system

Abstract

The system according to this embodiment aims to streamline teachers' administrative tasks and improve the quality of education. [Solution] The system according to the embodiment comprises a creation unit, a scoring unit, an analysis unit, a generation unit, a customization unit, and a support unit. The creation unit creates tests. The scoring unit scores the tests created by the creation unit. The analysis unit analyzes student data. The generation unit generates teaching materials based on the data obtained by the analysis unit. The customization unit adapts the teaching materials generated by the generation unit to individual learning needs. The support unit assists teachers based on the information provided by the customization unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the school administrative work of teachers is diverse, and in particular, the creation and grading of tests and the generation of teaching materials corresponding to individual learning needs require time and labor.

[0005] The system according to the embodiment aims to improve the efficiency of the school administrative work of teachers and improve the quality of education.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a creation unit, a scoring unit, an analysis unit, a generation unit, a customization unit, and a support unit. The creation unit creates tests. The scoring unit scores the tests created by the creation unit. The analysis unit analyzes student data. The generation unit generates teaching materials based on the data obtained by the analysis unit. The customization unit adapts the teaching materials generated by the generation unit to individual learning needs. The support unit assists teachers based on the information provided by the customization unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline teachers' administrative tasks and improve the quality of education. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that utilizes generative AI to fully support teachers' administrative tasks. This system reduces the burden on teachers and improves the time and quality of education by automating time-consuming tasks such as test creation and grading. The system analyzes student data through generative AI and generates effective teaching materials based on specific learning needs. Furthermore, the system responds to the needs of each individual learner, supporting teachers in providing the optimal educational approach for each learner. As a result, teachers can reduce the burden of administrative tasks and improve the time and quality of education. For example, by automating test creation and grading using generative AI, teachers can dedicate more time to lesson preparation and interaction with students. In addition, by analyzing student data using generative AI and providing effective teaching materials, the system improves student learning effectiveness. Furthermore, by responding to the needs of each individual learner, the system enables individualized educational approaches and improves the quality of education. As a result, the system can fully support teachers' administrative tasks and improve the time and quality of education.

[0029] The system according to this embodiment comprises a creation unit, a scoring unit, an analysis unit, a generation unit, a customization unit, and a support unit. The creation unit creates tests. The creation unit can generate tests based on, for example, past questions or textbook content. The creation unit uses generation AI to analyze past questions or textbook content and generate new test questions. For example, the creation unit can analyze the question trends of past questions and create new questions in a similar format. The creation unit can also generate questions related to specific units based on textbook content. Furthermore, the creation unit can use generation AI to adjust the difficulty level of the questions and create tests that match the students' level of understanding. For example, the creation unit can generate tests that include a balanced mix of questions of varying difficulty levels based on students' past performance data. The scoring unit scores the tests created by the creation unit. The scoring unit can automatically score, for example, multiple-choice questions and written response questions. The scoring unit uses generation AI to calculate the correct answer rate for multiple-choice questions and analyze the content of written response questions to score them. For example, the scoring department can assign points to multiple-choice questions based on the percentage of correct answers. It can also score written response questions based on the accuracy of the content and the expressiveness of the answers. Furthermore, the scoring department can use generative AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, it can assign partial credit to written response questions based on the accuracy of the content. The analysis department analyzes student data. For example, it can analyze students' past performance and learning history. Using generative AI, the analysis department analyzes students' performance data and learning history to identify learning trends and weaknesses. For example, it can identify areas where students have low understanding based on their past test results. It can also track learning progress based on learning history. Furthermore, the analysis department can use generative AI to analyze students' learning styles and interests and address their individual learning needs. For example, it can identify learning styles such as visual, auditory, and experiential based on students' learning history. The generation unit generates educational materials based on the data obtained by the analysis unit. For example, the generation unit can generate effective educational materials based on the analysis results.The generation unit uses generative AI to generate learning materials tailored to students' learning needs. For example, the generation unit can generate materials specifically for areas where students have difficulty understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate materials that are tailored to the student's learning progress. For example, based on the student's learning progress, the generation unit can generate materials to help them move to the next step. The customization unit adapts the materials generated by the generation unit to individual learning needs. For example, the customization unit can create individualized learning plans based on the student's level of understanding and interests. The customization unit uses generative AI to create learning plans tailored to the student's learning style and interests. For example, the customization unit can provide video materials to visually-oriented students. It can also provide audio materials to auditory-oriented students. Furthermore, the customization unit can provide interactive materials to experiential-oriented students. The support unit assists teachers based on the information provided by the customization unit. For example, the support unit can assist teachers based on individualized learning plans. The support unit uses generative AI to provide appropriate support to teachers. For example, the support department can provide teachers with advice on teaching methods based on students' learning progress. It can also suggest supplementary materials to teachers based on students' understanding. Furthermore, the support department can use generative AI to reduce the burden on teachers. For instance, it can automate tasks such as lesson preparation and grading, allowing teachers to focus on educational activities. In this way, the system according to this embodiment can fully support teachers' administrative tasks and improve the time and quality of education.

[0030] The test creation department is responsible for creating tests. For example, the department can generate tests based on past questions or textbook content. Using generative AI, the department analyzes past questions and textbook content to generate new test questions. For instance, it can analyze trends in past questions and create new questions in a similar format. It can also generate questions related to specific units based on textbook content. Furthermore, the department can use generative AI to adjust the difficulty level of questions, creating tests tailored to students' understanding. For example, it can generate tests with a balanced mix of questions of varying difficulty levels based on students' past performance data. Specifically, the generative AI uses natural language processing to analyze textbooks and past questions, extracting important keywords and concepts. This allows for the automatic generation of questions related to specific units. Additionally, the generative AI analyzes past test results and student performance data to adjust the format and difficulty level of questions, creating questions tailored to each student's understanding. For example, it can provide more difficult questions to students with high understanding and basic questions to students with lower understanding. Furthermore, the department can use generative AI to increase the variety of questions. For example, presenting the same concept in different formats can deepen students' understanding. This allows the test development team to create tests efficiently and effectively and accurately assess students' learning outcomes.

[0031] The scoring department scores the tests created by the creation department. The scoring department can automatically score multiple-choice and written response questions, for example. The scoring department uses generative AI to calculate the correct answer rate for multiple-choice questions and analyze the content of written response questions for scoring. For example, the scoring department can assign points to multiple-choice questions based on the correct answer rate. The scoring department can also score written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, the scoring department can use generative AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, the scoring department can assign partial credit to written response questions based on the accuracy of the content. Specifically, the generative AI uses natural language processing technology to analyze written response answers and evaluate keyword matching and contextual consistency. This allows for higher scores to be given to answers with accurate content and logical structure. In addition, since the generative AI automatically distributes partial credit, consistency and fairness in scoring can be maintained. For example, even if only part of an answer is correct, the student's effort can be evaluated by awarding appropriate partial credit. Furthermore, the grading department can use generative AI to quickly provide feedback on the grading results. This allows students to identify their weaknesses early and use that information to improve their future learning. As a result, the grading department can grade tests efficiently and accurately, and appropriately evaluate students' learning outcomes.

