System

Abstract

An object of a system according to an embodiment is to provide high-quality learning support in response to individual learning needs of students.SOLUTION: A system according to an embodiment includes a question reception unit, an advice generation unit, an instruction generation unit, an effect measurement unit, a model answer generation unit, and a visual information generation unit. The question reception unit receives a question from a student. The advice generation unit generates advice based on the question received by the question reception unit. The guidance generation unit generates learning guidance based on the advice generated by the advice generation unit. The effect measurement unit measures the effect based on the instruction generated by the instruction generation unit. The model answer generation unit generates a model answer based on the effect measured by the effect measurement unit. The visual information generation unit generates visual information based on the model answer generated by the model answer generation 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 technologies do not adequately provide personalized learning support to address students' individual learning needs, and there is room for improvement.

[0005] The system according to the embodiment aims to respond to the individual learning needs of students and provide high-quality learning support. [Means for solving the problem]

[0006] The system according to the embodiment includes a question receiving unit, an advice generating unit, a guidance generating unit, an effectiveness measuring unit, a model answer generating unit, and a visual information generating unit. The question receiving unit receives questions from students. The advice generating unit generates advice based on the questions received by the question receiving unit. The guidance generating unit generates learning guidance based on the advice generated by the advice generating unit. The effectiveness measuring unit measures effectiveness based on the guidance generated by the guidance generating unit. The model answer generating unit generates a model answer based on the effectiveness measured by the effectiveness measuring unit. The visual information generating unit generates visual information based on the model answer generated by the model answer generating unit. [Effects of the Invention]

[0007] The system according to the embodiment can respond to the individual learning needs of students and provide high-quality learning support. [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 learning support chatbot according to an embodiment of the present invention is a system in which a generative AI responds to questions and learning difficulties written by students and provides advice and explanations. This allows the learning support chatbot to be customized to meet the individual learning needs of each student and to provide advice and explanations on demand.

[0029] A learning support chatbot according to an embodiment includes a question receiving unit, an advice generating unit, a teaching generation unit, an effectiveness measurement unit, a model answer generating unit, and a visual information generating unit. The question receiving unit receives questions from students. For example, the questions can be received in text format or audio format. The question receiving unit can also receive questions about specific subjects. The advice generating unit generates advice based on the questions received by the question receiving unit. For example, the generation AI provides advice on appropriate learning methods and problem-solving procedures in response to the student's questions. The generation AI can also provide advice tailored to the student's learning style. The teaching generation unit generates learning guidance based on the advice generated by the advice generating unit. For example, the generation AI provides appropriate teaching content based on the student's learning progress and level of understanding. The generation AI can also provide teaching methods tailored to the student's learning style. The effectiveness measurement unit measures effectiveness based on the guidance generated by the teaching generation unit. For example, the generation AI analyzes the results of practice problems solved by the student to measure learning effectiveness. The generation AI can also analyze students' answer patterns, identify weak points, and provide focused instruction. The model answer generation unit generates model answers based on the effectiveness measured by the effectiveness measurement unit. For example, the generation AI provides model answers for questions submitted by students. The generation AI can also provide detailed explanations and supplementary information for students' answers. The visual information generation unit generates visual information based on the model answers generated by the model answer generation unit. For example, the generation AI can use an auxiliary app to incorporate diagrams, tables, illustrations, etc. to provide visually easy-to-understand explanations. The generation AI can also customize the layout of diagrams, tables, and illustrations to make them easier for students to understand. As a result, the learning support chatbot according to the embodiment can provide learning support by providing appropriate advice and guidance in response to students' questions, measuring effectiveness, generating model answers, and providing visual information.

[0030] The question reception unit analyzes students' past question history and can provide optimal advice for each individual student. For example, the question reception unit stores the history of questions that students have previously asked the generation AI in a database and analyzes that data. For example, it can identify topics that specific students repeatedly ask about and provide detailed advice on those topics. It can also analyze the question history to understand the student's learning style and level of understanding. For example, it can provide advice using diagrams and tables to students for whom visual explanations are effective. It can also evaluate the effectiveness of advice provided in the past based on the student's question history and generate optimal advice. For example, if previous advice was effective, it can use that method again. In this way, by analyzing students' past question history, it can provide optimal advice for each individual student.

[0031] The advice generation unit can generate advice that suits a student's learning style. For example, the advice generation unit grasps a student's learning style in advance through questionnaires or tests, and customizes advice based on that information. For example, it can provide explanations that make extensive use of diagrams and graphs to visual learners. It also provides an interface that allows students to select advice that suits their learning style when asking questions to the generation AI. For example, it can provide an option to provide audio commentary to auditory learners. It also builds a system that automatically adjusts the format of advice according to the student's learning style. For example, it can provide interactive simulations to tactile learners. This makes it possible to provide advice that suits each student's learning style.

[0032] The question receiving unit can automatically suggest related videos or audio commentaries in response to students' questions. For example, when a student inputs a question, the question receiving unit has the generation AI automatically search for and suggest related videos and audio commentaries. For example, an explanatory video is provided for a math problem. Furthermore, a system can be constructed in which the generation AI selects the most appropriate video or audio commentary based on the content of the question and presents it to the student. For example, a documentary video is suggested for a question about historical events. Furthermore, an interface is provided that displays related videos and audio commentaries in real time when a student inputs a question. For example, an audio commentary is instantly played for a question about English grammar. This makes it possible to automatically suggest related videos and audio commentaries in response to students' questions.

[0033] The question acceptance unit can also support voice input and handwriting input when students input questions. For example, the question acceptance unit builds a system that supports voice input when students input questions. For example, a question can be input by voice using a microphone, and the generation AI analyzes the voice and provides advice. In addition, an interface that supports handwriting input can be provided, allowing students to input questions by hand. For example, a tablet can be used to input handwritten mathematical formulas and diagrams, and the generation AI can analyze them. In addition, an interface that combines voice input and handwriting input can be provided, allowing students to input questions in the way that is most convenient for them. For example, a question can be input by voice, and supplementary information can be added by hand. This makes it possible to support both voice input and handwriting input when students input questions.

[0034] The instruction generation unit can evaluate students' level of understanding in real time and adjust the instruction content based on that. For example, as students study, the generation AI evaluates their level of understanding in real time and adjusts the instruction content based on the results. For example, if their level of understanding is low, it will explain the material again from the basics. In addition, to evaluate their level of understanding, the generation AI will regularly conduct quizzes and tests and adjust the instruction content based on the results. For example, if their level of understanding is low on a particular topic, it will provide additional practice questions. In addition, a system will be built that monitors students' level of understanding in real time and adjusts the instruction content as necessary. For example, if their level of understanding is high, it will provide the next level of content. This makes it possible to evaluate students' level of understanding in real time and adjust the instruction content based on that.

