on that data. For example, if a teacher prefers interactive lessons, it can provide teaching materials tailored to that style. Generative AI can also analyze the pace of the lesson and provide lesson content tailored to the class's characteristics based on that data. For example, it can provide advanced content for a class with a fast pace and basic content for a class with a slow pace. Generative AI can also analyze a teacher's teaching style and the pace of the lesson in real time and build a system that optimizes lesson content based on the results. For example, it can provide feedback tailored to the teacher's teaching style. This makes it possible to provide optimal lesson content tailored to the class's characteristics by taking into account the teacher's teaching style and the pace of the lesson.

[0039] When analyzing the characteristics of a class, the generative AI can perform comparative analysis with classes in different schools and regions. For example, the generative AI collects data on classes in different schools and regions and performs comparative analysis based on that data. For example, it can analyze the academic ability differences between classes in the same grade and provide the optimal lesson content. The generative AI can also analyze the characteristics of classes in different regions and provide the optimal lesson content for each region based on that data. For example, it can provide different teaching materials for classes in urban and rural areas. The generative AI can also perform comparative analysis with classes in different schools and regions in real time and build a system that optimizes lesson content based on the results. For example, it can refer to lesson content that has been successful in other schools. This allows it to perform comparative analysis with classes in different schools and regions and provide the optimal lesson content according to the characteristics of the class.

[0040] When analyzing class characteristics, generative AI can also accommodate online and hybrid classes. For example, generative AI can analyze the characteristics of online and hybrid classes and provide optimal lesson content based on that data. For example, it can provide teaching materials and assignments suitable for online classes. Generative AI can also analyze the progress of online and hybrid classes in real time and build a system that optimizes lesson content based on the results. For example, it can evaluate the level of understanding in online classes. Generative AI can also analyze the characteristics of online and hybrid classes and provide individual feedback based on that data. For example, it can provide feedback based on participation in online classes. This makes it possible to accommodate online and hybrid classes, enabling flexible learning support.

[0041] The generative AI can automatically highlight important keywords and phrases when summarizing lesson content. For example, the generative AI adds a function to automatically highlight important keywords and phrases when summarizing lesson content. For example, important words in the summary text are displayed in bold or color. The generative AI also adds a function to automatically list important points when summarizing lesson content. For example, important points are displayed in bullet points at the end of the summary text. The generative AI also adds a function to automatically highlight important keywords and phrases when summarizing lesson content. For example, important parts of the summary text are highlighted with a background color. This makes it easier for students to grasp the important points by highlighting important keywords and phrases when summarizing lesson content.

[0042] When summarizing lesson content, the generation AI can provide customized summaries based on the students' level of understanding. For example, the generation AI can analyze the students' level of understanding and provide customized summaries based on that data. For example, it can provide detailed summaries for students with low levels of understanding and concise summaries for students with high levels of understanding. The generation AI can also analyze the students' level of understanding in real time and build a system that provides individual customized summaries based on the results. For example, it can automatically generate summary text based on the students' level of understanding. The generation AI can also analyze the students' level of understanding and provide customized summaries based on that data. For example, it can provide summaries that focus on areas where the students have low levels of understanding. This improves learning effectiveness by providing customized summaries based on the students' level of understanding.

[0043] When summarizing class content, generative AI can automatically translate it into different languages ​​and provide summaries in multiple languages. For example, when summarizing class content, generative AI adds a function to automatically translate it into different languages. For example, it can provide summaries translated into multiple languages, such as English and Chinese. Furthermore, when summarizing class content, generative AI can automatically translate it into different languages ​​and build a system that provides summaries in multiple languages ​​based on the translation results. For example, it can develop an algorithm to improve translation accuracy. Furthermore, when summarizing class content, generative AI can automatically translate it into different languages ​​and provide summaries in multiple languages ​​based on the translation results. For example, it can combine summaries in different languages ​​into a single document. This makes it possible to support international learning by automatically translating it into different languages ​​and providing summaries in multiple languages.

[0044] When summarizing class content, generative AI can provide summaries in visual note or mind map format. For example, when summarizing class content, generative AI will add a function to provide summaries in visual note format. For example, it will visually represent important points with diagrams and illustrations. Furthermore, when summarizing class content, generative AI will add a function to provide summaries in mind map format. For example, it will display related information in a branched format centered around the main topic of the class content. Furthermore, generative AI will build a system that provides summaries in visual note or mind map format when summarizing class content. For example, it will develop an algorithm that automatically visualizes summary text. This will allow summaries to be provided in visual note or mind map format, making it easier to understand visually.

[0045] When presenting incorrect answers in educational programs, generative AI can customize them according to the viewer's age group and interests. For example, when presenting incorrect answers in educational programs, generative AI customizes them according to the viewer's age group. For example, it might present easy incorrect answers to elementary school students and more difficult incorrect answers to junior high school students. When presenting incorrect answers in educational programs, generative AI also customizes them according to the viewer's interests. For example, it might present science questions to viewers interested in science, and history questions to viewers interested in history. Furthermore, generative AI builds a system that customizes incorrect answers in educational programs according to the viewer's age group and interests. For example, it might generate the optimal incorrect answer based on the viewer's profile data. This allows for customization according to the viewer's age group and interests, maximizing the effectiveness of educational programs.

