System

Abstract

An object of a system according to an embodiment is to solve a problem in an educational field using generated AI.SOLUTION: A system includes a learning material generation unit, a test scoring unit, and a learning achievement level analysis unit. The learning material generation part generates a learning material using the generation AI. A test grading part grades and explains the answer of the test. A learning skill level analysis part analyzes the learning skill level of the student and proposes a follow plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has room for improvement, as it has led to a decrease in the number of teachers, an increase in workload, and insufficient support for diverse students.

[0005] The system according to the embodiment aims to solve problems in the educational field using generative AI. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning material generation unit, a test marking unit, and a learning proficiency analysis unit. The learning material generation unit generates learning materials using a generative AI. The test marking unit marks test answers and provides explanations. The learning proficiency analysis unit analyzes students' learning proficiency and proposes a follow-up plan. [Effects of the Invention]

[0007] The system according to the embodiment can solve problems in the educational field using generative AI. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​teacher system according to an embodiment of the present invention uses generative AI to solve problems such as a decrease in the number of teachers in the educational field, the workload of teachers, and the need to provide support to diverse students. This system utilizes generative AI to generate learning materials, grade and explain tests, and analyze students' learning proficiency and create follow-up plans. This reduces the burden on teachers and enables them to provide detailed instruction to each student.

[0029] An AI teacher system according to an embodiment includes a learning material generation unit, a test scoring unit, and a learning proficiency analysis unit. The learning material generation unit generates learning materials using a generation AI. For example, when a teacher inputs a prompt such as, "Please create test questions on quadratic equations in junior high school mathematics," the generation AI generates appropriate test questions based on the instruction. When a teacher inputs a prompt such as, "Please grade this mathematics test and provide explanations for each question," the generation AI grades the test and generates explanations for each question. When a teacher inputs a prompt such as, "Please analyze the mathematics test results for this class, identify areas where each student lacks understanding, and propose an improvement plan," the generation AI analyzes the test results, identifies areas where each student lacks understanding, and proposes a specific follow-up plan. This allows the AI ​​teacher system to reduce the burden on teachers and provide detailed instruction to each student.

[0030] The learning material generation unit can generate individually optimized questions by reflecting the student's past learning history. For example, the generation AI in the learning material generation unit analyzes each student's past test results and learning history and generates individually optimized questions based on that data. For example, when generating questions about quadratic equations in mathematics, the difficulty level is adjusted taking into account past grades and level of understanding. The generation AI also generates questions to reinforce specific weak points based on the student's learning history. For example, it may present questions similar to questions that the student got wrong in the past to deepen understanding. The generation AI also reflects the student's learning history and generates problem sets tailored to the student's individual learning progress. For example, it may provide applied questions to fast-paced students and basic questions to slow-paced students. This makes it possible to provide learning materials optimized for each student.

[0031] The learning material generation unit can provide feedback in real time when students solve problems. For example, the generation AI of the learning material generation unit monitors the progress of a student's answer in real time as they solve a problem, and provides hints as needed. For example, if the student is not making progress in solving the problem, it will suggest the next step. The generation AI also analyzes the student's answer in real time, and immediately displays an explanation if it detects an error. For example, it will point out a calculation error and explain the correct way to calculate it. The generation AI also provides feedback to the student's answer in real time, and automatically generates additional questions to deepen their understanding. For example, if a particular concept is not understood, it will add a question related to that concept. This allows students to immediately receive hints and explanations when solving problems.

[0032] The learning material generation unit can also accommodate visual learners by incorporating visual elements. For example, the generation AI automatically generates diagrams and graphs related to the problem statement, providing learning materials that are easy to understand visually. For example, it displays a graph of a function for a math problem. The generation AI also automatically generates explanatory videos to make it easier for visual learners to understand. For example, it shows the procedure for a physics experiment in video. The generation AI also incorporates interactive diagrams into the learning materials, allowing students to learn by manipulating them. For example, it displays a 3D model of a chemical molecular structure that can be rotated and observed. This makes it possible to provide learning materials that are also suitable for visual learners.