[0035] The instruction generation unit can automatically suggest what content should be learned next according to the student's learning progress. For example, the instruction generation unit builds a system in which the generation AI monitors the student's learning progress in real time and automatically suggests what content should be learned next. For example, the next unit may be suggested after a specific unit is completed. The generation AI also automatically generates an optimal learning plan according to the student's learning progress and presents it to the student. For example, it may set weekly learning goals and suggest learning content based on those. It may also analyze the student's learning progress and provide an interface that suggests what content should be learned next. For example, it may provide questions with difficulty adjusted according to the student's progress. This makes it possible to automatically suggest what content should be learned next according to the student's learning progress.

[0036] The instruction generation unit can provide students with an interactive learning experience using virtual reality or augmented reality when they are studying. The instruction generation unit, for example, builds a system that provides students with an interactive learning experience using VR or AR when they are studying. For example, virtual reality is used in a history class to experience past events. VR and AR are also used to provide content that allows students to learn while actually experiencing it. For example, a science experiment is reproduced in virtual reality so that students can experience the experiment. Interactive teaching materials using VR and AR are also provided to students when they are studying. For example, a math problem is visually explained using augmented reality. This makes it possible to provide students with an interactive learning experience using virtual reality or augmented reality when they are studying.

[0037] The instruction generation unit can provide a group chat function to promote collaborative learning with other students when students are studying. The instruction generation unit, for example, builds a system that provides a group chat function to promote collaborative learning with other students when students are studying. For example, it provides a chat room where students studying the same topic can exchange opinions. It also uses the group chat function to support students when they are studying collaboratively. For example, the generation AI answers questions and offers advice within the chat. It also provides a group chat function to promote collaborative learning with other students when students are studying, and shares their learning progress. For example, it sets learning goals within a group and reports progress to each other. This makes it possible to provide a group chat function to promote collaborative learning with other students when students are studying.

[0038] The effectiveness measurement unit can analyze students' answer patterns, identify weak points, and provide focused instruction. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the answer patterns of practice problems solved by students and identifies weak points. For example, if there are many mistakes on a specific question format, instruction will be focused on questions of that format. The answer patterns will also be analyzed to identify students' weak points and provide focused instruction. For example, if there is a lack of understanding of a specific topic, additional practice problems related to that topic will be provided. A system will also be developed that analyzes students' answer patterns in real time, identifies weak points, and provides focused instruction. For example, immediate feedback will be provided for questions that were answered incorrectly, encouraging the student to try again. This will enable the system to analyze students' answer patterns, identify weak points, and provide focused instruction.

[0039] The effectiveness measurement unit can analyze students' response times and provide time management advice. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the response times of practice problems solved by students and provides time management advice. For example, if a particular problem takes too long, it will suggest an efficient way to solve it. It will also analyze the response times and provide time management advice to students. For example, it will suggest which problem to start with when solving an exam. It will also develop a system that analyzes students' response times in real time and provides time management advice. For example, it will teach time management techniques for problems that take a long time to solve. This will allow it to analyze students' response times and provide time management advice.

[0040] The effectiveness measurement unit can provide feedback by comparing the results of problems solved by students with other students. For example, the effectiveness measurement unit constructs a system in which a generation AI analyzes the results of problems solved by students and provides feedback by comparing them with other students. For example, feedback is provided by comparing the results with the average score of other students who solved the same problem. The unit also compares the results of problems with other students and provides feedback to the student. For example, the unit displays the correct answer rate for a specific problem in comparison with other students. The unit also develops a system that analyzes the results of students' problems in real time and provides feedback by comparing them with other students. For example, feedback is provided by comparing the answer time of other students who solved the same problem. This makes it possible to provide feedback by comparing the results of problems solved by students with other students.

[0041] The effectiveness measurement unit can provide a function to automatically report the results of problems solved by students to parents and teachers. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the results of problems solved by students and automatically reports the results to parents and teachers. For example, it will periodically send learning progress reports by email. It will also provide a function to automatically report the results of problems solved to parents and teachers. For example, it will report the percentage of correct answers and the time it took to solve the problems solved by students. It will also develop a system that analyzes the results of students' problems in real time and automatically reports the results to parents and teachers. For example, it will display learning progress in a graph and share it with parents and teachers. This will provide a function to automatically report the results of problems solved by students to parents and teachers.

[0042] The model answer generation unit can analyze student answers and provide the most suitable model answer for each individual student. For example, the model answer generation unit will build a system in which a generation AI analyzes answers submitted by students and provides the most suitable model answer for each individual student. For example, it will point out errors in the answer and present the correct answer. It will also analyze student answers and provide the most suitable model answer for each individual student. For example, it will provide a detailed explanation of the answering process to deepen understanding. It will also develop a system that analyzes student answers in real time and provides the most suitable model answer for each individual student. For example, it will immediately point out errors in the answer and encourage the student to try again. This will allow it to analyze student answers and provide the most suitable model answer for each individual student.

[0043] The model answer generation unit can provide detailed explanations and supplementary information for students' answers. For example, the model answer generation unit will build a system in which the generation AI provides detailed explanations and supplementary information for answers submitted by students. For example, it will explain the process of the answer step by step. It will also provide detailed explanations and supplementary information for the answer. For example, it will explain related topics and background knowledge to deepen understanding. It will also develop a system that provides detailed explanations and supplementary information for students' answers in real time. For example, it will point out errors in the answer and present the correct answer. This will allow it to provide detailed explanations and supplementary information for students' answers.

[0044] The model answer generation unit can provide multiple model answers to problems submitted by students, allowing them to be compared and considered. For example, the model answer generation unit builds a system in which a generation AI provides multiple model answers to problems submitted by students. For example, different solutions may be presented, allowing students to compare and consider them. In addition, multiple model answers may be provided to problems, allowing students to compare and consider them. For example, answers from different perspectives may be presented to deepen understanding. In addition, a system may be developed in which multiple model answers are provided in real time to problems submitted by students. For example, different solutions may be presented instantly, allowing students to compare and consider them. This allows multiple model answers to be provided to problems submitted by students, allowing them to compare and consider them.