[0032] The analytics department analyzes student data. For example, it can analyze students' past grades and learning history. Using generative AI, the analytics department analyzes students' grade data and learning history to identify learning trends and weaknesses. For example, based on students' past test results, the analytics department can identify areas where students have low understanding. It can also grasp learning progress based on learning history. Furthermore, using generative AI, the analytics department can analyze students' learning styles and interests to address individual learning needs. For example, based on students' learning history, the analytics department can identify learning styles such as visual, auditory, and experiential learning. Specifically, the generative AI analyzes students' past test results and learning history to understand each student's learning patterns and level of understanding in detail. This allows it to identify areas of low understanding in specific subjects or units and provide data to address individual learning needs. In addition, to analyze students' learning styles and interests, the generative AI analyzes learning history and behavioral data to identify learning styles such as visual, auditory, and experiential learning. This allows it to propose the most suitable learning method for each student. Furthermore, the analytics department can use generative AI to monitor learning progress in real time and provide timely feedback. This allows students to always know their learning status and create effective learning plans. This enables the analytics department to analyze students' learning data in detail and provide information to address individual learning needs.

[0033] The generation unit generates learning materials based on data obtained by the analysis unit. For example, the generation unit can generate effective learning materials based on the analysis results. The generation unit uses generation AI to generate learning materials that meet the learning needs of students. For example, the generation unit can generate materials specifically for areas where students have a low level of understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate materials that are tailored to the student's learning progress. For example, based on the student's learning progress, the generation unit can generate materials to help them move on to the next step. Specifically, the generation AI automatically generates learning materials tailored to each student's level of understanding and learning style based on data provided by the analysis unit. This allows students to use learning materials that are best suited to their learning needs. For example, for areas where students have a low level of understanding, it generates materials that include detailed explanations and additional practice problems to support students in deepening their understanding. Also, for questions that students frequently get wrong, it can analyze the cause of the errors and generate supplementary materials to resolve misunderstandings. Furthermore, the generation unit generates materials to help students move on to the next step according to their learning progress. This allows students to learn at their own pace and achieve effective learning outcomes. This allows the generation unit to produce effective learning materials that meet students' learning needs, thereby improving the quality of learning.

[0034] The customization unit adapts the materials generated by the generation unit to individual learning needs. For example, the customization unit can create individualized learning plans based on students' comprehension levels and interests. The customization unit uses generational AI to create learning plans tailored to students' learning styles and interests. For example, the customization unit can provide video-based materials to visually-oriented students. It can also provide audio-based materials to auditory-oriented students. Furthermore, the customization unit can provide interactive materials to experiential-oriented students. Specifically, the generational AI analyzes students' learning history and interests and automatically creates the optimal learning plan for each student. This allows students to use materials that match their learning style and interests. For example, visually-oriented students can be provided with materials that heavily utilize videos and diagrams, deepening their understanding through visual information. Auditory-oriented students can be provided with audio commentary and podcast-style materials, allowing them to learn through auditory information. Furthermore, experiential-oriented students can be provided with materials that include simulations and interactive exercises, deepening their learning through actual experience. This allows the customization department to provide individualized learning plans tailored to each student's learning style and interests, thereby supporting effective learning.

[0035] The support department assists teachers based on information provided by the customization department. For example, the support department can assist teachers based on individual learning plans. The support department uses generative AI to provide appropriate support to teachers. For example, the support department can provide teachers with advice on teaching methods according to the students' learning progress. The support department can also suggest supplementary materials to teachers according to the students' level of understanding. Furthermore, the support department can use generative AI to help reduce the burden on teachers. For example, the support department can automate lesson preparation and grading so that teachers can concentrate on teaching activities. Specifically, the generative AI analyzes students' learning data and suggests appropriate teaching methods and materials to teachers based on each student's level of understanding and progress. This allows teachers to provide instruction tailored to the needs of each student. In addition, the generative AI reduces the burden on teachers by automating lesson preparation and grading, providing an environment where teachers can concentrate on teaching activities. For example, in lesson preparation, the generative AI assists in creating materials and planning lessons, providing support for teachers to conduct effective lessons. Furthermore, in the grading process, the generating AI will automatically perform the grading, allowing teachers to provide feedback quickly. This will enable the support department to reduce the burden on teachers and provide support to improve the quality of education.

[0036] The test creation unit can generate tests based on past questions and textbook content. For example, it can analyze the trends in past questions and create new questions in a similar format. The unit uses a generation AI to analyze the trends in past questions and generate new questions. For example, it can create new questions in a similar format based on the trends in past questions. Furthermore, the unit can generate questions related to specific units based on textbook content. The unit uses a generation AI to analyze textbook content and generate questions related to specific units. For example, it can generate questions related to specific units based on textbook content. This allows for improved test quality by generating tests based on past questions and textbook content.

[0037] The scoring unit can automatically score multiple-choice and written response questions. For example, the scoring unit can assign points to multiple-choice questions based on the percentage of correct answers. The scoring unit uses a generative AI to calculate the percentage of correct answers to multiple-choice questions and assign points. For example, the scoring unit can assign points to multiple-choice questions based on the percentage of correct answers. The scoring unit can also score written response questions based on the accuracy of the content and the expressiveness of the writing. The scoring unit uses a generative AI to analyze the content of written response questions and assigns points based on the accuracy of the content and the expressiveness of the writing. For example, the scoring unit can assign points to written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, the scoring unit can improve the accuracy of scoring by appropriately allocating partial credit. The scoring unit uses a generative AI to assign partial credit to written response questions based on the accuracy of the content. For example, the scoring unit can assign partial credit to written response questions based on the accuracy of the content. This allows for improved grading efficiency by automatically scoring multiple-choice and written response questions.

[0038] The analytics department can analyze students' past performance and learning history. For example, the analytics department can identify areas where students have a low level of understanding based on their past test results. The analytics department uses generative AI to analyze students' past test results and identify areas where students have a low level of understanding. For example, the analytics department can identify areas where students have a low level of understanding based on their past test results. The analytics department can also grasp the progress of learning based on their learning history. The analytics department uses generative AI to analyze students' learning history and grasp the progress of learning. For example, the analytics department can grasp the progress of learning based on their learning history. Furthermore, the analytics department can analyze students' learning styles and interests and respond to their individual learning needs. The analytics department uses generative AI to analyze students' learning styles and interests and respond to their individual learning needs. For example, the analytics department can identify learning styles such as visual, auditory, and experiential based on students' learning history. This allows the analytics department to understand students' learning status by analyzing their past performance and learning history.

[0039] The generation unit can generate effective learning materials based on the analysis results. For example, the generation unit can generate learning materials specifically tailored to areas where students have a low level of understanding. The generation unit uses a generation AI to generate learning materials specifically tailored to areas where students have a low level of understanding, based on the analysis results. For example, the generation unit can generate learning materials specifically tailored to areas where students have a low level of understanding. The generation unit can also generate supplementary materials for questions that students frequently get wrong. The generation unit uses a generation AI to generate supplementary materials for questions that students frequently get wrong, based on the analysis results. For example, the generation unit can generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate learning materials tailored to the student's learning progress. The generation unit uses a generation AI to generate learning materials tailored to the student's learning progress, based on the analysis results. For example, the generation unit can generate materials to help students move on to the next step based on their learning progress. In this way, by generating effective learning materials based on the analysis results, the effectiveness of students' learning can be improved.