[0033] The learning materials generation unit can be customized for different grades and subjects to meet a wide range of educational needs. For example, the generation AI customizes learning materials based on the curriculum for different grades and generates problems of appropriate difficulty. For example, it can handle everything from basic problems for elementary school students to applied problems for high school students. The generation AI also generates learning materials for different subjects to meet a wide range of educational needs. For example, it provides problems specialized for each subject, such as mathematics, science, and history. The generation AI also customizes learning materials based on the learning goals for each grade and subject, providing problems that match the student's learning progress. For example, it generates a problem set for focused study of a specific unit. This makes it possible to provide learning materials that meet a wide range of educational needs.

[0034] The test scoring unit can analyze answer patterns, identify the causes of incorrect answers, and reflect this in the explanations. In the test scoring unit, for example, the generation AI analyzes students' answer patterns and identifies the causes of incorrect answers. For example, it detects calculation errors or misunderstandings of concepts and reflects the causes in the explanations. The generation AI also analyzes the patterns of incorrect answers and identifies common errors. For example, if multiple students make the same mistake, it will include the common points in the explanations. The generation AI also identifies the causes of incorrect answers and includes specific ways to improve them in the explanations. For example, it provides advice to deepen understanding of specific calculation procedures or concepts. In this way, the causes of incorrect answers can be identified and reflected in the explanations, thereby deepening students' understanding.

[0035] The test scoring department can introduce handwriting recognition technology to recognize handwritten answers and accurately score them. In the test scoring department, for example, a generative AI uses handwriting recognition technology to accurately analyze and score students' handwritten answers. For example, it recognizes handwritten mathematical formulas and determines whether they are correct or incorrect. The generative AI also digitizes handwritten answers and automates the scoring process. For example, it converts handwritten written answers into text data and analyzes the content. The generative AI also uses handwriting recognition technology to accurately recognize and score handwritten diagrams and graphs. For example, it analyzes handwritten graphs and determines whether they are accurate answers. This allows handwritten answers to be scored accurately.

[0036] The test scoring section can evaluate students from multiple angles using different evaluation criteria. For example, the generative AI uses a rubric to evaluate students' answers from multiple angles. For example, it evaluates not only the accuracy of the content but also logical structure and expressiveness. The generative AI can also combine different evaluation criteria to comprehensively evaluate students' answers. For example, it can evaluate from multiple perspectives, such as the level of understanding of knowledge, application ability, and creativity. The generative AI can also evaluate students' answers in detail based on the rubric and provide specific feedback. For example, it can show the score for each evaluation criterion and areas for improvement. This makes multifaceted evaluation possible.

[0037] The test scoring unit can compare the answers of other students and perform relative evaluation. For example, the generative AI compares the answers of other students and performs relative evaluation. For example, evaluation is based on the average score of the entire class or the distribution of top and bottom scores. The generative AI also provides feedback indicating the student's position based on the relative evaluation. For example, it displays the student's ranking within the class or deviation score. The generative AI also compares the answers of other students to identify their relative strengths and weaknesses. For example, evaluation is based on the rate of correct answers and the rate of incorrect answers to a specific question. This makes relative evaluation possible.

[0038] The learning proficiency analysis unit can compare a student's past learning data with their current learning data and visualize their progress. In the learning proficiency analysis unit, for example, the generation AI compares a student's past learning data with their current data and visualizes their progress. For example, it displays their learning progress using graphs and charts. The generation AI also compares past test results with current test results to identify improvements in understanding and identify challenges. For example, it shows changes in grades in specific units. The generation AI also visualizes the student's learning progress and reports it to teachers and parents. For example, it generates regular reports to share their learning progress. This makes it possible to visualize the student's learning progress.

[0039] The learning proficiency analysis unit can consider a student's learning style and propose the optimal follow-up plan. In the learning proficiency analysis unit, for example, the generation AI analyzes a student's learning style and classifies them as visual, auditory, etc. For example, learning style is identified based on past learning data and survey results. The generation AI then proposes a follow-up plan according to the learning style. For example, visual students could be provided with teaching materials that make extensive use of diagrams and graphs, while auditory students could be provided with audio commentary. The generation AI can also generate individual follow-up plans that take learning style into consideration and propose them to the teacher. For example, it could suggest teaching methods that are tailored to specific learning styles. This makes it possible to propose follow-up plans that suit each student's learning style.