[0045] The model answer generation unit can also provide example answers from other students for reference to questions submitted by students. For example, the model answer generation unit will build a system in which the generation AI provides example answers from other students to questions submitted by students. For example, it will present excellent example answers so that students can use them as reference. It will also provide example answers from other students to questions so that students can use them as reference. For example, it will present answers from different perspectives to deepen understanding. It will also develop a system that provides example answers from other students in real time to questions submitted by students. For example, it will instantly present excellent example answers so that students can use them as reference. This will make it possible to provide example answers from other students as reference to questions submitted by students.

[0046] The visual information generation unit can automatically generate optimal diagrams, tables, and illustrations according to the student's learning content. For example, the visual information generation unit will build a system in which the generation AI analyzes the student's learning content and automatically generates optimal diagrams, tables, and illustrations. For example, it will automatically generate graphs for math problems. It will also automatically generate optimal diagrams, tables, and illustrations according to the learning content. For example, it will automatically generate illustrations of historical events and provide them to students. It will also develop a system that analyzes the student's learning content in real time and automatically generates optimal diagrams, tables, and illustrations. For example, it will show the results of a science experiment in a graph. This will make it possible to automatically generate optimal diagrams, tables, and illustrations according to the student's learning content.

[0047] The visual information generation unit can customize the layout of figures, tables, and illustrations to make them easier for students to understand. For example, the visual information generation unit will build a system in which the generative AI customizes the layout of figures, tables, and illustrations to make them easier for students to understand. For example, it will highlight important information. It will also customize the layout of figures, tables, and illustrations to make them easier for students to understand. For example, it will adjust colors and fonts to make them visually easier to understand. It will also develop a system that customizes the layout of figures, tables, and illustrations according to students' learning styles. For example, it will provide larger figures for visual learners. This will allow the layout of figures, tables, and illustrations to be customized to make them easier for students to understand.

[0048] The visual information generation unit can provide interactive diagrams, tables, and illustrations that students can manipulate as they study. For example, the visual information generation unit will build a system in which a generative AI provides interactive diagrams, tables, and illustrations as students study. For example, clicking on a data point on a graph will display detailed information. The unit will also provide interactive diagrams, tables, and illustrations that students can manipulate. For example, they can drag and move parts of an illustration. The unit will also develop a system that provides interactive diagrams, tables, and illustrations in real time as students study. For example, they can enlarge part of a diagram to display details. This will allow the unit to provide interactive diagrams, tables, and illustrations as students study and manipulate them.

[0049] The visual information generation unit can provide a function that allows students to share diagrams, tables, and illustrations with other students as they study, and to study collaboratively. For example, the visual information generation unit builds a system that allows students to share diagrams, tables, and illustrations with other students as they study, and to provide a function that allows them to study collaboratively. For example, they can hold discussions while looking at the same diagram. The unit also provides a function that allows diagrams, tables, and illustrations to be shared with other students and to study collaboratively. For example, it provides an interactive whiteboard that can be edited collaboratively. The unit also develops a function that allows students to share diagrams, tables, and illustrations with other students in real time as they study, and to study collaboratively. For example, they can add comments in real time while looking at the same diagram. This makes it possible to provide a function that allows students to share diagrams, tables, and illustrations with other students as they study, and to study collaboratively.

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

[0051] The question acceptance unit can also support voice input and handwriting input when students enter questions. For example, a system can be built that supports voice input when students enter questions. For example, a microphone can be used to enter questions by voice, and the generation AI can analyze the voice and provide advice. An interface that supports handwriting input can also be provided, allowing students to enter questions by hand. For example, a tablet can be used to enter handwritten mathematical formulas and diagrams, which the generation AI can analyze. An interface that combines voice input and handwriting input can also be provided, allowing students to enter questions in the way that is most convenient for them. For example, a question can be entered by voice, and supplementary information can be added by hand. This makes it possible to support both voice input and handwriting input when students enter questions.

[0052] The instruction generation unit can evaluate students' level of understanding in real time and adjust the instruction content based on that. For example, as students study, the generation AI evaluates their level of understanding in real time and adjusts the instruction content based on the results. For example, if their level of understanding is low, it will explain the material again from the basics. In addition, to evaluate their level of understanding, the generation AI will periodically conduct quizzes and tests and adjust the instruction content based on the results. For example, if their level of understanding is low on a particular topic, it will provide additional practice questions. We will also build a system that monitors students' level of understanding in real time and adjusts the instruction content as necessary. For example, if their level of understanding is high, it will provide the next level of content. This makes it possible to evaluate students' level of understanding in real time and adjust the instruction content based on that.

[0053] The effectiveness measurement department can analyze students' answer patterns, identify their weak points, and provide focused instruction. For example, we will build a system in which a generation AI analyzes the answer patterns of practice problems solved by students and identifies their weak points. For example, if there are many mistakes made on a specific question format, instruction will be focused on questions of that format. We will also analyze answer patterns to identify students' weak points and provide focused instruction. For example, if there is a lack of understanding of a specific topic, we will provide additional practice problems related to that topic. We will also develop a system that analyzes students' answer patterns in real time, identifies their weak points, and provides focused instruction. For example, we will provide instant feedback on questions that were answered incorrectly, encouraging the student to try again. This will enable us to analyze students' answer patterns, identify their weak points, and provide focused instruction.

[0054] The model answer generation unit can analyze students' answers and provide the most suitable model answer for each individual student. For example, we will build a system in which a generation AI analyzes answers submitted by students and provides the most suitable model answer for each individual student. For example, it will point out errors in the answer and present the correct answer. We will also analyze students' answers and provide the most suitable model answer for each individual student. For example, it will provide a detailed explanation of the answering process to deepen understanding. We will also develop a system that analyzes students' answers in real time and provides the most suitable model answer for each individual student. For example, it will immediately point out errors in the answer and encourage the student to try again. This will allow us to analyze students' answers and provide the most suitable model answer for each individual student.

[0055] The visual information generation unit can automatically generate optimal diagrams, tables, and illustrations according to the student's learning content. For example, we will build a system in which the generation AI analyzes the student's learning content and automatically generates the optimal diagrams, tables, and illustrations. For example, graphs can be automatically generated for math problems. We will also automatically generate optimal diagrams, tables, and illustrations according to the learning content. For example, we will automatically generate illustrations of historical events and provide them to students. We will also develop a system that analyzes the student's learning content in real time and automatically generates the optimal diagrams, tables, and illustrations. For example, we can show the results of a science experiment in a graph. This will make it possible to automatically generate the optimal diagrams, tables, and illustrations according to the student's learning content.