[0040] The customization department can create individualized learning plans based on students' understanding and interests. For example, it can provide video-based learning materials to visually-oriented students. The customization department uses generative AI to create learning plans tailored to students' learning styles and interests. For example, it can provide video-based learning materials to visually-oriented students. It can also provide audio-based learning materials to auditory-oriented students. Furthermore, it can provide interactive learning materials to experiential-oriented students. This allows for the creation of individualized learning plans based on students' understanding and interests, thereby addressing their individual learning needs.

[0041] The support department can assist teachers based on individual learning plans. For example, the support department can provide advice on teaching methods to teachers based on the students' learning progress. The support department can use generative AI to provide advice on teaching methods to teachers based on the students' learning progress. For example, the support department can provide advice on teaching methods to teachers based on the students' learning progress. The support department can also suggest the provision of supplementary materials to teachers based on the students' level of understanding. The support department can use generative AI to suggest the provision of supplementary materials to teachers based on the students' level of understanding. For example, the support department can suggest the provision of supplementary materials to teachers based on the students' level of understanding. Furthermore, the support department can use generative AI to provide support to reduce the burden on teachers. The support department can use generative AI to automate lesson preparation and grading, allowing teachers to concentrate on educational activities. For example, the support department can automate lesson preparation and grading, allowing teachers to concentrate on educational activities. This reduces the burden on teachers by supporting them based on individual learning plans.

[0042] The creation unit can analyze past test results and generate questions tailored to students' understanding levels. For example, the creation unit can generate tests that include many questions in areas where students have a low level of understanding, based on students' past test results. The creation unit uses generation AI to analyze past test results and generate questions tailored to students' understanding levels. For example, the creation unit can generate tests that include many questions in areas where students have a low level of understanding, based on students' past test results. The creation unit can also generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. The creation unit uses generation AI to generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. For example, the creation unit can generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. Furthermore, the creation unit can generate tests that include questions that consider the balance of understanding levels, based on students' past test results. The creation unit uses generation AI to generate tests that include questions that consider the balance of understanding levels, based on students' past test results. For example, the creation unit can generate tests that include questions that consider the balance of understanding levels, based on students' past test results. This allows for the generation of questions tailored to each student's level of understanding, thereby improving the effectiveness of their learning.

[0043] The test creation unit can generate tests based not only on textbook content but also on the latest research findings and news articles. For example, the unit can generate questions that incorporate the latest research findings in addition to textbook content. The test creation unit uses generative AI to generate tests based not only on textbook content but also on the latest research findings and news articles. For example, the unit can generate questions that incorporate the latest research findings in addition to textbook content. Furthermore, the unit can generate questions that incorporate the latest news articles in addition to textbook content. The test creation unit uses generative AI to generate questions that incorporate the latest news articles in addition to textbook content. For example, the unit can generate questions that incorporate the latest news articles in addition to textbook content. In addition, the unit can generate questions that incorporate the latest technological trends in addition to textbook content. The test creation unit uses generative AI to generate questions that incorporate the latest technological trends in addition to textbook content. For example, the unit can generate questions that incorporate the latest technological trends in addition to textbook content. This allows for improved test quality by generating tests based not only on textbook content but also on the latest research findings and news articles.

[0044] The creation unit can generate tests in different formats depending on the student's learning style. For example, if the student prefers multiple-choice questions, the generation AI will create a test that contains many multiple-choice questions. The creation unit uses generation AI to generate tests in different formats depending on the student's learning style. For example, if the student prefers multiple-choice questions, the generation AI can create a test that contains many multiple-choice questions. The creation unit can also use generation AI to create a test that contains many written-response questions if the student prefers written-response questions. The creation unit uses generation AI to create a test that contains many written-response questions if the student prefers written-response questions. For example, if the student prefers written-response questions, the generation AI can create a test that contains many written-response questions. Furthermore, if the student prefers practical skills problems, the generation AI can create a test that contains many practical skills problems. The creation unit uses generation AI to create a test that contains many practical skills problems if the student prefers practical skills problems. For example, if the creation department knows that students prefer practical skills-based questions, the generation AI can create a test that includes many practical skills-based questions. This allows for the creation of tests tailored to students' learning styles, thereby improving their learning effectiveness.

[0045] The creation unit can generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the creation unit's generative AI will create a test that includes many science-related questions. The creation unit uses generative AI to generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the creation unit's generative AI can create a test that includes many science-related questions. The creation unit can also use generative AI to create tests that include many history-related questions if a student is interested in history. The creation unit uses generative AI to create tests that include many history-related questions if a student is interested in history. For example, if a student is interested in history, the creation unit's generative AI can create a test that includes many history-related questions. Furthermore, if a student is interested in literature, the creation unit's generative AI can create a test that includes many literature-related questions. The creation unit uses generative AI to create tests that include many literature-related questions if a student is interested in literature. For example, if a student is interested in literature, the creation unit's generative AI can create a test that includes many literature-related questions. This allows for the generation of tests based on students' areas of interest, thereby improving their motivation to learn.

[0046] The scoring unit can improve the accuracy of scoring by referring to past answer patterns during scoring. For example, the scoring unit can score similar answers with high accuracy based on the student's past answer patterns. The scoring unit uses generative AI to improve the accuracy of scoring by referring to past answer patterns during scoring. For example, the scoring unit can score similar answers with high accuracy based on the student's past answer patterns. The scoring unit can also analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. The scoring unit uses generative AI to analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. For example, the scoring unit can analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. Furthermore, the scoring unit can appropriately allocate partial points based on the student's past answer patterns and score accordingly. The scoring unit uses generative AI to appropriately allocate partial points based on the student's past answer patterns and score accordingly. For example, the scoring unit can appropriately allocate partial points based on the student's past answer patterns and score accordingly. This allows for improved scoring accuracy by referencing past answer patterns.

[0047] The scoring unit can score essay questions using multiple evaluation criteria. For example, the scoring unit can score essay questions using accuracy of content and expressiveness as evaluation criteria. The scoring unit uses generative AI to score essay questions using multiple evaluation criteria. For example, the scoring unit can score essay questions using accuracy of content and expressiveness as evaluation criteria. The scoring unit can also score essay questions using logical structure and persuasiveness as evaluation criteria. The scoring unit uses generative AI to score essay questions using logical structure and persuasiveness as evaluation criteria. For example, the scoring unit can score essay questions using logical structure and persuasiveness as evaluation criteria. Furthermore, the scoring unit can score essay questions using creativity and originality as evaluation criteria. The scoring unit uses generative AI to score essay questions using creativity and originality as evaluation criteria. For example, the scoring unit can score essay questions using creativity and originality as evaluation criteria. This allows for improved accuracy in grading essay-type questions by using multiple evaluation criteria.

[0048] The grading system can provide individualized feedback based on students' learning history during grading. For example, the grading system can provide feedback on areas where students have a low level of understanding, based on their learning history. The grading system can use generative AI to provide individualized feedback based on students' learning history during grading. For example, the grading system can provide feedback on areas where students have a low level of understanding, based on their learning history. The grading system can also provide feedback on areas where students have a high level of understanding, based on their learning history. The grading system can use generative AI to provide feedback on areas where students have a high level of understanding, based on their learning history. For example, the grading system can provide feedback on areas where students have a high level of understanding, based on their learning history. Furthermore, the grading system can provide feedback tailored to the student's learning progress, based on their learning history. The grading system can use generative AI to provide feedback tailored to the student's learning progress, based on their learning history. For example, the grading system can provide feedback tailored to the student's learning progress, based on their learning history. By providing individualized feedback based on students' learning history, the effectiveness of students' learning can be improved.