[0040] The learning proficiency analysis unit can propose a comprehensive learning plan by taking into account the relationships between different subjects. For example, in the learning proficiency analysis unit, the generative AI analyzes the relationships between different subjects and proposes a comprehensive learning plan. For example, it considers the relationship between mathematics and physics and creates a plan to study both subjects in a balanced manner. The generative AI also suggests learning priorities based on the relationships between subjects. For example, if the basics of mathematics are important for understanding physics, it will propose a plan to study mathematics first. The generative AI also integrates learning data from different subjects and visualizes overall learning progress. For example, it summarizes grades for each subject in a single graph to grasp the overall learning situation. This makes it possible to propose a comprehensive learning plan that takes into account the relationships between different subjects.

[0041] The learning proficiency analysis unit can propose more realistic follow-up plans by taking into account the home environment and lifestyle habits. In the learning proficiency analysis unit, for example, the generation AI takes into account the student's home environment and lifestyle habits and proposes a realistic follow-up plan. For example, it creates a study plan that suits home study times and daily rhythms. The generation AI also suggests the optimal timing for studying based on the student's lifestyle data. For example, it proposes a plan to study during times when concentration is highest. The generation AI also generates individual follow-up plans that take into account the home environment and lifestyle habits and proposes them to the teacher. For example, for students who need support at home, it suggests cooperation with parents. This makes it possible to propose realistic follow-up plans that take into account the home environment and lifestyle habits.

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

[0043] The AI ​​teaching system can also be equipped with customization functions according to students' learning styles. For example, visual learners can be provided with teaching materials that make extensive use of diagrams and graphs, while auditory learners can be provided with audio commentary. The generative AI can also analyze students' learning styles and suggest optimal learning methods. For example, it can provide experiment videos for students who like experiments, and a list of related books for students who prefer reading. This makes it possible to provide instruction that is tailored to each student's learning style.

[0044] The AI ​​teacher system can also implement a reward system based on students' learning progress. For example, digital badges or points can be awarded when certain goals are achieved, increasing motivation. The generative AI can also monitor students' progress in real time and provide rewards at the appropriate time. For example, a special reward can be given for consecutive correct answers. The reward system can also encourage competition among students, increasing their motivation to learn. This can increase students' motivation to learn.

[0045] The AI ​​teacher system can also be equipped with a suggestion function to optimize students' learning environments. For example, the generative AI can analyze students' learning environments and provide advice to improve their concentration. For example, it can suggest studying in a quiet place or using appropriate lighting. The generative AI can also monitor students' learning environments and point out areas for improvement. For example, it can advise them on tidying their desks or taking appropriate breaks. This can optimize students' learning environments and improve their learning efficiency.

[0046] The AI ​​teacher system can also propose long-term learning plans based on students' learning history. For example, the generative AI analyzes past learning data and sets future learning goals. For example, it creates a plan aimed at improving grades in a specific subject. The generative AI can also dynamically adjust long-term learning plans based on students' learning history. For example, it can revise the plan based on progress and suggest optimal learning methods. The generative AI can also provide advice on future career paths based on students' learning history. For example, it can suggest a plan for learning the skills needed for a specific occupation. This can support students' long-term learning plans.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The learning material generation unit generates learning materials using generative AI. For example, if a teacher inputs a prompt containing an instruction such as "Please create test questions on quadratic equations in junior high school mathematics," the unit generates appropriate test questions based on the instruction. Step 2: The test scoring unit uses generative AI to score the test answers and provide explanations for each question. For example, when a teacher inputs a prompt including instructions such as "Please score this math test and create explanations for each question," the test is scored and explanations for each question are generated. Step 3: The learning proficiency analysis unit uses generative AI to analyze students' learning proficiency and propose a follow-up plan. For example, if a teacher inputs a prompt including instructions such as, "Analyze the math test results for this class, identify areas where each student lacks understanding, and propose an improvement plan," the system will analyze the test results, identify areas where each student lacks understanding, and propose a specific follow-up plan.