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

[0057] Step 1: The question reception unit receives questions from students. For example, questions can be received in text format or audio format. The question reception unit can also receive questions about specific subjects. Step 2: The advice generator generates advice based on the question received by the question receiver. For example, the generator AI provides advice on appropriate study methods and problem-solving procedures in response to the student's question. The generator AI can also provide advice tailored to the student's learning style. Step 3: The instruction generation unit generates learning instruction based on the advice generated by the advice generation unit. For example, the generation AI provides appropriate instruction content according to the student's learning progress and level of understanding. The generation AI can also provide instruction methods that suit the student's learning style. Step 4: The effectiveness measurement unit measures the effectiveness of the instruction generated by the instruction generation unit. For example, the generation AI analyzes the results of practice problems solved by students and measures their learning effectiveness. The generation AI can also analyze students' answer patterns to identify weak points and provide focused instruction. Step 5: The model answer generator generates a model answer based on the effectiveness measured by the effectiveness measurement unit. For example, the generation AI provides a model answer for the question submitted by the student. The generation AI can also provide detailed explanations and supplementary information for the student's answer. Step 6: The visual information generation unit generates visual information based on the model answer generated by the model answer generation unit. For example, the generation AI can use a support app to incorporate diagrams, tables, illustrations, etc. to provide a visually easy-to-understand explanation. The generation AI can also customize the layout of the diagrams, tables, and illustrations to make them easier for students to understand.

[0058] (Example 2) The learning support chatbot according to an embodiment of the present invention is a system in which a generative AI responds to questions and learning difficulties written by students and provides advice and explanations. This allows the learning support chatbot to be customized to meet the individual learning needs of each student and to provide advice and explanations on demand.

[0059] A learning support chatbot according to an embodiment includes a question receiving unit, an advice generating unit, a teaching generation unit, an effectiveness measurement unit, a model answer generating unit, and a visual information generating unit. The question receiving unit receives questions from students. For example, the questions can be received in text format or audio format. The question receiving unit can also receive questions about specific subjects. The advice generating unit generates advice based on the questions received by the question receiving unit. For example, the generation AI provides advice on appropriate learning methods and problem-solving procedures in response to the student's questions. The generation AI can also provide advice tailored to the student's learning style. The teaching generation unit generates learning guidance based on the advice generated by the advice generating unit. For example, the generation AI provides appropriate teaching content based on the student's learning progress and level of understanding. The generation AI can also provide teaching methods tailored to the student's learning style. The effectiveness measurement unit measures effectiveness based on the guidance generated by the teaching generation unit. For example, the generation AI analyzes the results of practice problems solved by the student to measure learning effectiveness. The generation AI can also analyze students' answer patterns, identify weak points, and provide focused instruction. The model answer generation unit generates model answers based on the effectiveness measured by the effectiveness measurement unit. For example, the generation AI provides model answers for questions submitted by students. The generation AI can also provide detailed explanations and supplementary information for students' answers. The visual information generation unit generates visual information based on the model answers generated by the model answer generation unit. For example, the generation AI can use an auxiliary app to incorporate diagrams, tables, illustrations, etc. to provide visually easy-to-understand explanations. The generation AI can also customize the layout of diagrams, tables, and illustrations to make them easier for students to understand. As a result, the learning support chatbot according to the embodiment can provide learning support by providing appropriate advice and guidance in response to students' questions, measuring effectiveness, generating model answers, and providing visual information.

[0060] The question reception unit analyzes students' past question history and can provide optimal advice for each individual student. For example, the question reception unit stores the history of questions that students have previously asked the generation AI in a database and analyzes that data. For example, it can identify topics that specific students repeatedly ask about and provide detailed advice on those topics. It can also analyze the question history to understand the student's learning style and level of understanding. For example, it can provide advice using diagrams and tables to students for whom visual explanations are effective. It can also evaluate the effectiveness of advice provided in the past based on the student's question history and generate optimal advice. For example, if previous advice was effective, it can use that method again. In this way, by analyzing students' past question history, it can provide optimal advice for each individual student.

[0061] The advice generation unit can generate advice that suits a student's learning style. For example, the advice generation unit grasps a student's learning style in advance through questionnaires or tests, and customizes advice based on that information. For example, it can provide explanations that make extensive use of diagrams and graphs to visual learners. It also provides an interface that allows students to select advice that suits their learning style when asking questions to the generation AI. For example, it can provide an option to provide audio commentary to auditory learners. It also builds a system that automatically adjusts the format of advice according to the student's learning style. For example, it can provide interactive simulations to tactile learners. This makes it possible to provide advice that suits each student's learning style.

[0062] The advice generation unit can use the emotion estimation function to provide encouragement and advice to improve motivation according to the student's emotional state. For example, when a student inputs a question, the advice generation unit uses a camera or microphone to analyze facial expressions and voice tone to estimate the student's emotional state. For example, if the student is tired, an encouraging message is displayed. Furthermore, a system is constructed that uses the emotion estimation function to provide advice according to the student's emotional state. For example, if a student is feeling anxious, advice to relax is provided. Furthermore, the emotional state of a student is monitored in real time and advice to improve motivation is provided. For example, if a student is lacking concentration, a short break is suggested. In this way, encouragement and advice to improve motivation can be provided according to the student's emotional state.

[0063] The question receiving unit can automatically suggest related videos or audio commentaries in response to students' questions. For example, when a student inputs a question, the question receiving unit has the generation AI automatically search for and suggest related videos and audio commentaries. For example, an explanatory video is provided for a math problem. Furthermore, a system can be constructed in which the generation AI selects the most appropriate video or audio commentary based on the content of the question and presents it to the student. For example, a documentary video is suggested for a question about historical events. Furthermore, an interface is provided that displays related videos and audio commentaries in real time when a student inputs a question. For example, an audio commentary is instantly played for a question about English grammar. This makes it possible to automatically suggest related videos and audio commentaries in response to students' questions.

[0064] The question acceptance unit can also support voice input and handwriting input when students input questions. For example, the question acceptance unit builds a system that supports voice input when students input questions. For example, a question can be input by voice using a microphone, and the generation AI analyzes the voice and provides advice. In addition, an interface that supports handwriting input can be provided, allowing students to input questions by hand. For example, a tablet can be used to input handwritten mathematical formulas and diagrams, and the generation AI can analyze them. In addition, an interface that combines voice input and handwriting input can be provided, allowing students to input questions in the way that is most convenient for them. For example, a question can be input by voice, and supplementary information can be added by hand. This makes it possible to support both voice input and handwriting input when students input questions.