[0049] The scoring department can adjust the scope of the next test based on the scoring results. For example, the scoring department can include areas where students have a low level of understanding in the scope of the next test. The scoring department uses generative AI to adjust the scope of the next test based on the scoring results. For example, the scoring department can include areas where students have a low level of understanding in the scope of the next test. The scoring department can also exclude areas where students have a high level of understanding from the scope of the next test. The scoring department uses generative AI to exclude areas where students have a high level of understanding from the scope of the next test based on the scoring results. For example, the scoring department can exclude areas where students have a high level of understanding from the scope of the next test. Furthermore, the scoring department can set a scope of questions that takes into account the balance of understanding. The scoring department uses generative AI to set a scope of questions that takes into account the balance of understanding based on the scoring results. For example, the scoring department can set a scope of questions that takes into account the balance of understanding. This allows for adjustments to the scope of the next test based on the scoring results, thereby improving students' learning effectiveness.

[0050] The analysis department can include not only students' learning history but also their lifestyle and health status in its analysis. For example, the analysis department can analyze learning efficiency based on students' lifestyle. The analysis department uses generative AI to include not only students' learning history but also their lifestyle and health status in its analysis. For example, the analysis department can analyze learning efficiency based on students' lifestyle. Furthermore, the analysis department can analyze learning progress based on students' health status. The analysis department uses generative AI to analyze learning progress based on students' health status. For example, the analysis department can analyze learning progress based on students' health status. In addition, the analysis department can analyze the effectiveness of learning based on students' lifestyle and health status. The analysis department uses generative AI to analyze the effectiveness of learning based on students' lifestyle and health status. For example, the analysis department can analyze the effectiveness of learning based on students' lifestyle and health status. This allows for a more comprehensive learning analysis by considering lifestyle and health status.

[0051] The analysis department can provide individualized learning advice based on the analysis results. For example, the analysis department can provide learning advice for areas where understanding is low. The analysis department can provide individualized learning advice based on the analysis results using generative AI. For example, the analysis department can provide learning advice for areas where understanding is low. The analysis department can also provide learning advice for areas where understanding is high. The analysis department can provide learning advice for areas where understanding is high using generative AI. For example, the analysis department can provide learning advice for areas where understanding is high. Furthermore, the analysis department can provide learning advice tailored to the student's learning progress. The analysis department can provide learning advice tailored to the student's learning progress using generative AI. For example, the analysis department can provide learning advice tailored to the student's learning progress. By providing individualized learning advice, the effectiveness of students' learning can be improved.

[0052] The analysis department can perform analyses while considering the student's learning environment. For example, if a student is studying at home, the generative AI can analyze the efficiency of their home learning. The analysis department uses generative AI to perform analyses while considering the student's learning environment. For example, if a student is studying at home, the generative AI can analyze the efficiency of their home learning. The analysis department can also use generative AI to analyze the efficiency of students studying at school. For example, if a student is studying at school, the generative AI can analyze the efficiency of their school learning. Furthermore, if a student is studying in the library, the generative AI can analyze the efficiency of their library learning. The analysis department uses generative AI to analyze the efficiency of students studying in the library. For example, if a student is studying in the library, the generative AI can analyze the efficiency of their library learning. This allows for more accurate learning analysis by considering the learning environment.

[0053] The analysis department can propose the formation of learning groups based on the analysis results. For example, the analysis department can group students with low levels of understanding together. The analysis department can also propose the formation of learning groups based on the analysis results using generative AI. For example, the analysis department can group students with low levels of understanding together. The analysis department can also group students with high levels of understanding together. The analysis department can use generative AI to form groups of students with high levels of understanding together based on the analysis results. For example, the analysis department can form groups of students with high levels of understanding together. Furthermore, the analysis department can form groups that take into account a balance of understanding levels. The analysis department uses generative AI to form groups that take into account a balance of understanding levels based on the analysis results. For example, the analysis department can form groups that take into account a balance of understanding levels. In this way, by proposing the formation of learning groups, collaborative learning among students can be promoted.

[0054] The generation unit can generate learning materials to reinforce students' weaknesses based on the analysis results. For example, the generation unit can generate materials specifically tailored to areas where students have a low level of understanding. The generation unit uses a generation AI to generate learning materials to reinforce students' weaknesses based on the analysis results. For example, the generation unit can generate materials specifically tailored to areas where students have a low level of understanding. The generation unit can also generate supplementary materials for questions that students frequently get wrong. The generation unit uses a generation AI to generate supplementary materials for questions that students frequently get wrong based on the analysis results. For example, the generation unit can generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate supplementary materials tailored to the student's learning progress. The generation unit uses a generation AI to generate supplementary materials tailored to the student's learning progress based on the analysis results. For example, the generation unit can generate supplementary materials tailored to the student's learning progress. By generating learning materials to reinforce students' weaknesses, the learning effect can be improved.

[0055] The generation unit can incorporate the latest research findings and case studies into the content of educational materials. For example, the generation unit can generate scientific educational materials based on the latest research findings. The generation unit uses generational AI to incorporate the latest research findings and case studies into the content of educational materials. For example, the generation unit can generate scientific educational materials based on the latest research findings. The generation unit can also generate practical educational materials based on the latest case studies. The generation unit uses generational AI to generate practical educational materials based on the latest case studies. For example, the generation unit can generate practical educational materials based on the latest case studies. Furthermore, the generation unit can generate technical educational materials based on the latest technological trends. The generation unit uses generational AI to generate technical educational materials based on the latest technological trends. For example, the generation unit can generate technical educational materials based on the latest technological trends. This allows for an improvement in the quality of educational materials by incorporating the latest research findings and case studies.

[0056] The generation unit can generate different formats of learning materials depending on the student's learning style. For example, if a student prefers visual learning, the generation AI can provide video-format learning materials. The generation unit uses the generation AI to generate different formats of learning materials depending on the student's learning style. For example, if a student prefers visual learning, the generation AI can provide video-format learning materials. The generation unit can also use the generation AI to provide audio-format learning materials if a student prefers auditory learning. The generation unit uses the generation AI to provide audio-format learning materials if a student prefers auditory learning. For example, if a student prefers auditory learning, the generation AI can provide audio-format learning materials. Furthermore, if a student prefers experiential learning, the generation unit can provide interactive-format learning materials. The generation unit uses the generation AI to provide interactive-format learning materials if a student prefers experiential learning. For example, if a student prefers experiential learning, the generation AI can provide interactive-format learning materials. By generating learning materials tailored to the student's learning style, learning effectiveness can be improved.

[0057] The generation unit can generate educational materials that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can provide science-related educational materials. The generation unit uses the generation AI to generate educational materials that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can provide science-related educational materials. The generation unit can also use the generation AI to provide history-related educational materials if a student is interested in history. For example, if a student is interested in history, the generation AI can provide history-related educational materials. Furthermore, if a student is interested in literature, the generation AI can provide literature-related educational materials. The generation unit uses the generation AI to provide literature-related educational materials if a student is interested in literature. For example, if a student is interested in literature, the generation AI can provide literature-related educational materials. This allows for increased motivation to learn by generating educational materials based on students' areas of interest.