[0049] (Example 2) The AI ​​teacher system according to an embodiment of the present invention uses generative AI to solve problems such as a decrease in the number of teachers in the educational field, the workload of teachers, and the need to provide support to diverse students. This system utilizes generative AI to generate learning materials, grade and explain tests, and analyze students' learning proficiency and create follow-up plans. This reduces the burden on teachers and enables them to provide detailed instruction to each student.

[0050] An AI teacher system according to an embodiment includes a learning material generation unit, a test scoring unit, and a learning proficiency analysis unit. The learning material generation unit generates learning materials using a generation AI. For example, when a teacher inputs a prompt such as, "Please create test questions on quadratic equations in junior high school mathematics," the generation AI generates appropriate test questions based on the instruction. When a teacher inputs a prompt such as, "Please grade this mathematics test and provide explanations for each question," the generation AI grades the test and generates explanations for each question. When a teacher inputs a prompt such as, "Please analyze the mathematics test results for this class, identify areas where each student lacks understanding, and propose an improvement plan," the generation AI analyzes the test results, identifies areas where each student lacks understanding, and proposes a specific follow-up plan. This allows the AI ​​teacher system to reduce the burden on teachers and provide detailed instruction to each student.

[0051] The learning material generation unit can generate individually optimized questions by reflecting the student's past learning history. For example, the generation AI in the learning material generation unit analyzes each student's past test results and learning history and generates individually optimized questions based on that data. For example, when generating questions about quadratic equations in mathematics, the difficulty level is adjusted taking into account past grades and level of understanding. The generation AI also generates questions to reinforce specific weak points based on the student's learning history. For example, it may present questions similar to questions that the student got wrong in the past to deepen understanding. The generation AI also reflects the student's learning history and generates problem sets tailored to the student's individual learning progress. For example, it may provide applied questions to fast-paced students and basic questions to slow-paced students. This makes it possible to provide learning materials optimized for each student.

[0052] The learning material generation unit can provide feedback in real time when students solve problems. For example, the generation AI of the learning material generation unit monitors the progress of a student's answer in real time as they solve a problem, and provides hints as needed. For example, if the student is not making progress in solving the problem, it will suggest the next step. The generation AI also analyzes the student's answer in real time, and immediately displays an explanation if it detects an error. For example, it will point out a calculation error and explain the correct way to calculate it. The generation AI also provides feedback to the student's answer in real time, and automatically generates additional questions to deepen their understanding. For example, if a particular concept is not understood, it will add a question related to that concept. This allows students to immediately receive hints and explanations when solving problems.

[0053] The learning materials generation unit can analyze students' emotions while they are learning and automatically generate positive feedback to increase their motivation. For example, the generation AI in the learning materials generation unit analyzes students' facial expressions and voices to estimate their emotions while learning in real time. For example, it displays an encouraging message if their concentration is declining. The generation AI also automatically generates positive feedback to increase students' motivation based on their emotional data. For example, it displays a message such as "Well done!" when they solve a problem. The generation AI also monitors changes in students' emotions and provides advice to help them relax if negative emotions are detected. For example, it suggests taking a short break. This makes it possible to provide feedback to increase students' motivation.

[0054] The learning material generation unit can also accommodate visual learners by incorporating visual elements. For example, the generation AI automatically generates diagrams and graphs related to the problem statement, providing learning materials that are easy to understand visually. For example, it displays a graph of a function for a math problem. The generation AI also automatically generates explanatory videos to make it easier for visual learners to understand. For example, it shows the procedure for a physics experiment in video. The generation AI also incorporates interactive diagrams into the learning materials, allowing students to learn by manipulating them. For example, it displays a 3D model of a chemical molecular structure that can be rotated and observed. This makes it possible to provide learning materials that are also suitable for visual learners.