[0065] The question reception unit can use the emotion estimation function to analyze the emotions of students when they input questions in real time and provide appropriate feedback. For example, when a student inputs a question, the question reception unit analyzes the emotions in real time using a camera or microphone and provides feedback based on the results. For example, if a student is nervous, advice on how to relax is displayed. Furthermore, a system is constructed that uses the emotion estimation function to provide feedback according to the student's emotional state. For example, if a student is confused, a more detailed explanation is provided. Furthermore, an interface is developed that monitors the student's emotional state in real time and provides appropriate feedback. For example, if a student is lacking concentration, a short break is suggested. This makes it possible to analyze the emotions of students when they input questions in real time and provide appropriate feedback.

[0066] The instruction generation unit can evaluate students' level of understanding in real time and adjust the instruction content based on that. For example, as students study, the generation AI evaluates their level of understanding in real time and adjusts the instruction content based on the results. For example, if their level of understanding is low, it will explain the material again from the basics. In addition, to evaluate their level of understanding, the generation AI will regularly conduct quizzes and tests and adjust the instruction content based on the results. For example, if their level of understanding is low on a particular topic, it will provide additional practice questions. In addition, a system will be built that monitors students' level of understanding in real time and adjusts the instruction content as necessary. For example, if their level of understanding is high, it will provide the next level of content. This makes it possible to evaluate students' level of understanding in real time and adjust the instruction content based on that.

[0067] The instruction generation unit can automatically suggest what content should be learned next according to the student's learning progress. For example, the instruction generation unit builds a system in which the generation AI monitors the student's learning progress in real time and automatically suggests what content should be learned next. For example, the next unit may be suggested after a specific unit is completed. The generation AI also automatically generates an optimal learning plan according to the student's learning progress and presents it to the student. For example, it may set weekly learning goals and suggest learning content based on those. It may also analyze the student's learning progress and provide an interface that suggests what content should be learned next. For example, it may provide questions with difficulty adjusted according to the student's progress. This makes it possible to automatically suggest what content should be learned next according to the student's learning progress.

[0068] The instruction generation unit can use the emotion estimation function to provide instruction methods to increase students' motivation to learn. For example, the instruction generation unit builds a system that analyzes students' emotional states in real time and provides instruction methods to increase students' motivation to learn. For example, if a student is tired, an encouraging message is displayed. The emotion estimation function is also used to provide instruction methods to increase students' motivation to learn. For example, learning content related to topics that interest the student is suggested. An interface is also developed that monitors students' emotional states and provides feedback to increase their motivation to learn. For example, if a student is lacking concentration, a short break is suggested. This makes it possible to provide instruction methods to increase students' motivation to learn.

[0069] The instruction generation unit can provide students with an interactive learning experience using virtual reality or augmented reality when they are studying. The instruction generation unit, for example, builds a system that provides students with an interactive learning experience using VR or AR when they are studying. For example, virtual reality is used in a history class to experience past events. VR and AR are also used to provide content that allows students to learn while actually experiencing it. For example, a science experiment is reproduced in virtual reality so that students can experience the experiment. Interactive teaching materials using VR and AR are also provided to students when they are studying. For example, a math problem is visually explained using augmented reality. This makes it possible to provide students with an interactive learning experience using virtual reality or augmented reality when they are studying.

[0070] The instruction generation unit can provide a group chat function to promote collaborative learning with other students when students are studying. The instruction generation unit, for example, builds a system that provides a group chat function to promote collaborative learning with other students when students are studying. For example, it provides a chat room where students studying the same topic can exchange opinions. It also uses the group chat function to support students when they are studying collaboratively. For example, the generation AI answers questions and offers advice within the chat. It also provides a group chat function to promote collaborative learning with other students when students are studying, and shares their learning progress. For example, it sets learning goals within a group and reports progress to each other. This makes it possible to provide a group chat function to promote collaborative learning with other students when students are studying.

[0071] The instruction generation unit can use the emotion estimation function to analyze the emotional compatibility between students and suggest optimal study partners. The instruction generation unit, for example, analyzes the emotional state of students and builds a system that matches students with good emotional compatibility. For example, it suggests students with similar emotion scores as study partners. The emotion estimation function also analyzes the emotional compatibility between students and suggests optimal study partners. For example, it matches students with strong positive emotions. The emotional state of students is also monitored in real time, and an interface is provided that matches students with good emotional compatibility. For example, it suggests students with high emotion scores as study partners. This makes it possible to analyze the emotional compatibility between students and suggest optimal study partners.

[0072] The effectiveness measurement unit can analyze students' answer patterns, identify weak points, and provide focused instruction. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the answer patterns of practice problems solved by students and identifies weak points. For example, if there are many mistakes on a specific question format, instruction will be focused on questions of that format. The answer patterns will also be analyzed to identify students' weak points and provide focused instruction. For example, if there is a lack of understanding of a specific topic, additional practice problems related to that topic will be provided. A system will also be developed that analyzes students' answer patterns in real time, identifies weak points, and provides focused instruction. For example, immediate feedback will be provided for questions that were answered incorrectly, encouraging the student to try again. This will enable the system to analyze students' answer patterns, identify weak points, and provide focused instruction.

[0073] The effectiveness measurement unit can analyze students' response times and provide time management advice. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the response times of practice problems solved by students and provides time management advice. For example, if a particular problem takes too long, it will suggest an efficient way to solve it. It will also analyze the response times and provide time management advice to students. For example, it will suggest which problem to start with when solving an exam. It will also develop a system that analyzes students' response times in real time and provides time management advice. For example, it will teach time management techniques for problems that take a long time to solve. This will allow it to analyze students' response times and provide time management advice.

[0074] The effectiveness measurement unit can use the emotion estimation function to analyze the stress level of students when solving problems and provide advice on how to relax. For example, when students are solving problems, the effectiveness measurement unit uses a camera or microphone to analyze their emotions in real time and estimate their stress level. For example, if stress is high, it provides advice on how to relax. Furthermore, a system is constructed that uses the emotion estimation function to analyze the stress level of students when solving problems and provide advice on how to relax. For example, it suggests deep breathing or short breaks. Furthermore, an interface is developed that monitors students' stress levels in real time and provides advice on how to relax. For example, if stress is high, it plays relaxing music. This makes it possible to analyze the stress level of students when solving problems and provide advice on how to relax.