[0058] The customization function can create optimal learning plans based on a student's past learning history. For example, the customization function can create learning plans specifically tailored to areas where the student has a low level of understanding. The customization function uses generative AI to create optimal learning plans based on a student's past learning history. For example, the customization function can create learning plans specifically tailored to areas where the student has a low level of understanding. The customization function can also create learning plans for questions that the student frequently gets wrong. The customization function uses generative AI to create learning plans for questions that the student frequently gets wrong, based on a student's past learning history. For example, the customization function can create learning plans for questions that the student frequently gets wrong. Furthermore, the customization function can create learning plans that are tailored to the student's learning progress. The customization function uses generative AI to create learning plans that are tailored to the student's learning progress, based on a student's past learning history. For example, the customization function can create learning plans that are tailored to the student's learning progress. By creating optimal learning plans based on a student's past learning history, the effectiveness of learning can be improved.

[0059] The customization function can take into account students' lifestyles and health conditions when creating learning plans. For example, the customization function can create learning plans that consider learning efficiency based on students' lifestyles. The customization function uses generative AI to take students' lifestyles and health conditions into account when creating learning plans. For example, the customization function can create learning plans that consider learning efficiency based on students' lifestyles. The customization function can also create learning plans that consider learning progress based on students' health conditions. The customization function uses generative AI to create learning plans that consider learning progress based on students' health conditions. For example, the customization function can create learning plans that consider learning progress based on students' health conditions. Furthermore, the customization function can create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. The customization function uses generative AI to create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. For example, the customization function can create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. This allows for improved learning effectiveness by taking students' lifestyles and health conditions into consideration.

[0060] The customization function can create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at home. The customization function uses generative AI to create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at home. Furthermore, if a student is studying at school, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at school. The customization function uses generative AI to create learning plans that take into account the efficiency of studying at school. For example, if a student is studying at school, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at school. Furthermore, if a student is studying in the library, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying in the library. The customization function uses generative AI to create learning plans that take into account the efficiency of studying in the library. For example, if a student is studying in the library, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying in the library. This allows us to improve learning effectiveness by taking into account the students' learning environment.

[0061] The customization function can reflect students' areas of interest in their learning plans. For example, if a student is interested in science, the customization function's generative AI can create a science-related learning plan. The customization function uses generative AI to reflect students' areas of interest in their learning plans. For example, if a student is interested in science, the customization function's generative AI can create a science-related learning plan. The customization function can also use generative AI to create a history-related learning plan if a student is interested in history. For example, if a student is interested in history, the customization function's generative AI can create a history-related learning plan. Furthermore, if a student is interested in literature, the customization function's generative AI can create a literature-related learning plan. The customization function uses generative AI to create a literature-related learning plan if a student is interested in literature. For example, if a student is interested in literature, the customization function's generative AI can create a literature-related learning plan. By reflecting students' areas of interest, this can improve their motivation to learn.

[0062] The support department can provide optimal support methods based on the teacher's past teaching history. For example, the support department can provide support methods for areas where students have a low level of understanding. The support department uses generative AI to provide optimal support methods based on the teacher's past teaching history. For example, the support department can provide support methods for areas where students have a low level of understanding. The support department can also provide support methods for problems that students frequently get wrong. The support department uses generative AI to provide support methods for problems that students frequently get wrong, based on the teacher's past teaching history. For example, the support department can provide support methods for problems that students frequently get wrong. Furthermore, the support department can provide support methods tailored to the student's learning progress. The support department uses generative AI to provide support methods tailored to the student's learning progress, based on the teacher's past teaching history. For example, the support department can provide support methods tailored to the student's learning progress. This reduces the burden on teachers by providing optimal support methods based on their past teaching history.

[0063] The support department can incorporate the latest educational theories and case studies into its support services. For example, the support department can provide scientific support services based on the latest educational theories. The support department can use generative AI to incorporate the latest educational theories and case studies into its support services. For example, the support department can provide scientific support services based on the latest educational theories. The support department can also provide practical support services based on the latest case studies. The support department can use generative AI to provide practical support services based on the latest case studies. For example, the support department can provide practical support services based on the latest case studies. Furthermore, the support department can provide technical support services based on the latest technological trends. The support department can use generative AI to provide technical support services based on the latest technological trends. For example, the support department can provide technical support services based on the latest technological trends. By incorporating the latest educational theories and case studies, the quality of support services can be improved.

[0064] The support system can provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the support system can use its generative AI to provide visual support methods. The support system can use its generative AI to provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the support system can use its generative AI to provide visual support methods. The support system can also use its generative AI to provide auditory support methods if a teacher prefers auditory instruction. For example, if a teacher prefers auditory instruction, the support system can use its generative AI to provide auditory support methods. Furthermore, if a teacher prefers experiential instruction, the support system can use its generative AI to provide experiential support methods. The support system can use its generative AI to provide experiential support methods if a teacher prefers experiential instruction. For example, if a teacher prefers experiential instruction, the support system can use its generative AI to provide experiential support methods. By providing support methods tailored to the teacher's teaching style, the support system can reduce the burden on teachers.

[0065] The support department can reflect the teacher's areas of interest in the support content. For example, if a teacher is interested in science, the support department's generative AI can provide science-related support content. The support department uses generative AI to reflect the teacher's areas of interest in the support content. For example, if a teacher is interested in science, the support department's generative AI can provide science-related support content. Also, if a teacher is interested in history, the support department's generative AI can provide history-related support content. The support department uses generative AI to provide history-related support content if a teacher is interested in history. For example, if a teacher is interested in history, the support department's generative AI can provide history-related support content. Furthermore, if a teacher is interested in literature, the support department's generative AI can provide literature-related support content. In this way, the quality of support content can be improved by reflecting the teacher's areas of interest.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The test creation unit can generate tests tailored to students' learning progress based on their learning history. For example, if a student is struggling with a particular unit, the unit can create a test that includes many questions related to that unit. It can also create tests with more difficult questions in areas where students excel. Furthermore, the unit can adjust the frequency and content of tests according to the student's learning pace. This allows for improved learning effectiveness by providing tests that match the student's learning situation.

[0068] The analysis department can include not only students' learning history but also their lifestyle and health status in its analysis. For example, it can analyze learning efficiency based on students' lifestyle habits. It can also analyze learning progress based on students' health status. Furthermore, it can analyze the effectiveness of learning based on students' lifestyle habits and health status. This allows for a more comprehensive learning analysis by considering lifestyle habits and health status.

[0069] The customization function can create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the generating AI can create a learning plan that considers the efficiency of home learning. Similarly, if a student is studying at school, the generating AI can create a learning plan that considers the efficiency of school learning. Furthermore, if a student is studying in the library, the generating AI can create a learning plan that considers the efficiency of library learning. By considering the student's learning environment, learning effectiveness can be improved.

[0070] The creation function can generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can create a test with many science-related questions. Similarly, if a student is interested in history, the generation AI can create a test with many history-related questions. Furthermore, if a student is interested in literature, the generation AI can create a test with many literature-related questions. This allows for the generation of tests based on students' areas of interest, thereby improving their motivation to learn.