[0055] The learning materials generation unit can be customized for different grades and subjects to meet a wide range of educational needs. For example, the generation AI customizes learning materials based on the curriculum for different grades and generates problems of appropriate difficulty. For example, it can handle everything from basic problems for elementary school students to applied problems for high school students. The generation AI also generates learning materials for different subjects to meet a wide range of educational needs. For example, it provides problems specialized for each subject, such as mathematics, science, and history. The generation AI also customizes learning materials based on the learning goals for each grade and subject, providing problems that match the student's learning progress. For example, it generates a problem set for focused study of a specific unit. This makes it possible to provide learning materials that meet a wide range of educational needs.

[0056] The learning material generation unit can use the emotion estimation function to identify topics that interest students and generate learning materials related to those topics. In the learning material generation unit, for example, the generation AI identifies topics that interest students using the emotion estimation function and generates questions related to those topics. For example, science-related questions are provided to students who are interested in science. The generation AI also customizes learning materials related to topics of interest based on the student's emotion data. For example, detailed explanations about history are provided to students who are interested in history. The generation AI also identifies topics that interest students and generates interactive learning materials related to those topics. For example, questions using maps are provided to students who are interested in geography. This makes it possible to provide learning materials related to topics that interest students.

[0057] The test scoring unit can analyze answer patterns, identify the causes of incorrect answers, and reflect this in the explanations. In the test scoring unit, for example, the generation AI analyzes students' answer patterns and identifies the causes of incorrect answers. For example, it detects calculation errors or misunderstandings of concepts and reflects the causes in the explanations. The generation AI also analyzes the patterns of incorrect answers and identifies common errors. For example, if multiple students make the same mistake, it will include the common points in the explanations. The generation AI also identifies the causes of incorrect answers and includes specific ways to improve them in the explanations. For example, it provides advice to deepen understanding of specific calculation procedures or concepts. In this way, the causes of incorrect answers can be identified and reflected in the explanations, thereby deepening students' understanding.

[0058] The test scoring department can introduce handwriting recognition technology to recognize handwritten answers and accurately score them. In the test scoring department, for example, a generative AI uses handwriting recognition technology to accurately analyze and score students' handwritten answers. For example, it recognizes handwritten mathematical formulas and determines whether they are correct or incorrect. The generative AI also digitizes handwritten answers and automates the scoring process. For example, it converts handwritten written answers into text data and analyzes the content. The generative AI also uses handwriting recognition technology to accurately recognize and score handwritten diagrams and graphs. For example, it analyzes handwritten graphs and determines whether they are accurate answers. This allows handwritten answers to be scored accurately.

[0059] The test scoring unit can use the emotion estimation function to analyze the emotions expressed by students' answers and generate encouraging messages for students who have negative emotions. For example, the generation AI in the test scoring unit analyzes the emotions expressed by students' answers and generates encouraging messages for students who have negative emotions. For example, it displays a message such as "You'll do better next time!" for a question that was answered incorrectly. The generation AI also provides positive feedback based on the student's emotional data. For example, it displays a message such as "Great!" for a question that was answered correctly. The generation AI also monitors changes in the student's emotions and provides encouraging messages if negative emotions are detected. For example, if the overall test result is poor, it displays a message such as "Try harder next time!". This makes it possible to provide encouraging messages to students who have negative emotions.

[0060] The test scoring section can evaluate students from multiple angles using different evaluation criteria. For example, the generative AI uses a rubric to evaluate students' answers from multiple angles. For example, it evaluates not only the accuracy of the content but also logical structure and expressiveness. The generative AI can also combine different evaluation criteria to comprehensively evaluate students' answers. For example, it can evaluate from multiple perspectives, such as the level of understanding of knowledge, application ability, and creativity. The generative AI can also evaluate students' answers in detail based on the rubric and provide specific feedback. For example, it can show the score for each evaluation criterion and areas for improvement. This makes multifaceted evaluation possible.

[0061] The test scoring unit can compare the answers of other students and perform relative evaluation. For example, the generative AI compares the answers of other students and performs relative evaluation. For example, evaluation is based on the average score of the entire class or the distribution of top and bottom scores. The generative AI also provides feedback indicating the student's position based on the relative evaluation. For example, it displays the student's ranking within the class or deviation score. The generative AI also compares the answers of other students to identify their relative strengths and weaknesses. For example, evaluation is based on the rate of correct answers and the rate of incorrect answers to a specific question. This makes relative evaluation possible.