[0046] When presenting incorrect answers in educational programs, generative AI can introduce an interactive quiz format that matches the progress of the program. For example, when presenting incorrect answers in educational programs, generative AI introduces an interactive quiz format. For example, it allows viewers to select the answer using a remote control or smartphone. Furthermore, when presenting incorrect answers in educational programs, generative AI introduces a quiz format that matches the progress of the program. For example, it could ask a quiz question in a specific segment of the program, allowing viewers to participate in real time. Furthermore, generative AI could build a system that introduces an interactive quiz format when presenting incorrect answers in educational programs. For example, it could collect viewer response data in real time and reflect it in the progress of the program. This could increase viewer participation by introducing an interactive quiz format that matches the progress of the program.

[0047] Generative AI can enable use across different media (television, online, radio) when presenting incorrect answers in educational programs. For example, generative AI can enable incorrect answers in educational programs to be used not only on television but also online and radio. For example, it can provide quiz-style questions on online platforms. Generative AI can also build a system that enables use across different media when presenting incorrect answers in educational programs. For example, it can provide audio quizzes on radio programs. Generative AI can also develop an interface that enables use across different media when presenting incorrect answers in educational programs. For example, it can link television programs with online platforms. This can maximize the effectiveness of educational programs by enabling use across different media.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The educational support system may further include a learning progress tracking unit. The learning progress tracking unit tracks the learning progress of students in real time and provides feedback according to the progress. For example, if a student is struggling with a particular unit, the learning progress tracking unit may provide additional practice questions related to that unit. The learning progress tracking unit may also visually display the student's learning progress in graphs or charts, making it easy for teachers and parents to understand the progress. Furthermore, the learning progress tracking unit may suggest individual learning plans based on the student's learning progress. For example, if the student's understanding is low in a particular area, the learning progress tracking unit may suggest a learning plan that focuses on that area. This makes it possible to effectively manage the student's learning progress and meet the individual learning needs of the student.

[0050] The educational support system can further include a learning style adaptation unit. The learning style adaptation unit analyzes the learning style (visual, auditory, tactile) of each student and provides learning materials and feedback appropriate to that style. For example, visual learners can be provided with learning materials that make extensive use of diagrams and graphs, while auditory learners can be provided with audio commentary. Tactile learners can also be helped to understand the learning content through experiments and practical training. Furthermore, the learning style adaptation unit can analyze each student's learning style in real time and provide individual feedback based on the results. For example, it can automatically generate exercises and assignments appropriate to each student's learning style. This makes it possible to provide an optimal learning environment appropriate to each student's learning style.

[0051] The educational support system can further include a collaborative learning support unit. The collaborative learning support unit supports students when they study cooperatively in groups. For example, it can automatically suggest role assignments within the group and promote learning activities that make use of each member's strengths. The collaborative learning support unit can also provide tools to promote communication within the group. For example, online chat and video conferencing functions can be used to smoothly communicate with members in remote locations. Furthermore, the collaborative learning support unit can monitor the learning progress within the group in real time and provide feedback as needed. This can maximize the effectiveness of collaborative learning and improve students' teamwork and communication skills.

[0052] The educational support system can further include an intercultural understanding promotion unit. The intercultural understanding promotion unit supports students in interacting with and deepening understanding of people from different cultures and backgrounds. For example, the intercultural understanding promotion unit may collaborate online with schools in different countries and regions to provide a platform where students can interact with each other. The intercultural understanding promotion unit may also provide information and teaching materials about different cultures, allowing students to learn while comparing them with their own culture. Furthermore, the intercultural understanding promotion unit may provide tools to resolve communication challenges that arise during intercultural exchange. For example, it may use translation functions or multilingual chat tools to support communication across language barriers. This allows students to understand different cultures and develop a global perspective.

[0053] The educational support system can further include a parent-teacher collaboration unit. The parent-teacher collaboration unit shares information about students' learning status with parents and promotes learning support at home. For example, the parent-teacher collaboration unit may provide parents with regular reports on students' learning progress and grades. The parent-teacher collaboration unit may also provide advice and resources for parents to support their students at home. For example, it may provide information on how to create a learning environment at home and effective learning methods. The parent-teacher collaboration unit may also provide communication tools that enable parents and teachers to collaborate to support students' learning. For example, parents and teachers may use online interviews or chat functions to regularly share information and understand students' learning status. This allows homes and schools to work together to support students' learning.