[0071] The customization feature allows for the creation of learning plans that take into account students' lifestyles and health conditions. For example, a learning plan can be created that considers learning efficiency based on the student's lifestyle. Similarly, a learning plan can be created that considers learning progress based on the student's health condition. Furthermore, a learning plan can be created that considers learning effectiveness based on the student's lifestyle and health condition. This allows for improved learning effectiveness by taking students' lifestyles and health conditions into account.

[0072] The support system can provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the generative AI can provide visual support methods. Similarly, if a teacher prefers auditory instruction, the generative AI can provide auditory support methods. Furthermore, if a teacher prefers experiential instruction, the generative AI can provide experiential support methods. This reduces the burden on teachers by providing support methods tailored to their teaching style.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The creation unit creates the test. The creation unit can generate tests based on past questions and textbook content. Using generation AI, it analyzes past questions and textbook content to generate new test questions. For example, the creation unit can analyze the trends in past questions and create new questions in a similar format. It can also generate questions related to specific units based on textbook content. Furthermore, using generation AI, it can adjust the difficulty level of the questions to create tests that match the students' level of understanding. For example, based on students' past performance data, it can generate tests that include a balanced mix of questions of varying difficulty levels. Step 2: The scoring unit scores the tests created by the creation unit. The scoring unit can automatically score multiple-choice and written response questions. Using a generation AI, it calculates the correct answer rate for multiple-choice questions and analyzes the content of written response questions for scoring. For example, it can assign points to multiple-choice questions based on the correct answer rate. It can also score written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, it can use the generation AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, it can assign partial credit to written response questions based on the accuracy of the content. Step 3: The analytics department analyzes student data. The analytics department can analyze students' past performance and learning history. Using generative AI, it analyzes students' performance data and learning history to identify learning trends and weaknesses. For example, it can identify areas where students have a low level of understanding based on their past test results. It can also grasp the progress of learning based on the learning history. Furthermore, it can use generative AI to analyze students' learning styles and interests and address their individual learning needs. For example, it can identify learning styles such as visual, auditory, and experiential based on students' learning history. Step 4: The generation unit generates learning materials based on the data obtained by the analysis unit. The generation unit can generate effective learning materials based on the analysis results. Using the generation AI, it generates learning materials that meet the learning needs of students. For example, it can generate materials that specialize in areas where students have a low level of understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, it can generate learning materials that are tailored to the student's learning progress. For example, it can generate materials to help students move on to the next step based on their learning progress. Step 5: The customization unit adapts the materials generated by the generation unit to individual learning needs. The customization unit can create individualized learning plans based on students' understanding and interests. Using the generation AI, it creates learning plans tailored to students' learning styles and interests. For example, video materials can be provided for visually-oriented students. Audio materials can be provided for auditory-oriented students. Furthermore, interactive materials can be provided for experiential-oriented students. Step 6: The support department assists teachers based on the information provided by the customization department. The support department can assist teachers based on individual learning plans. It uses generative AI to provide appropriate support to teachers. For example, it can provide teachers with advice on teaching methods according to the students' learning progress. It can also suggest supplementary materials to teachers according to the students' level of understanding. Furthermore, it can use generative AI to help reduce the burden on teachers. For example, it can automate lesson preparation and grading so that teachers can concentrate on teaching activities.

[0075] (Example of form 2) The system according to an embodiment of the present invention is a system that utilizes generative AI to fully support teachers' administrative tasks. This system reduces the burden on teachers and improves the time and quality of education by automating time-consuming tasks such as test creation and grading. The system analyzes student data through generative AI and generates effective teaching materials based on specific learning needs. Furthermore, the system responds to the needs of each individual learner, supporting teachers in providing the optimal educational approach for each learner. As a result, teachers can reduce the burden of administrative tasks and improve the time and quality of education. For example, by automating test creation and grading using generative AI, teachers can dedicate more time to lesson preparation and interaction with students. In addition, by analyzing student data using generative AI and providing effective teaching materials, the system improves student learning effectiveness. Furthermore, by responding to the needs of each individual learner, the system enables individualized educational approaches and improves the quality of education. As a result, the system can fully support teachers' administrative tasks and improve the time and quality of education.

[0076] The system according to this embodiment comprises a creation unit, a scoring unit, an analysis unit, a generation unit, a customization unit, and a support unit. The creation unit creates tests. The creation unit can generate tests based on, for example, past questions or textbook content. The creation unit uses generation AI to analyze past questions or textbook content and generate new test questions. For example, the creation unit can analyze the question trends of past questions and create new questions in a similar format. The creation unit can also generate questions related to specific units based on textbook content. Furthermore, the creation unit can use generation AI to adjust the difficulty level of the questions and create tests that match the students' level of understanding. For example, the creation unit can generate tests that include a balanced mix of questions of varying difficulty levels based on students' past performance data. The scoring unit scores the tests created by the creation unit. The scoring unit can automatically score, for example, multiple-choice questions and written response questions. The scoring unit uses generation AI to calculate the correct answer rate for multiple-choice questions and analyze the content of written response questions to score them. For example, the scoring department can assign points to multiple-choice questions based on the percentage of correct answers. It can also score written response questions based on the accuracy of the content and the expressiveness of the answers. Furthermore, the scoring department can use generative AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, it can assign partial credit to written response questions based on the accuracy of the content. The analysis department analyzes student data. For example, it can analyze students' past performance and learning history. Using generative AI, the analysis department analyzes students' performance data and learning history to identify learning trends and weaknesses. For example, it can identify areas where students have low understanding based on their past test results. It can also track learning progress based on learning history. Furthermore, the analysis department can use generative AI to analyze students' learning styles and interests and address their individual learning needs. For example, it can identify learning styles such as visual, auditory, and experiential based on students' learning history. The generation unit generates educational materials based on the data obtained by the analysis unit. For example, the generation unit can generate effective educational materials based on the analysis results.The generation unit uses generative AI to generate learning materials tailored to students' learning needs. For example, the generation unit can generate materials specifically for areas where students have difficulty understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate materials that are tailored to the student's learning progress. For example, based on the student's learning progress, the generation unit can generate materials to help them move to the next step. The customization unit adapts the materials generated by the generation unit to individual learning needs. For example, the customization unit can create individualized learning plans based on the student's level of understanding and interests. The customization unit uses generative AI to create learning plans tailored to the student's learning style and interests. For example, the customization unit can provide video materials to visually-oriented students. It can also provide audio materials to auditory-oriented students. Furthermore, the customization unit can provide interactive materials to experiential-oriented students. The support unit assists teachers based on the information provided by the customization unit. For example, the support unit can assist teachers based on individualized learning plans. The support unit uses generative AI to provide appropriate support to teachers. For example, the support department can provide teachers with advice on teaching methods based on students' learning progress. It can also suggest supplementary materials to teachers based on students' understanding. Furthermore, the support department can use generative AI to reduce the burden on teachers. For instance, it can automate tasks such as lesson preparation and grading, allowing teachers to focus on educational activities. In this way, the system according to this embodiment can fully support teachers' administrative tasks and improve the time and quality of education.