[0062] The test scoring unit uses the emotion estimation function to analyze the stress and anxiety felt by students while answering questions, and can adjust the explanations based on the results. In the test scoring unit, for example, the generation AI analyzes the emotions felt by students while answering questions and identifies the parts where they felt stressed or anxious. For example, it analyzes based on answer time and facial expression data. The generation AI also adjusts the explanations for parts where students felt stressed or anxious based on the emotion data. For example, it provides detailed explanations for difficult questions. The generation AI also monitors changes in students' emotions and provides advice to reduce stress and anxiety. For example, it suggests breathing techniques to help them relax or to take a break. This makes it possible to provide explanations that take students' stress and anxiety into consideration.

[0063] The learning proficiency analysis unit can compare a student's past learning data with their current learning data and visualize their progress. In the learning proficiency analysis unit, for example, the generation AI compares a student's past learning data with their current data and visualizes their progress. For example, it displays their learning progress using graphs and charts. The generation AI also compares past test results with current test results to identify improvements in understanding and identify challenges. For example, it shows changes in grades in specific units. The generation AI also visualizes the student's learning progress and reports it to teachers and parents. For example, it generates regular reports to share their learning progress. This makes it possible to visualize the student's learning progress.

[0064] The learning proficiency analysis unit can consider a student's learning style and propose the optimal follow-up plan. In the learning proficiency analysis unit, for example, the generation AI analyzes a student's learning style and classifies them as visual, auditory, etc. For example, learning style is identified based on past learning data and survey results. The generation AI then proposes a follow-up plan according to the learning style. For example, visual students could be provided with teaching materials that make extensive use of diagrams and graphs, while auditory students could be provided with audio commentary. The generation AI can also generate individual follow-up plans that take learning style into consideration and propose them to the teacher. For example, it could suggest teaching methods that are tailored to specific learning styles. This makes it possible to propose follow-up plans that suit each student's learning style.

[0065] The learning proficiency analysis unit uses the emotion estimation function to analyze students' emotions while studying and propose individual follow-up plans to maintain motivation. For example, the generation AI in the learning proficiency analysis unit analyzes students' emotions while studying in real time and proposes follow-up plans to maintain motivation. For example, it suggests taking a break if concentration drops while studying. The generation AI also proposes follow-up plans to elicit positive emotions based on the student's emotional data. For example, it may set small goals that will give the student a sense of accomplishment. The generation AI also monitors changes in the student's emotions and provides encouraging messages if negative emotions are detected. For example, if learning is not going well, it may display a message such as "I'm sure you'll do it next time!". This makes it possible to propose follow-up plans to maintain the student's motivation.

[0066] The learning proficiency analysis unit can propose a comprehensive learning plan by taking into account the relationships between different subjects. For example, in the learning proficiency analysis unit, the generative AI analyzes the relationships between different subjects and proposes a comprehensive learning plan. For example, it considers the relationship between mathematics and physics and creates a plan to study both subjects in a balanced manner. The generative AI also suggests learning priorities based on the relationships between subjects. For example, if the basics of mathematics are important for understanding physics, it will propose a plan to study mathematics first. The generative AI also integrates learning data from different subjects and visualizes overall learning progress. For example, it summarizes grades for each subject in a single graph to grasp the overall learning situation. This makes it possible to propose a comprehensive learning plan that takes into account the relationships between different subjects.

[0067] The learning proficiency analysis unit can propose more realistic follow-up plans by taking into account the home environment and lifestyle habits. In the learning proficiency analysis unit, for example, the generation AI takes into account the student's home environment and lifestyle habits and proposes a realistic follow-up plan. For example, it creates a study plan that suits home study times and daily rhythms. The generation AI also suggests the optimal timing for studying based on the student's lifestyle data. For example, it proposes a plan to study during times when concentration is highest. The generation AI also generates individual follow-up plans that take into account the home environment and lifestyle habits and proposes them to the teacher. For example, for students who need support at home, it suggests cooperation with parents. This makes it possible to propose realistic follow-up plans that take into account the home environment and lifestyle habits.