[0054] The education support system can further include a career support unit. The career support unit supports students when they think about their future careers. For example, the career support unit may suggest appropriate occupations and career paths based on the students' interests and aptitudes. The career support unit can also provide learning plans that help students set future goals and acquire the skills and knowledge necessary to achieve them. For example, the career support unit may show them the steps to acquire the qualifications and skills necessary for a specific occupation. The career support unit can also provide students with opportunities to think about their future careers through actual work experience. For example, the career support unit may provide opportunities for internships and workplace visits. The career support unit can also provide online counseling services that allow students to consult about their future careers. This allows students to think about their future and set specific goals.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The incorrect answer generator generates intentionally incorrect answers to questions entered by the teacher. For example, the generator AI generates an incorrect answer such as "2 + 2 = 5" for a math problem. The generator AI can also present an incorrect date for a history question. Furthermore, the generator AI can present an incorrect experimental procedure for a science question. Step 2: The reaction analysis unit analyzes the student's reaction to the incorrect answer generated by the incorrect answer generation unit. For example, the reaction analysis unit may capture the student's facial expression with a camera and analyze the reaction using an emotion estimation algorithm. The reaction analysis unit may also record the student's voice and analyze the reaction using voice analysis technology. Furthermore, the reaction analysis unit may collect the student's behavior with a sensor and analyze the reaction using a behavior analysis algorithm. Step 3: The optimization unit optimizes the characteristics of the class based on the responses analyzed by the response analysis unit. For example, the optimization unit analyzes the academic level of the class and provides lesson content appropriate to that level. The optimization unit can also analyze the interests of the class and provide lesson content appropriate to those interests. Furthermore, the optimization unit can analyze the learning style of the class and provide lesson content appropriate to that style. Step 4: The summarization unit summarizes the lesson content optimized by the optimization unit. For example, the summarization unit can extract the main topics of the lesson and summarize them concisely. The summarization unit can also list the important points of the lesson. Furthermore, the summarization unit can summarize the lesson content in the form of visual notes or mind maps.

[0057] (Example 2) The education support system according to the embodiment of the present invention is a system that supports teachers and naturally encourages students to "think for themselves." This allows teachers to effectively develop lessons that foster the ability to "think for themselves."

[0058] An educational support system according to an embodiment includes an incorrect answer generation unit, a response analysis unit, an optimization unit, and a summarization unit. The incorrect answer generation unit generates intentionally incorrect answers to questions entered by a teacher. For example, the generation AI generates an incorrect answer such as "2 + 2 = 5" for a math problem. The generation AI can also present an incorrect date for a history question. The generation AI can also present an incorrect experimental procedure for a science question. The response analysis unit analyzes students' responses to the incorrect answers generated by the incorrect answer generation unit. For example, the response analysis unit captures students' facial expressions with a camera and analyzes their responses using an emotion estimation algorithm. The response analysis unit can also record students' voices and analyze their responses using voice analysis technology. The response analysis unit can also collect students' behaviors using sensors and analyze their responses using a behavior analysis algorithm. The optimization unit optimizes class characteristics based on the responses analyzed by the response analysis unit. For example, the optimization unit analyzes the academic level of the class and provides lesson content appropriate to that level. The optimization unit can also analyze the interests of the class and provide lesson content that matches those interests. The optimization unit can also analyze the learning style of the class and provide lesson content that matches that style. The summarization unit summarizes the lesson content optimized by the optimization unit. For example, the summarization unit extracts main topics of the lesson and briefly summarizes them. The summarization unit can also list important points of the lesson. The summarization unit can also summarize the lesson content in the form of visual notes or mind maps. This allows the education support system according to the embodiment to effectively develop lessons that foster students' ability to "think for themselves." For example, a teacher can use incorrect answers generated by the generation AI to conduct lessons that encourage students to think. A teacher can also provide appropriate instruction based on the reactions of students analyzed by the response analysis unit. A teacher can use the lesson content optimized by the optimization unit to conduct lessons that match the characteristics of the class. A teacher can also use the lesson content summarized by the summarization unit to efficiently conduct lessons.

[0059] The incorrect answer generation unit can analyze a student's past answer history and generate the most effective incorrect answer for each student. For example, the generation AI stores a student's past answer history in a database and generates the most effective incorrect answer for each student based on that data. For example, it analyzes patterns of questions that have been answered incorrectly in the past and generates new questions containing similar mistakes. The incorrect answer generation unit also analyzes a student's answer history in real time and generates the most effective incorrect answer on the spot. For example, if a student frequently gets a particular type of question wrong, it generates incorrect answers mainly for questions of that type. The incorrect answer generation unit also tracks a student's answer history over the long term and generates optimal incorrect answers according to their learning progress. For example, it analyzes answer history each semester and prepares effective incorrect answers for the next semester. This allows it to provide the optimal incorrect answers for each student.

[0060] The incorrect answer generation unit can generate multiple incorrect answers and have students choose the correct one from among them. For example, the incorrect answer generation unit uses a generation AI to generate multiple incorrect answers for a single problem and have students choose the correct one from among them. For example, it could present three incorrect answers and one correct answer for a math problem. The incorrect answer generation unit also adds a function that allows the generation AI to generate multiple incorrect answers and explain the reason for each error. For example, it could display reasons such as "calculation error" or "conceptual misunderstanding" for each incorrect answer option. The incorrect answer generation unit also generates multiple incorrect answers and provides feedback for the answer chosen by the student. For example, if a student chooses an incorrect answer, it could explain the reason and how to lead to the correct answer. This improves learning effectiveness by allowing students to choose the correct answer from the options.