[0077] The test creation department is responsible for creating tests. For example, the department can generate tests based on past questions or textbook content. Using generative AI, the department analyzes past questions and textbook content to generate new test questions. For instance, it can analyze trends in past questions and create new questions in a similar format. It can also generate questions related to specific units based on textbook content. Furthermore, the department can use generative AI to adjust the difficulty level of questions, creating tests tailored to students' understanding. For example, it can generate tests with a balanced mix of questions of varying difficulty levels based on students' past performance data. Specifically, the generative AI uses natural language processing to analyze textbooks and past questions, extracting important keywords and concepts. This allows for the automatic generation of questions related to specific units. Additionally, the generative AI analyzes past test results and student performance data to adjust the format and difficulty level of questions, creating questions tailored to each student's understanding. For example, it can provide more difficult questions to students with high understanding and basic questions to students with lower understanding. Furthermore, the department can use generative AI to increase the variety of questions. For example, presenting the same concept in different formats can deepen students' understanding. This allows the test development team to create tests efficiently and effectively and accurately assess students' learning outcomes.

[0078] The scoring department scores the tests created by the creation department. The scoring department can automatically score multiple-choice and written response questions, for example. The scoring department uses generative AI to calculate the correct answer rate for multiple-choice questions and analyze the content of written response questions for scoring. For example, the scoring department can assign points to multiple-choice questions based on the correct answer rate. The scoring department can also score written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, the scoring department can use generative AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, the scoring department can assign partial credit to written response questions based on the accuracy of the content. Specifically, the generative AI uses natural language processing technology to analyze written response answers and evaluate keyword matching and contextual consistency. This allows for higher scores to be given to answers with accurate content and logical structure. In addition, since the generative AI automatically distributes partial credit, consistency and fairness in scoring can be maintained. For example, even if only part of an answer is correct, the student's effort can be evaluated by awarding appropriate partial credit. Furthermore, the grading department can use generative AI to quickly provide feedback on the grading results. This allows students to identify their weaknesses early and use that information to improve their future learning. As a result, the grading department can grade tests efficiently and accurately, and appropriately evaluate students' learning outcomes.

[0079] The analytics department analyzes student data. For example, it can analyze students' past grades and learning history. Using generative AI, the analytics department analyzes students' grade data and learning history to identify learning trends and weaknesses. For example, based on students' past test results, the analytics department can identify areas where students have low understanding. It can also grasp learning progress based on learning history. Furthermore, using generative AI, the analytics department can analyze students' learning styles and interests to address individual learning needs. For example, based on students' learning history, the analytics department can identify learning styles such as visual, auditory, and experiential learning. Specifically, the generative AI analyzes students' past test results and learning history to understand each student's learning patterns and level of understanding in detail. This allows it to identify areas of low understanding in specific subjects or units and provide data to address individual learning needs. In addition, to analyze students' learning styles and interests, the generative AI analyzes learning history and behavioral data to identify learning styles such as visual, auditory, and experiential learning. This allows it to propose the most suitable learning method for each student. Furthermore, the analytics department can use generative AI to monitor learning progress in real time and provide timely feedback. This allows students to always know their learning status and create effective learning plans. This enables the analytics department to analyze students' learning data in detail and provide information to address individual learning needs.

[0080] The generation unit generates learning materials based on data obtained by the analysis unit. For example, the generation unit can generate effective learning materials based on the analysis results. The generation unit uses generation AI to generate learning materials that meet the learning needs of students. For example, the generation unit can generate materials specifically for areas where students have a low level of understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate materials that are tailored to the student's learning progress. For example, based on the student's learning progress, the generation unit can generate materials to help them move on to the next step. Specifically, the generation AI automatically generates learning materials tailored to each student's level of understanding and learning style based on data provided by the analysis unit. This allows students to use learning materials that are best suited to their learning needs. For example, for areas where students have a low level of understanding, it generates materials that include detailed explanations and additional practice problems to support students in deepening their understanding. Also, for questions that students frequently get wrong, it can analyze the cause of the errors and generate supplementary materials to resolve misunderstandings. Furthermore, the generation unit generates materials to help students move on to the next step according to their learning progress. This allows students to learn at their own pace and achieve effective learning outcomes. This allows the generation unit to produce effective learning materials that meet students' learning needs, thereby improving the quality of learning.

[0081] The customization unit adapts the materials generated by the generation unit to individual learning needs. For example, the customization unit can create individualized learning plans based on students' comprehension levels and interests. The customization unit uses generational AI to create learning plans tailored to students' learning styles and interests. For example, the customization unit can provide video-based materials to visually-oriented students. It can also provide audio-based materials to auditory-oriented students. Furthermore, the customization unit can provide interactive materials to experiential-oriented students. Specifically, the generational AI analyzes students' learning history and interests and automatically creates the optimal learning plan for each student. This allows students to use materials that match their learning style and interests. For example, visually-oriented students can be provided with materials that heavily utilize videos and diagrams, deepening their understanding through visual information. Auditory-oriented students can be provided with audio commentary and podcast-style materials, allowing them to learn through auditory information. Furthermore, experiential-oriented students can be provided with materials that include simulations and interactive exercises, deepening their learning through actual experience. This allows the customization department to provide individualized learning plans tailored to each student's learning style and interests, thereby supporting effective learning.

[0082] The support department assists teachers based on information provided by the customization department. For example, the support department can assist teachers based on individual learning plans. The support department uses generative AI to provide appropriate support to teachers. For example, the support department can provide teachers with advice on teaching methods according to the students' learning progress. The support department can also suggest supplementary materials to teachers according to the students' level of understanding. Furthermore, the support department can use generative AI to help reduce the burden on teachers. For example, the support department can automate lesson preparation and grading so that teachers can concentrate on teaching activities. Specifically, the generative AI analyzes students' learning data and suggests appropriate teaching methods and materials to teachers based on each student's level of understanding and progress. This allows teachers to provide instruction tailored to the needs of each student. In addition, the generative AI reduces the burden on teachers by automating lesson preparation and grading, providing an environment where teachers can concentrate on teaching activities. For example, in lesson preparation, the generative AI assists in creating materials and planning lessons, providing support for teachers to conduct effective lessons. Furthermore, in the grading process, the generating AI will automatically perform the grading, allowing teachers to provide feedback quickly. This will enable the support department to reduce the burden on teachers and provide support to improve the quality of education.

[0083] The test creation unit can generate tests based on past questions and textbook content. For example, it can analyze the trends in past questions and create new questions in a similar format. The unit uses a generation AI to analyze the trends in past questions and generate new questions. For example, it can create new questions in a similar format based on the trends in past questions. Furthermore, the unit can generate questions related to specific units based on textbook content. The unit uses a generation AI to analyze textbook content and generate questions related to specific units. For example, it can generate questions related to specific units based on textbook content. This allows for improved test quality by generating tests based on past questions and textbook content.