[0068] The learning proficiency analysis unit can use the emotion estimation function to identify the learning content in which a student is most interested and propose a follow-up plan centered on that content. For example, in the learning proficiency analysis unit, the generation AI can identify the learning content in which a student is most interested based on the student's emotion data and propose a follow-up plan centered on that content. For example, a student interested in science can be given many science-related assignments. The generation AI can also identify the learning content in which a student is interested and provide learning materials and assignments related to that content. For example, a student interested in history can be suggested a history-related project. The generation AI can also monitor changes in the student's emotions and dynamically adjust the follow-up plan centered on the learning content of interest. For example, if interests change, it can propose a plan to accommodate the new content. This makes it possible to propose a follow-up plan centered on the learning content in which a student is most interested.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The AI ​​teaching system can also be equipped with customization functions according to students' learning styles. For example, visual learners can be provided with teaching materials that make extensive use of diagrams and graphs, while auditory learners can be provided with audio commentary. The generative AI can also analyze students' learning styles and suggest optimal learning methods. For example, it can provide experiment videos for students who like experiments, and a list of related books for students who prefer reading. This makes it possible to provide instruction that is tailored to each student's learning style.

[0071] The AI ​​teacher system can also implement a reward system based on students' learning progress. For example, digital badges or points can be awarded when certain goals are achieved, increasing motivation. The generative AI can also monitor students' progress in real time and provide rewards at the appropriate time. For example, a special reward can be given for consecutive correct answers. The reward system can also encourage competition among students, increasing their motivation to learn. This can increase students' motivation to learn.

[0072] The AI ​​teacher system can also be equipped with a suggestion function to optimize students' learning environments. For example, the generative AI can analyze students' learning environments and provide advice to improve their concentration. For example, it can suggest studying in a quiet place or using appropriate lighting. The generative AI can also monitor students' learning environments and point out areas for improvement. For example, it can advise them on tidying their desks or taking appropriate breaks. This can optimize students' learning environments and improve their learning efficiency.

[0073] The AI ​​teacher system can also propose long-term learning plans based on students' learning history. For example, the generative AI analyzes past learning data and sets future learning goals. For example, it creates a plan aimed at improving grades in a specific subject. The generative AI can also dynamically adjust long-term learning plans based on students' learning history. For example, it can revise the plan based on progress and suggest optimal learning methods. The generative AI can also provide advice on future career paths based on students' learning history. For example, it can suggest a plan for learning the skills needed for a specific occupation. This can support students' long-term learning plans.

[0074] The AI ​​teacher system can also analyze students' emotions while they are studying and propose individual follow-up plans to maintain their motivation. For example, the generation AI can analyze students' emotions in real time while they are studying and propose follow-up plans to maintain their motivation. For example, it can suggest taking a break if their concentration drops while studying. The generation AI can also propose follow-up plans to bring out positive emotions based on the student's emotional data. For example, it can set small goals that will give them a sense of accomplishment. The generation AI can also monitor changes in students' emotions and provide encouraging messages if negative emotions are detected. For example, if a student is not making good progress in their studies, it can display a message such as "I'm sure you'll do it next time!". This makes it possible to propose follow-up plans to maintain students' motivation.

[0075] The AI ​​teacher system can also analyze students' emotions while they study and be equipped with a relaxation function to reduce stress. For example, the generating AI can analyze students' facial expressions and voices to estimate their stress levels in real time. For example, it can play relaxation music if stress levels increase. The generating AI can also provide advice to reduce stress based on students' emotional data. For example, it can suggest deep breathing or short breaks. The generating AI can also monitor students' stress levels and suggest relaxation exercises as needed. For example, it can recommend simple stretching or meditation. This can reduce students' stress and improve their learning efficiency.