[0061] The incorrect answer generation unit can use the emotion estimation function to analyze how students feel about incorrect answers and generate incorrect answers that elicit a positive emotional response. For example, the incorrect answer generation unit can use the emotion estimation function to analyze in real time how students feel about incorrect answers and generate incorrect answers that elicit a positive response. For example, it can present humorous incorrect answers that make students smile. Furthermore, if a student feels negative emotions about an incorrect answer, the incorrect answer generation unit can use the emotion estimation function to provide feedback to alleviate those emotions. For example, it can display an encouraging message such as, "That was close! You were almost right!" Furthermore, the incorrect answer generation unit can use the emotion estimation function to devise a way to present incorrect answers so that students feel positive emotions about incorrect answers. For example, it can present incorrect answers in the form of a quiz, allowing students to learn in a game-like manner. This allows students to progress through their studies while feeling positive emotions.

[0062] The incorrect answer generation unit can be made to support different subjects and courses. For example, the incorrect answer generation unit enables the generation AI to support not only mathematics but also different subjects and courses such as Japanese, science, and social studies. For example, it generates intentionally incorrect options for Japanese reading comprehension questions. In addition, in order for the generation AI to support different subjects and courses, the incorrect answer generation unit registers specialized knowledge of each subject in a database and generates incorrect answers based on that. For example, it presents incorrect procedures in science experiment questions. In addition, in order for the generation AI to support different subjects and courses, the incorrect answer generation unit analyzes the question format and question trends of each subject and generates incorrect answers based on that. For example, it presents the wrong date in a history question in social studies. This allows it to support different subjects and courses, enabling a wide range of learning support.

[0063] The incorrect answer generation unit can generate incorrect answers of a level of difficulty appropriate to the age and grade of the student. For example, the generation AI of the incorrect answer generation unit generates incorrect answers of a level of difficulty appropriate to the age and grade of the student. For example, it presents easy incorrect answers to first-grade elementary school students and more difficult incorrect answers to third-grade junior high school students. The incorrect answer generation unit also generates incorrect answers of an appropriate level of difficulty based on the curriculum appropriate to the student's grade. For example, it generates incorrect answers by referencing the curriculum guidelines for each grade. The incorrect answer generation unit also analyzes the learning progress appropriate to the student's age and grade, and generates incorrect answers of the optimal level of difficulty based on that. For example, it presents difficult incorrect answers as a general review at the end of the school year. This makes it possible to provide incorrect answers of an appropriate level of difficulty appropriate to the student's age and grade.

[0064] The incorrect answer generation unit can use the emotion estimation function to monitor in real time how students feel about incorrect answers and generate optimal incorrect answers. The incorrect answer generation unit, for example, can use the emotion estimation function to monitor in real time how students feel about incorrect answers and generate optimal incorrect answers based on that data. For example, it can present incorrect answers that are likely to interest students. Furthermore, if a student feels negative emotions about an incorrect answer, the incorrect answer generation unit can use the emotion estimation function to generate an incorrect answer that alleviates those emotions. For example, it can present an incorrect answer that incorporates humor. Furthermore, the incorrect answer generation unit can use the emotion estimation function to devise a method for presenting incorrect answers so that students feel positive emotions about incorrect answers. For example, it can present incorrect answers in a game format, allowing students to learn while having fun. This makes it possible to provide optimal incorrect answers that correspond to the student's emotions.

[0065] When analyzing students' responses, generative AI can provide more detailed feedback by taking into account the speed and frequency of responses. For example, generative AI can analyze students' response speed and frequency and provide detailed feedback based on that data. For example, it can analyze how quickly students respond to questions and evaluate their level of understanding. Generative AI can also analyze students' response frequency and provide individualized feedback based on that data. For example, it can provide additional practice questions for questions that students frequently get wrong. Generative AI can also analyze students' response speed and frequency in real time and build a system that reports the results to teachers. For example, if a student responds slowly to a particular question, it can provide an explanation for that question. This allows for more detailed feedback to be provided by taking response speed and frequency into account.

[0066] The generative AI can use the emotion estimation function to provide emotional feedback based on the reactions of children and students, thereby improving their motivation. For example, the generative AI can use the emotion estimation function to provide emotional feedback based on the reactions of children and students. For example, if a child shows a happy expression, it can provide positive feedback to reinforce that emotion. The generative AI can also use the emotion estimation function to provide feedback to alleviate the child's negative emotions. For example, if a child shows a confused expression, it can identify the cause and provide a solution. The generative AI can also use the emotion estimation function to provide emotional feedback to improve the child's motivation. For example, it can provide feedback that makes the child feel a sense of accomplishment. This makes it possible to provide emotional feedback to improve the child's motivation.

[0067] When analyzing student responses, generative AI can also analyze responses in group activities and discussions. For example, generative AI can analyze responses in group activities and discussions and provide feedback based on that data. For example, it can analyze the frequency and content of comments within a group to evaluate the group's dynamics. Generative AI can also analyze responses in group activities and discussions in real time and build a system that reports the results to teachers. For example, it can analyze the level of cooperation and agreement within a group and notify the teacher. Generative AI can also analyze responses in group activities and discussions and provide individual feedback based on that data. For example, if a particular student does not speak up, it can identify the cause and provide a solution. This allows for more detailed feedback to be provided by analyzing responses in group activities and discussions.