[0075] The effectiveness measurement unit can provide feedback by comparing the results of problems solved by students with other students. For example, the effectiveness measurement unit constructs a system in which a generation AI analyzes the results of problems solved by students and provides feedback by comparing them with other students. For example, feedback is provided by comparing the results with the average score of other students who solved the same problem. The unit also compares the results of problems with other students and provides feedback to the student. For example, the unit displays the correct answer rate for a specific problem in comparison with other students. The unit also develops a system that analyzes the results of students' problems in real time and provides feedback by comparing them with other students. For example, feedback is provided by comparing the answer time of other students who solved the same problem. This makes it possible to provide feedback by comparing the results of problems solved by students with other students.

[0076] The effectiveness measurement unit can provide a function to automatically report the results of problems solved by students to parents and teachers. For example, the effectiveness measurement unit will build a system in which a generation AI analyzes the results of problems solved by students and automatically reports the results to parents and teachers. For example, it will periodically send learning progress reports by email. It will also provide a function to automatically report the results of problems solved to parents and teachers. For example, it will report the percentage of correct answers and the time it took to solve the problems solved by students. It will also develop a system that analyzes the results of students' problems in real time and automatically reports the results to parents and teachers. For example, it will display learning progress in a graph and share it with parents and teachers. This will provide a function to automatically report the results of problems solved by students to parents and teachers.

[0077] The effectiveness measurement unit can use the emotion estimation function to analyze the emotions students feel when solving problems and provide feedback to elicit positive emotions. For example, the effectiveness measurement unit can use a camera or microphone to analyze the emotions of students when solving problems in real time and provide feedback to elicit positive emotions. For example, if a student is feeling anxious, it can display an encouraging message. Furthermore, a system is constructed that uses the emotion estimation function to analyze the emotions students feel when solving problems and provide feedback to elicit positive emotions. For example, if a student is lacking concentration, it can suggest a short break. Furthermore, an interface is developed that monitors students' emotional states in real time and provides feedback to elicit positive emotions. For example, if a student is feeling stressed, it can play relaxing music. This makes it possible to analyze the emotions students feel when solving problems and provide feedback to elicit positive emotions.

[0078] The model answer generation unit can analyze student answers and provide the most suitable model answer for each individual student. For example, the model answer generation unit will build a system in which a generation AI analyzes answers submitted by students and provides the most suitable model answer for each individual student. For example, it will point out errors in the answer and present the correct answer. It will also analyze student answers and provide the most suitable model answer for each individual student. For example, it will provide a detailed explanation of the answering process to deepen understanding. It will also develop a system that analyzes student answers in real time and provides the most suitable model answer for each individual student. For example, it will immediately point out errors in the answer and encourage the student to try again. This will allow it to analyze student answers and provide the most suitable model answer for each individual student.

[0079] The model answer generation unit can provide detailed explanations and supplementary information for students' answers. For example, the model answer generation unit will build a system in which the generation AI provides detailed explanations and supplementary information for answers submitted by students. For example, it will explain the process of the answer step by step. It will also provide detailed explanations and supplementary information for the answer. For example, it will explain related topics and background knowledge to deepen understanding. It will also develop a system that provides detailed explanations and supplementary information for students' answers in real time. For example, it will point out errors in the answer and present the correct answer. This will allow it to provide detailed explanations and supplementary information for students' answers.

[0080] The model answer generation unit can use the emotion estimation function to provide an explanation that takes emotions into consideration so that students can easily understand the model answer. For example, when a student receives a model answer, the model answer generation unit analyzes the student's emotions in real time using a camera or microphone and provides an explanation that takes emotions into consideration. For example, if the student is confused, a more detailed explanation is provided. Furthermore, a system is constructed that uses the emotion estimation function to provide an explanation that takes emotions into consideration so that students can easily understand the model answer. For example, if a student is feeling anxious, an encouraging message is displayed. Furthermore, an interface is developed that monitors the student's emotional state in real time and provides an explanation that takes emotions into consideration. For example, if a student is lacking concentration, a short break is suggested. This makes it possible to provide an explanation that takes emotions into consideration so that students can easily understand the model answer.

[0081] The model answer generation unit can provide multiple model answers to problems submitted by students, allowing them to be compared and considered. For example, the model answer generation unit builds a system in which a generation AI provides multiple model answers to problems submitted by students. For example, different solutions may be presented, allowing students to compare and consider them. In addition, multiple model answers may be provided to problems, allowing students to compare and consider them. For example, answers from different perspectives may be presented to deepen understanding. In addition, a system may be developed in which multiple model answers are provided in real time to problems submitted by students. For example, different solutions may be presented instantly, allowing students to compare and consider them. This allows multiple model answers to be provided to problems submitted by students, allowing them to compare and consider them.

[0082] The model answer generation unit can also provide example answers from other students for reference to questions submitted by students. For example, the model answer generation unit will build a system in which the generation AI provides example answers from other students to questions submitted by students. For example, it will present excellent example answers so that students can use them as reference. It will also provide example answers from other students to questions so that students can use them as reference. For example, it will present answers from different perspectives to deepen understanding. It will also develop a system that provides example answers from other students in real time to questions submitted by students. For example, it will instantly present excellent example answers so that students can use them as reference. This will make it possible to provide example answers from other students as reference to questions submitted by students.

[0083] The model answer generation unit can use the emotion estimation function to analyze the emotions of students when they receive the model answer and provide feedback to improve their understanding. For example, when a student receives the model answer, the model answer generation unit analyzes the emotions of the student in real time using a camera or microphone and provides feedback to improve their understanding. For example, if the student is confused, a more detailed explanation is provided. Furthermore, a system is constructed that uses the emotion estimation function to analyze the emotions of students when they receive the model answer and provide feedback to improve their understanding. For example, if a student is feeling anxious, an encouraging message is displayed. Furthermore, an interface is developed that monitors the student's emotional state in real time and provides feedback to improve their understanding. For example, if a student is lacking concentration, a short break is suggested. This makes it possible to analyze the emotions of students when they receive the model answer and provide feedback to improve their understanding.