[0076] The AI ​​teacher system can also be equipped with the ability to analyze students' emotions while they are studying and adjust the learning content. For example, the generating AI can analyze students' emotions in real time and adjust the difficulty of the learning content. For example, it can lower the difficulty if their concentration is declining. The generating AI can also dynamically change the learning content based on the student's emotional data. For example, it can add questions related to topics that interest them. The generating AI can also monitor changes in students' emotions and adjust the learning content to maintain motivation. For example, if negative emotions are detected, it can switch to relaxing content. This makes it possible to adjust the learning content according to the student's emotions.

[0077] The AI ​​teacher system can also be equipped with a function to analyze students' emotions during learning and visualize their learning progress. For example, the generation AI can display learning progress in graphs and charts based on students' emotional data. For example, it can show the relationship between periods of high positive emotions and learning outcomes. The generation AI can also monitor changes in students' emotions and update progress in real time. For example, it can highlight goals achieved during periods of increased concentration. The generation AI can also visualize learning progress based on students' emotional data and report it to teachers and parents. For example, it can generate regular reports showing the relationship between emotions and learning outcomes. This makes it possible to visualize students' learning progress along with their emotional data.

[0078] The AI ​​teacher system can also be equipped with a function to analyze students' emotions during learning and visualize their learning progress. For example, the generation AI can display learning progress in graphs and charts based on students' emotional data. For example, it can show the relationship between periods of high positive emotions and learning outcomes. The generation AI can also monitor changes in students' emotions and update progress in real time. For example, it can highlight goals achieved during periods of increased concentration. The generation AI can also visualize learning progress based on students' emotional data and report it to teachers and parents. For example, it can generate regular reports showing the relationship between emotions and learning outcomes. This makes it possible to visualize students' learning progress along with their emotional data.

[0079] The AI ​​teacher system can also be equipped with a function to analyze students' emotions during learning and visualize their learning progress. For example, the generation AI can display learning progress in graphs and charts based on students' emotional data. For example, it can show the relationship between periods of high positive emotions and learning outcomes. The generation AI can also monitor changes in students' emotions and update progress in real time. For example, it can highlight goals achieved during periods of increased concentration. The generation AI can also visualize learning progress based on students' emotional data and report it to teachers and parents. For example, it can generate regular reports showing the relationship between emotions and learning outcomes. This makes it possible to visualize students' learning progress along with their emotional data.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The learning material generation unit generates learning materials using generative AI. For example, if a teacher inputs a prompt containing an instruction such as "Please create test questions on quadratic equations in junior high school mathematics," the unit generates appropriate test questions based on the instruction. Step 2: The test scoring unit uses generative AI to score the test answers and provide explanations for each question. For example, when a teacher inputs a prompt including instructions such as "Please score this math test and create explanations for each question," the test is scored and explanations for each question are generated. Step 3: The learning proficiency analysis unit uses generative AI to analyze students' learning proficiency and propose a follow-up plan. For example, if a teacher inputs a prompt including instructions such as, "Analyze the math test results for this class, identify areas where each student lacks understanding, and propose an improvement plan," the system will analyze the test results, identify areas where each student lacks understanding, and propose a specific follow-up plan.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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 AI 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 AI 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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 AI 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 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 learning material generation unit using generative AI; A test grading department that grades and explains test answers; A learning proficiency analysis unit that analyzes students' learning proficiency and proposes a follow-up plan. A system characterized by:

2. The learning material generation unit Generate individually optimized questions that reflect the student's past learning history 2. The system of claim 1.

3. The learning material generation unit Providing real-time feedback as the student solves the problem 2. The system of claim 1.

4. The learning material generation unit Analyze the student's emotions during learning and automatically generate positive feedback to increase motivation.

2. The system of claim 1.

5. The learning material generation unit Incorporating visual elements also caters to visual learners 2. The system of claim 1.

6. The learning material generation unit Customized for different grades and subjects to meet a wide range of educational needs 2. The system of claim 1.

7. The learning material generation unit Identifying topics of interest to said students and generating educational materials related to those topics 2. The system of claim 1.

8. The test marking unit Analyze the pattern of the answers, identify the causes of the incorrect answers, and reflect them in the explanations.

2. The system of claim 1.

Images