[0068] When analyzing students' responses, generative AI can provide feedback tailored to different learning styles (visual, auditory, tactile). For example, generative AI can analyze students' learning styles and provide visual, auditory, and tactile feedback based on that data. For example, visual learners can be provided with feedback using diagrams and graphs. Generative AI can also analyze students' learning styles in real time and provide individualized feedback based on the results. For example, auditory learners can be provided with audio explanations. Generative AI can also analyze students' learning styles and provide practical feedback to tactile learners based on that data. For example, helping them understand the learning content through experiments and practical training. This makes it possible to provide feedback tailored to different learning styles.

[0069] The generative AI can use its emotion estimation function to propose individualized learning plans based on students' responses, maximizing learning effectiveness. For example, the generative AI uses its emotion estimation function to propose individualized learning plans based on students' responses. For example, it provides a learning plan that focuses on areas that students are interested in. The generative AI also uses its emotion estimation function to propose learning plans to alleviate students' negative responses. For example, it provides a step-by-step learning plan to help students overcome areas in which they are weak. The generative AI also uses its emotion estimation function to propose learning plans to improve students' motivation. For example, it provides a learning plan that includes goal setting that gives students a sense of accomplishment. This makes it possible to maximize learning effectiveness by proposing individualized learning plans.

[0070] When analyzing class characteristics, the generative AI can also take into account data such as past test results and attendance rates. For example, when analyzing class characteristics, the generative AI stores past test results in a database and optimizes lesson content based on that data. For example, it provides lessons that focus on areas where test results are low. The generative AI can also analyze class attendance rates and optimize lesson content based on that data. For example, it can provide lessons that focus on review on days when attendance is low. The generative AI can also analyze past test results and attendance rates in real time and build a system that optimizes lesson content based on the results. For example, it can provide additional practice questions for areas where test results are low. In this way, by taking past test results and attendance rates into consideration, it is possible to provide optimal lesson content according to the characteristics of a class.

[0071] When analyzing class characteristics, generative AI can also take into account the teacher's teaching style and the pace of the lesson. For example, generative AI can analyze a teacher's teaching style and provide lesson content tailored to the class's characteristics based on that data. For example, if a teacher prefers interactive lessons, it can provide teaching materials tailored to that style. Generative AI can also analyze the pace of the lesson and provide lesson content tailored to the class's characteristics based on that data. For example, it can provide advanced content for a class with a fast pace and basic content for a class with a slow pace. Generative AI can also analyze a teacher's teaching style and the pace of the lesson in real time and build a system that optimizes lesson content based on the results. For example, it can provide feedback tailored to the teacher's teaching style. This makes it possible to provide optimal lesson content tailored to the class's characteristics by taking into account the teacher's teaching style and the pace of the lesson.

[0072] The generative AI can use its emotion estimation function to analyze the emotional atmosphere of the entire class and optimize to create a positive learning environment. For example, the generative AI can use its emotion estimation function to analyze the emotional atmosphere of the entire class in real time and use that data to optimize to create a positive learning environment. For example, it can provide lesson content that helps the entire class relax. The generative AI can also use its emotion estimation function to optimize to alleviate negative emotions in the entire class. For example, if the entire class is feeling stressed, it can identify the cause and provide a solution. The generative AI can also use its emotion estimation function to optimize to reinforce positive emotions in the entire class. For example, it can provide lesson content that includes goal setting that makes the entire class feel a sense of accomplishment. This improves learning effectiveness by analyzing the emotional atmosphere of the entire class and optimizing to create a positive learning environment.

[0073] When analyzing the characteristics of a class, the generative AI can perform comparative analysis with classes in different schools and regions. For example, the generative AI collects data on classes in different schools and regions and performs comparative analysis based on that data. For example, it can analyze the academic ability differences between classes in the same grade and provide the optimal lesson content. The generative AI can also analyze the characteristics of classes in different regions and provide the optimal lesson content for each region based on that data. For example, it can provide different teaching materials for classes in urban and rural areas. The generative AI can also perform comparative analysis with classes in different schools and regions in real time and build a system that optimizes lesson content based on the results. For example, it can refer to lesson content that has been successful in other schools. This allows it to perform comparative analysis with classes in different schools and regions and provide the optimal lesson content according to the characteristics of the class.

[0074] When analyzing class characteristics, generative AI can also accommodate online and hybrid classes. For example, generative AI can analyze the characteristics of online and hybrid classes and provide optimal lesson content based on that data. For example, it can provide teaching materials and assignments suitable for online classes. Generative AI can also analyze the progress of online and hybrid classes in real time and build a system that optimizes lesson content based on the results. For example, it can evaluate the level of understanding in online classes. Generative AI can also analyze the characteristics of online and hybrid classes and provide individual feedback based on that data. For example, it can provide feedback based on participation in online classes. This makes it possible to accommodate online and hybrid classes, enabling flexible learning support.

[0075] The generative AI can automatically highlight important keywords and phrases when summarizing lesson content. For example, the generative AI adds a function to automatically highlight important keywords and phrases when summarizing lesson content. For example, important words in the summary text are displayed in bold or color. The generative AI also adds a function to automatically list important points when summarizing lesson content. For example, important points are displayed in bullet points at the end of the summary text. The generative AI also adds a function to automatically highlight important keywords and phrases when summarizing lesson content. For example, important parts of the summary text are highlighted with a background color. This makes it easier for students to grasp the important points by highlighting important keywords and phrases when summarizing lesson content.