[0084] The visual information generation unit can automatically generate optimal diagrams, tables, and illustrations according to the student's learning content. For example, the visual information generation unit will build a system in which the generation AI analyzes the student's learning content and automatically generates optimal diagrams, tables, and illustrations. For example, it will automatically generate graphs for math problems. It will also automatically generate optimal diagrams, tables, and illustrations according to the learning content. For example, it will automatically generate illustrations of historical events and provide them to students. It will also develop a system that analyzes the student's learning content in real time and automatically generates optimal diagrams, tables, and illustrations. For example, it will show the results of a science experiment in a graph. This will make it possible to automatically generate optimal diagrams, tables, and illustrations according to the student's learning content.

[0085] The visual information generation unit can customize the layout of figures, tables, and illustrations to make them easier for students to understand. For example, the visual information generation unit will build a system in which the generative AI customizes the layout of figures, tables, and illustrations to make them easier for students to understand. For example, it will highlight important information. It will also customize the layout of figures, tables, and illustrations to make them easier for students to understand. For example, it will adjust colors and fonts to make them visually easier to understand. It will also develop a system that customizes the layout of figures, tables, and illustrations according to students' learning styles. For example, it will provide larger figures for visual learners. This will allow the layout of figures, tables, and illustrations to be customized to make them easier for students to understand.

[0086] The visual information generation unit can use the emotion estimation function to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually. For example, the visual information generation unit builds a system in which the generation AI uses the emotion estimation function to provide diagrams, tables, and illustrations that are easier for students to understand visually. For example, if a student is confused, a simple diagram is provided. The emotion estimation function is also used to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually. For example, if a student is feeling anxious, an illustration to help them relax is displayed. In addition, an interface is developed that monitors students' emotional state in real time and provides diagrams, tables, and illustrations that are easier to understand visually. For example, if a student is lacking concentration, a simple diagram is provided. This makes it possible to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually.

[0087] The visual information generation unit can provide interactive diagrams, tables, and illustrations that students can manipulate as they study. For example, the visual information generation unit will build a system in which a generative AI provides interactive diagrams, tables, and illustrations as students study. For example, clicking on a data point on a graph will display detailed information. The unit will also provide interactive diagrams, tables, and illustrations that students can manipulate. For example, they can drag and move parts of an illustration. The unit will also develop a system that provides interactive diagrams, tables, and illustrations in real time as students study. For example, they can enlarge part of a diagram to display details. This will allow the unit to provide interactive diagrams, tables, and illustrations as students study and manipulate them.

[0088] The visual information generation unit can provide a function that allows students to share diagrams, tables, and illustrations with other students as they study, and to study collaboratively. For example, the visual information generation unit builds a system that allows students to share diagrams, tables, and illustrations with other students as they study, and to provide a function that allows them to study collaboratively. For example, they can hold discussions while looking at the same diagram. The unit also provides a function that allows diagrams, tables, and illustrations to be shared with other students and to study collaboratively. For example, it provides an interactive whiteboard that can be edited collaboratively. The unit also develops a function that allows students to share diagrams, tables, and illustrations with other students in real time as they study, and to study collaboratively. For example, they can add comments in real time while looking at the same diagram. This makes it possible to provide a function that allows students to share diagrams, tables, and illustrations with other students as they study, and to study collaboratively.

[0089] The visual information generation unit uses an emotion estimation function to analyze the emotions of students when they receive visual information and can provide the most appropriate visual information. For example, when a student receives visual information, the visual information generation unit uses the emotion estimation function to analyze the emotions in real time using the generation AI, building a system that provides the most appropriate visual information. For example, if a student is confused, a simple diagram is provided. The emotion estimation function is also used to analyze the emotions of students when they receive visual information and provide the most appropriate visual information. For example, if a student is feeling anxious, an illustration to help them relax is displayed. We also developed an interface that monitors students' emotional state in real time and provides the most appropriate visual information. For example, if a student is lacking concentration, a simple diagram is provided. This makes it possible to analyze the emotions of students when they receive visual information and provide the most appropriate visual information.

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

[0091] The question acceptance unit can also support voice input and handwriting input when students enter questions. For example, a system can be built that supports voice input when students enter questions. For example, a microphone can be used to enter questions by voice, and the generation AI can analyze the voice and provide advice. An interface that supports handwriting input can also be provided, allowing students to enter questions by hand. For example, a tablet can be used to enter handwritten mathematical formulas and diagrams, which the generation AI can analyze. An interface that combines voice input and handwriting input can also be provided, allowing students to enter questions in the way that is most convenient for them. For example, a question can be entered by voice, and supplementary information can be added by hand. This makes it possible to support both voice input and handwriting input when students enter questions.

[0092] The advice generation unit can use the emotion estimation function to provide encouragement and advice to improve motivation according to the student's emotional state. For example, when a student inputs a question, the camera and microphone can be used to analyze their facial expressions and voice tone to estimate their emotional state. For example, if the student is tired, an encouraging message can be displayed. The emotion estimation function can also be used to build a system that provides advice according to the student's emotional state. For example, if a student is feeling anxious, advice on how to relax can be provided. The system can also monitor the student's emotional state in real time and provide advice to improve motivation. For example, if a student is lacking concentration, the system can suggest taking a short break. This makes it possible to provide encouragement and advice to improve motivation according to the student's emotional state.

[0093] The instruction generation unit can evaluate students' level of understanding in real time and adjust the instruction content based on that. For example, as students study, the generation AI evaluates their level of understanding in real time and adjusts the instruction content based on the results. For example, if their level of understanding is low, it will explain the material again from the basics. In addition, to evaluate their level of understanding, the generation AI will periodically conduct quizzes and tests and adjust the instruction content based on the results. For example, if their level of understanding is low on a particular topic, it will provide additional practice questions. We will also build a system that monitors students' level of understanding in real time and adjusts the instruction content as necessary. For example, if their level of understanding is high, it will provide the next level of content. This makes it possible to evaluate students' level of understanding in real time and adjust the instruction content based on that.

[0094] The instruction generation unit can use the emotion estimation function to provide instruction methods to increase students' motivation to learn. For example, a system can be constructed that analyzes students' emotional states in real time and provides instruction methods to increase students' motivation to learn. For example, if a student is tired, an encouraging message can be displayed. The emotion estimation function can also be used to provide instruction methods to increase students' motivation to learn. For example, learning content related to topics that interest the student can be suggested. An interface can also be developed that monitors students' emotional states and provides feedback to increase their motivation to learn. For example, if a student is lacking concentration, a short break can be suggested. This makes it possible to provide instruction methods to increase students' motivation to learn.