[0076] When summarizing lesson content, the generation AI can provide customized summaries based on the students' level of understanding. For example, the generation AI can analyze the students' level of understanding and provide customized summaries based on that data. For example, it can provide detailed summaries for students with low levels of understanding and concise summaries for students with high levels of understanding. The generation AI can also analyze the students' level of understanding in real time and build a system that provides individual customized summaries based on the results. For example, it can automatically generate summary text based on the students' level of understanding. The generation AI can also analyze the students' level of understanding and provide customized summaries based on that data. For example, it can provide summaries that focus on areas where the students have low levels of understanding. This improves learning effectiveness by providing customized summaries based on the students' level of understanding.

[0077] The generation AI can use the emotion estimation function to analyze students' emotional reactions to the summary content and generate summaries that elicit positive reactions. For example, the generation AI can use the emotion estimation function to analyze students' emotional reactions to the summary content in real time and generate summaries that elicit positive reactions based on that data. For example, it can provide summaries that are likely to interest students. The generation AI can also use the emotion estimation function to generate summaries that alleviate negative reactions to the summary content. For example, it can provide summaries that are easy to understand so that students are not confused. The generation AI can also use the emotion estimation function to generate summaries that reinforce positive emotions toward the summary content. For example, it can provide summaries that make students feel a sense of accomplishment. In this way, learning effectiveness is improved by analyzing students' emotional reactions and generating summaries that elicit positive reactions.

[0078] When summarizing class content, generative AI can automatically translate it into different languages ​​and provide summaries in multiple languages. For example, when summarizing class content, generative AI adds a function to automatically translate it into different languages. For example, it can provide summaries translated into multiple languages, such as English and Chinese. Furthermore, when summarizing class content, generative AI can automatically translate it into different languages ​​and build a system that provides summaries in multiple languages ​​based on the translation results. For example, it can develop an algorithm to improve translation accuracy. Furthermore, when summarizing class content, generative AI can automatically translate it into different languages ​​and provide summaries in multiple languages ​​based on the translation results. For example, it can combine summaries in different languages ​​into a single document. This makes it possible to support international learning by automatically translating it into different languages ​​and providing summaries in multiple languages.

[0079] When summarizing class content, generative AI can provide summaries in visual note or mind map format. For example, when summarizing class content, generative AI will add a function to provide summaries in visual note format. For example, it will visually represent important points with diagrams and illustrations. Furthermore, when summarizing class content, generative AI will add a function to provide summaries in mind map format. For example, it will display related information in a branched format centered around the main topic of the class content. Furthermore, generative AI will build a system that provides summaries in visual note or mind map format when summarizing class content. For example, it will develop an algorithm that automatically visualizes summary text. This will allow summaries to be provided in visual note or mind map format, making it easier to understand visually.

[0080] The generation AI can use the emotion estimation function to monitor students' emotional reactions to the summary content in real time and provide the optimal summary. For example, the generation AI can use the emotion estimation function to monitor students' emotional reactions to the summary content in real time and provide the optimal summary based on that data. For example, it can provide a summary that is likely to interest students. The generation AI can also use the emotion estimation function to provide a summary that alleviates negative reactions to the summary content. For example, it can provide an easy-to-understand summary so that students are not confused. The generation AI can also use the emotion estimation function to provide a summary that reinforces positive emotions toward the summary content. For example, it can provide a summary that makes students feel a sense of accomplishment. In this way, the generation AI can monitor students' emotional reactions in real time and provide the optimal summary, thereby improving learning effectiveness.

[0081] When presenting incorrect answers in educational programs, generative AI can customize them according to the viewer's age group and interests. For example, when presenting incorrect answers in educational programs, generative AI customizes them according to the viewer's age group. For example, it might present easy incorrect answers to elementary school students and more difficult incorrect answers to junior high school students. When presenting incorrect answers in educational programs, generative AI also customizes them according to the viewer's interests. For example, it might present science questions to viewers interested in science, and history questions to viewers interested in history. Furthermore, generative AI builds a system that customizes incorrect answers in educational programs according to the viewer's age group and interests. For example, it might generate the optimal incorrect answer based on the viewer's profile data. This allows for customization according to the viewer's age group and interests, maximizing the effectiveness of educational programs.

[0082] When presenting incorrect answers in educational programs, generative AI can introduce an interactive quiz format that matches the progress of the program. For example, when presenting incorrect answers in educational programs, generative AI introduces an interactive quiz format. For example, it allows viewers to select the answer using a remote control or smartphone. Furthermore, when presenting incorrect answers in educational programs, generative AI introduces a quiz format that matches the progress of the program. For example, it could ask a quiz question in a specific segment of the program, allowing viewers to participate in real time. Furthermore, generative AI could build a system that introduces an interactive quiz format when presenting incorrect answers in educational programs. For example, it could collect viewer response data in real time and reflect it in the progress of the program. This could increase viewer participation by introducing an interactive quiz format that matches the progress of the program.