[0095] The effectiveness measurement department can analyze students' answer patterns, identify their weak points, and provide focused instruction. For example, we will build a system in which a generation AI analyzes the answer patterns of practice problems solved by students and identifies their weak points. For example, if there are many mistakes made on a specific question format, instruction will be focused on questions of that format. We will also analyze answer patterns to identify students' weak points and provide focused instruction. For example, if there is a lack of understanding of a specific topic, we will provide additional practice problems related to that topic. We will also develop a system that analyzes students' answer patterns in real time, identifies their weak points, and provides focused instruction. For example, we will provide instant feedback on questions that were answered incorrectly, encouraging the student to try again. This will enable us to analyze students' answer patterns, identify their weak points, and provide focused instruction.

[0096] The effectiveness measurement unit can use the emotion estimation function to analyze students' stress levels when solving problems and provide them with advice on how to relax. For example, when students are solving problems, a camera or microphone can be used to analyze their emotions in real time and estimate their stress level. For example, if stress is high, advice on how to relax can be provided. We will also build a system that uses the emotion estimation function to analyze students' stress levels when solving problems and provide them with advice on how to relax. For example, it can suggest deep breathing or short breaks. We will also develop an interface that monitors students' stress levels in real time and provides them with advice on how to relax. For example, if stress is high, it can play relaxing music. This will allow us to analyze students' stress levels when solving problems and provide them with advice on how to relax.

[0097] The model answer generation unit can analyze students' answers and provide the most suitable model answer for each individual student. For example, we will build a system in which a generation AI analyzes answers submitted by students and provides the most suitable model answer for each individual student. For example, it will point out errors in the answer and present the correct answer. We will also analyze students' answers and provide the most suitable model answer for each individual student. For example, it will provide a detailed explanation of the answering process to deepen understanding. We will also develop a system that analyzes students' answers in real time and provides the most suitable model answer for each individual student. For example, it will immediately point out errors in the answer and encourage the student to try again. This will allow us to analyze students' answers and provide the most suitable model answer for each individual student.

[0098] The model answer generation unit can use the emotion estimation function to provide emotionally sensitive explanations to help students understand the model answer. For example, when a student receives the model answer, the system can analyze the student's emotions in real time using a camera or microphone and provide emotionally sensitive explanations. For example, if the student is confused, a more detailed explanation can be provided. We also build a system that uses the emotion estimation function to provide emotionally sensitive explanations to help students understand the model answer. For example, if a student is feeling anxious, an encouraging message can be displayed. We also develop an interface that monitors the student's emotional state in real time and provides emotionally sensitive explanations. For example, if a student is losing concentration, the system can suggest a short break. This makes it possible to provide emotionally sensitive explanations to help students understand the model answer.

[0099] The visual information generation unit can automatically generate optimal diagrams, tables, and illustrations according to the student's learning content. For example, we will build a system in which the generation AI analyzes the student's learning content and automatically generates the optimal diagrams, tables, and illustrations. For example, graphs can be automatically generated for math problems. We will also automatically generate optimal diagrams, tables, and illustrations according to the learning content. For example, we will automatically generate illustrations of historical events and provide them to students. We will also develop a system that analyzes the student's learning content in real time and automatically generates the optimal diagrams, tables, and illustrations. For example, we can show the results of a science experiment in a graph. This will make it possible to automatically generate the optimal diagrams, tables, and illustrations according to the student's learning content.

[0100] The visual information generation unit can use the emotion estimation function to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually. For example, we will build a system in which the generation AI uses the emotion estimation function to provide diagrams, tables, and illustrations that are easier for students to understand visually. For example, if a student is confused, a simple diagram will be provided. We will also use the emotion estimation function to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually. For example, if a student is feeling anxious, an illustration to help them relax will be displayed. We will also develop an interface that monitors students' emotional state in real time and provides diagrams, tables, and illustrations that are easier for students to understand visually. For example, if a student is lacking concentration, a simple diagram will be provided. This will make it possible to provide diagrams, tables, and illustrations that take emotions into consideration to make them easier for students to understand visually.

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

[0102] Step 1: The question reception unit receives questions from students. For example, questions can be received in text format or audio format. The question reception unit can also receive questions about specific subjects. Step 2: The advice generator generates advice based on the question received by the question receiver. For example, the generator AI provides advice on appropriate study methods and problem-solving procedures in response to the student's question. The generator AI can also provide advice tailored to the student's learning style. Step 3: The instruction generation unit generates learning instruction based on the advice generated by the advice generation unit. For example, the generation AI provides appropriate instruction content according to the student's learning progress and level of understanding. The generation AI can also provide instruction methods that suit the student's learning style. Step 4: The effectiveness measurement unit measures the effectiveness of the instruction generated by the instruction generation unit. For example, the generation AI analyzes the results of practice problems solved by students and measures their learning effectiveness. The generation AI can also analyze students' answer patterns to identify weak points and provide focused instruction. Step 5: The model answer generator generates a model answer based on the effectiveness measured by the effectiveness measurement unit. For example, the generation AI provides a model answer for the question submitted by the student. The generation AI can also provide detailed explanations and supplementary information for the student's answer. Step 6: The visual information generation unit generates visual information based on the model answer generated by the model answer generation unit. For example, the generation AI can use a support app to incorporate diagrams, tables, illustrations, etc. to provide a visually easy-to-understand explanation. The generation AI can also customize the layout of the diagrams, tables, and illustrations to make them easier for students to understand.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

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

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A question reception section that accepts questions from students; an advice generating unit that generates advice based on the question received by the question receiving unit; an instruction generation unit that generates learning instruction based on the advice generated by the advice generation unit; an effect measurement unit that measures an effect based on the instruction generated by the instruction generation unit; a model answer generation unit that generates a model answer based on the effect measured by the effect measurement unit; a visual information generating unit that generates visual information based on the model answer generated by the model answer generating unit. A system characterized by:

2. The question receiving unit Analyze students' past question history and provide personalized advice 2. The system of claim 1.

3. The advice generation unit Generate advice according to the student's learning style 2. The system of claim 1.

4. The advice generation unit Providing encouragement and motivational advice according to the student's emotional state 2. The system of claim 1.

5. The question receiving unit Automatically suggest relevant videos or audio explanations to the student's questions 2. The system of claim 1.

6. The question receiving unit The student can also input questions using voice or handwriting.

2. The system of claim 1.

7. The question receiving unit Analyze the student's emotions in real time when they type their question and provide appropriate feedback 2. The system of claim 1.

Images