[0083] The generative AI can use its emotion estimation function to analyze viewers' emotional responses in real time and optimize program content. For example, the generative AI can use its emotion estimation function to analyze viewers' emotional responses in real time and optimize program content based on that data. For example, it can change the content to make it more appealing to viewers. The generative AI can also use its emotion estimation function to provide program content that alleviates viewers' negative emotions. For example, it can add easy-to-understand explanations so viewers don't get confused. The generative AI can also use its emotion estimation function to provide program content that reinforces viewers' positive emotions. For example, it can add quizzes and challenges that give viewers a sense of accomplishment. In this way, the generative AI can analyze viewers' emotional responses in real time and optimize program content, thereby improving viewer satisfaction.

[0084] Generative AI can enable use across different media (television, online, radio) when presenting incorrect answers in educational programs. For example, generative AI can enable incorrect answers in educational programs to be used not only on television but also online and radio. For example, it can provide quiz-style questions on online platforms. Generative AI can also build a system that enables use across different media when presenting incorrect answers in educational programs. For example, it can provide audio quizzes on radio programs. Generative AI can also develop an interface that enables use across different media when presenting incorrect answers in educational programs. For example, it can link television programs with online platforms. This can maximize the effectiveness of educational programs by enabling use across different media.

[0085] The generative AI can use its emotion estimation function to monitor viewers' emotional responses in real time and propose optimal program progression. For example, the generative AI can use its emotion estimation function to monitor viewers' emotional responses in real time and propose optimal program progression based on that data. For example, it can change the content to make it more appealing to viewers. The generative AI can also use its emotion estimation function to propose program progression that will alleviate viewers' negative emotions. For example, it can add easy-to-understand explanations so viewers don't get confused. The generative AI can also use its emotion estimation function to propose program progression that will reinforce viewers' positive emotions. For example, it can add quizzes or challenges that will give viewers a sense of accomplishment. In this way, the generative AI can monitor viewers' emotional responses in real time and propose optimal program progression, thereby improving viewer satisfaction.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The educational support system may further include a learning progress tracking unit. The learning progress tracking unit tracks the learning progress of students in real time and provides feedback according to the progress. For example, if a student is struggling with a particular unit, the learning progress tracking unit may provide additional practice questions related to that unit. The learning progress tracking unit may also visually display the student's learning progress in graphs or charts, making it easy for teachers and parents to understand the progress. Furthermore, the learning progress tracking unit may suggest individual learning plans based on the student's learning progress. For example, if the student's understanding is low in a particular area, the learning progress tracking unit may suggest a learning plan that focuses on that area. This makes it possible to effectively manage the student's learning progress and meet the individual learning needs of the student.

[0088] The educational support system can further include a learning style adaptation unit. The learning style adaptation unit analyzes the learning style (visual, auditory, tactile) of each student and provides learning materials and feedback appropriate to that style. For example, visual learners can be provided with learning materials that make extensive use of diagrams and graphs, while auditory learners can be provided with audio commentary. Tactile learners can also be helped to understand the learning content through experiments and practical training. Furthermore, the learning style adaptation unit can analyze each student's learning style in real time and provide individual feedback based on the results. For example, it can automatically generate exercises and assignments appropriate to each student's learning style. This makes it possible to provide an optimal learning environment appropriate to each student's learning style.

[0089] The educational support system can further include a collaborative learning support unit. The collaborative learning support unit supports students when they study cooperatively in groups. For example, it can automatically suggest role assignments within the group and promote learning activities that make use of each member's strengths. The collaborative learning support unit can also provide tools to promote communication within the group. For example, online chat and video conferencing functions can be used to smoothly communicate with members in remote locations. Furthermore, the collaborative learning support unit can monitor the learning progress within the group in real time and provide feedback as needed. This can maximize the effectiveness of collaborative learning and improve students' teamwork and communication skills.

[0090] The educational support system can also use the emotion estimation function to provide feedback to improve students' motivation. For example, the emotion estimation function can be used to analyze in real time the stress and anxiety students feel while studying and provide feedback to alleviate those emotions. For example, the emotion estimation function could display an encouraging message such as, "You're doing great! You're almost there!". The emotion estimation function can also be used to provide feedback that makes students feel a sense of accomplishment. For example, when a specific task is completed, a positive message such as, "Great! Let's move on to the next step!" can be displayed. Furthermore, the emotion estimation function can be used to incorporate game elements to improve students' motivation. For example, a system could be introduced that allows students to earn points and badges according to their learning progress. This allows students to enjoy learning.

[0091] The educational support system can further include an intercultural understanding promotion unit. The intercultural understanding promotion unit supports students in interacting with and deepening understanding of people from different cultures and backgrounds. For example, the intercultural understanding promotion unit may collaborate online with schools in different countries and regions to provide a platform where students can interact with each other. The intercultural understanding promotion unit may also provide information and teaching materials about different cultures, allowing students to learn while comparing them with their own culture. Furthermore, the intercultural understanding promotion unit may provide tools to resolve communication challenges that arise during intercultural exchange. For example, it may use translation functions or multilingual chat tools to support communication across language barriers. This allows students to understand different cultures and develop a global perspective.

[0092] The education support system can further use the emotion estimation function to provide customized study plans to increase students' motivation to learn. For example, the emotion estimation function can be used to analyze students' emotions toward specific subjects or topics and adjust the study plan based on those emotions. For example, a study plan focusing on areas of interest to the student can be provided. If a student has negative feelings about learning, the emotion estimation function can also be used to suggest a study plan to alleviate those feelings. For example, the difficulty level can be adjusted or the learning method can be changed to help students develop positive feelings about learning. Furthermore, the emotion estimation function can be used to set goals to increase students' motivation to learn. For example, a plan can be provided that sets short-term and long-term goals and progresses students' learning step by step toward those goals. This allows students to progress through their studies at their own pace.

[0093] The educational support system can further include a parent-teacher collaboration unit. The parent-teacher collaboration unit shares information about students' learning status with parents and promotes learning support at home. For example, the parent-teacher collaboration unit may provide parents with regular reports on students' learning progress and grades. The parent-teacher collaboration unit may also provide advice and resources for parents to support their students at home. For example, it may provide information on how to create a learning environment at home and effective learning methods. The parent-teacher collaboration unit may also provide communication tools that enable parents and teachers to collaborate to support students' learning. For example, parents and teachers may use online interviews or chat functions to regularly share information and understand students' learning status. This allows homes and schools to work together to support students' learning.

[0094] The educational support system can also use the emotion estimation function to monitor students' stress levels and suggest appropriate relaxation methods. For example, the emotion estimation function can be used to analyze the stress students feel while studying in real time and suggest relaxation methods based on that data. For example, simple relaxation methods such as deep breathing and stretching can be suggested. The emotion estimation function can also be used to identify the causes of students' stress and provide advice to address those causes. For example, advice can be provided on improving the learning environment and time management methods. Furthermore, the emotion estimation function can be used to monitor students' stress levels and encourage them to take breaks as needed. This allows students to study without feeling stressed.

[0095] The education support system can further include a career support unit. The career support unit supports students when they think about their future careers. For example, the career support unit may suggest appropriate occupations and career paths based on the students' interests and aptitudes. The career support unit can also provide learning plans that help students set future goals and acquire the skills and knowledge necessary to achieve them. For example, the career support unit may show them the steps to acquire the qualifications and skills necessary for a specific occupation. The career support unit can also provide students with opportunities to think about their future careers through actual work experience. For example, the career support unit may provide opportunities for internships and workplace visits. The career support unit can also provide online counseling services that allow students to consult about their future careers. This allows students to think about their future and set specific goals.

[0096] The educational support system can also use emotion estimation to analyze students' emotional responses to learning and provide feedback to provide a positive learning experience. For example, the emotion estimation function can be used to analyze in real time the joy and sense of accomplishment students feel while learning and provide feedback to reinforce those emotions. For example, a positive message such as "Great! Keep it up!" can be displayed. Furthermore, if a student has negative feelings about learning, the emotion estimation function can be used to provide feedback to alleviate those feelings. For example, an encouraging message such as "It's okay, let's take it one step at a time" can be displayed. Furthermore, the emotion estimation function can be used to incorporate game elements to make students' learning experiences more positive. For example, a system can be introduced that allows students to earn points and badges according to their learning progress. This allows students to enjoy learning.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The incorrect answer generator generates intentionally incorrect answers to questions entered by the teacher. For example, the generator AI generates an incorrect answer such as "2 + 2 = 5" for a math problem. The generator AI can also present an incorrect date for a history question. Furthermore, the generator AI can present an incorrect experimental procedure for a science question. Step 2: The reaction analysis unit analyzes the student's reaction to the incorrect answer generated by the incorrect answer generation unit. For example, the reaction analysis unit may capture the student's facial expression with a camera and analyze the reaction using an emotion estimation algorithm. The reaction analysis unit may also record the student's voice and analyze the reaction using voice analysis technology. Furthermore, the reaction analysis unit may collect the student's behavior with a sensor and analyze the reaction using a behavior analysis algorithm. Step 3: The optimization unit optimizes the characteristics of the class based on the responses analyzed by the response analysis unit. For example, the optimization unit analyzes the academic level of the class and provides lesson content appropriate to that level. The optimization unit can also analyze the interests of the class and provide lesson content appropriate to those interests. Furthermore, the optimization unit can analyze the learning style of the class and provide lesson content appropriate to that style. Step 4: The summarization unit summarizes the lesson content optimized by the optimization unit. For example, the summarization unit can extract the main topics of the lesson and summarize them concisely. The summarization unit can also list the important points of the lesson. Furthermore, the summarization unit can summarize the lesson content in the form of visual notes or mind maps.

[0099] 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.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] 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.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 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.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0166] 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. an incorrect answer generation unit that generates intentionally incorrect answers to questions input by a teacher; a reaction analysis unit that analyzes the reaction of students to the incorrect answers generated by the incorrect answer generation unit; an optimization unit that optimizes the characteristics of the class based on the reaction analyzed by the reaction analysis unit; a summarizing unit that summarizes the lesson content optimized by the optimization unit; A system characterized by:

2. The incorrect answer generation unit Analyze the past answer history of the student and generate the most effective incorrect answer for each student.

2. The system of claim 1.

3. The incorrect answer generation unit Generate multiple incorrect answers and have the student choose the correct answer from them 2. The system of claim 1.

4. The incorrect answer generation unit Analyze how the student feels about incorrect answers and generate incorrect answers that elicit positive emotional responses.

2. The system of claim 1.

5. The incorrect answer generation unit To be able to accommodate different subjects and courses 2. The system of claim 1.

Images