[0084] The scoring unit can automatically score multiple-choice and written response questions. For example, the scoring unit can assign points to multiple-choice questions based on the percentage of correct answers. The scoring unit uses a generative AI to calculate the percentage of correct answers to multiple-choice questions and assign points. For example, the scoring unit can assign points to multiple-choice questions based on the percentage of correct answers. The scoring unit can also score written response questions based on the accuracy of the content and the expressiveness of the writing. The scoring unit uses a generative AI to analyze the content of written response questions and assigns points based on the accuracy of the content and the expressiveness of the writing. For example, the scoring unit can assign points to written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, the scoring unit can improve the accuracy of scoring by appropriately allocating partial credit. The scoring unit uses a generative AI to assign partial credit to written response questions based on the accuracy of the content. For example, the scoring unit can assign partial credit to written response questions based on the accuracy of the content. This allows for improved grading efficiency by automatically scoring multiple-choice and written response questions.

[0085] The analytics department can analyze students' past performance and learning history. For example, the analytics department can identify areas where students have a low level of understanding based on their past test results. The analytics department uses generative AI to analyze students' past test results and identify areas where students have a low level of understanding. For example, the analytics department can identify areas where students have a low level of understanding based on their past test results. The analytics department can also grasp the progress of learning based on their learning history. The analytics department uses generative AI to analyze students' learning history and grasp the progress of learning. For example, the analytics department can grasp the progress of learning based on their learning history. Furthermore, the analytics department can analyze students' learning styles and interests and respond to their individual learning needs. The analytics department uses generative AI to analyze students' learning styles and interests and respond to their individual learning needs. For example, the analytics department can identify learning styles such as visual, auditory, and experiential based on students' learning history. This allows the analytics department to understand students' learning status by analyzing their past performance and learning history.

[0086] The generation unit can generate effective learning materials based on the analysis results. For example, the generation unit can generate learning materials specifically tailored to areas where students have a low level of understanding. The generation unit uses a generation AI to generate learning materials specifically tailored to areas where students have a low level of understanding, based on the analysis results. For example, the generation unit can generate learning materials specifically tailored to areas where students have a low level of understanding. The generation unit can also generate supplementary materials for questions that students frequently get wrong. The generation unit uses a generation AI to generate supplementary materials for questions that students frequently get wrong, based on the analysis results. For example, the generation unit can generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate learning materials tailored to the student's learning progress. The generation unit uses a generation AI to generate learning materials tailored to the student's learning progress, based on the analysis results. For example, the generation unit can generate materials to help students move on to the next step based on their learning progress. In this way, by generating effective learning materials based on the analysis results, the effectiveness of students' learning can be improved.

[0087] The customization department can create individualized learning plans based on students' understanding and interests. For example, it can provide video-based learning materials to visually-oriented students. The customization department uses generative AI to create learning plans tailored to students' learning styles and interests. For example, it can provide video-based learning materials to visually-oriented students. It can also provide audio-based learning materials to auditory-oriented students. Furthermore, it can provide interactive learning materials to experiential-oriented students. This allows for the creation of individualized learning plans based on students' understanding and interests, thereby addressing their individual learning needs.

[0088] The support department can assist teachers based on individual learning plans. For example, the support department can provide advice on teaching methods to teachers based on the students' learning progress. The support department can use generative AI to provide advice on teaching methods to teachers based on the students' learning progress. For example, the support department can provide advice on teaching methods to teachers based on the students' learning progress. The support department can also suggest the provision of supplementary materials to teachers based on the students' level of understanding. The support department can use generative AI to suggest the provision of supplementary materials to teachers based on the students' level of understanding. For example, the support department can suggest the provision of supplementary materials to teachers based on the students' level of understanding. Furthermore, the support department can use generative AI to provide support to reduce the burden on teachers. The support department can use generative AI to automate lesson preparation and grading, allowing teachers to concentrate on educational activities. For example, the support department can automate lesson preparation and grading, allowing teachers to concentrate on educational activities. This reduces the burden on teachers by supporting them based on individual learning plans.

[0089] The creation unit can estimate the teacher's emotions and adjust the test difficulty based on the estimated emotions. For example, if the teacher is stressed, the creation unit can use the generative AI to create a test with many easy questions. The creation unit uses the generative AI to estimate the teacher's emotions and adjust the test difficulty based on the estimated emotions. For example, if the teacher is stressed, the creation unit can use the generative AI to create a test with many easy questions. The creation unit can also use the generative AI to create a test with many difficult questions if the teacher is relaxed. The creation unit uses the generative AI to create a test with many difficult questions if the teacher is relaxed. For example, if the teacher is relaxed, the creation unit can use the generative AI to create a test with many difficult questions. Furthermore, if the teacher is tired, the creation unit can use the generative AI to create a test with a good balance of questions of moderate difficulty. The creation unit uses the generative AI to create a test with a good balance of questions of moderate difficulty if the teacher is tired. For example, if the teacher is tired, the creation unit can use the generative AI to create a test with a good balance of questions of moderate difficulty. This allows for a reduction in the burden on teachers by adjusting the difficulty of tests based on their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The creation unit can analyze past test results and generate questions tailored to students' understanding levels. For example, the creation unit can generate tests that include many questions in areas where students have a low level of understanding, based on students' past test results. The creation unit uses generation AI to analyze past test results and generate questions tailored to students' understanding levels. For example, the creation unit can generate tests that include many questions in areas where students have a low level of understanding, based on students' past test results. The creation unit can also generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. The creation unit uses generation AI to generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. For example, the creation unit can generate tests that include fewer questions in areas where students have a high level of understanding, based on students' past test results. Furthermore, the creation unit can generate tests that include questions that consider the balance of understanding levels, based on students' past test results. The creation unit uses generation AI to generate tests that include questions that consider the balance of understanding levels, based on students' past test results. For example, the creation unit can generate tests that include questions that consider the balance of understanding levels, based on students' past test results. This allows for the generation of questions tailored to each student's level of understanding, thereby improving the effectiveness of their learning.

[0091] The test creation unit can generate tests based not only on textbook content but also on the latest research findings and news articles. For example, the unit can generate questions that incorporate the latest research findings in addition to textbook content. The test creation unit uses generative AI to generate tests based not only on textbook content but also on the latest research findings and news articles. For example, the unit can generate questions that incorporate the latest research findings in addition to textbook content. Furthermore, the unit can generate questions that incorporate the latest news articles in addition to textbook content. The test creation unit uses generative AI to generate questions that incorporate the latest news articles in addition to textbook content. For example, the unit can generate questions that incorporate the latest news articles in addition to textbook content. In addition, the unit can generate questions that incorporate the latest technological trends in addition to textbook content. The test creation unit uses generative AI to generate questions that incorporate the latest technological trends in addition to textbook content. For example, the unit can generate questions that incorporate the latest technological trends in addition to textbook content. This allows for improved test quality by generating tests based not only on textbook content but also on the latest research findings and news articles.

[0092] The creation unit can estimate the teacher's emotions and adjust the order of questions in the test based on the estimated emotions. For example, if the teacher is stressed, the creation unit can create a test in which the generating AI presents easy questions first. The creation unit uses the generating AI to estimate the teacher's emotions and adjust the order of questions in the test based on the estimated emotions. For example, if the teacher is stressed, the creation unit can create a test in which the generating AI presents easy questions first. The creation unit can also create a test in which the generating AI presents difficult questions first if the teacher is relaxed. The creation unit uses the generating AI to create a test in which difficult questions first if the teacher is relaxed. For example, if the teacher is relaxed, the creation unit can create a test in which difficult questions first. Furthermore, if the teacher is tired, the creation unit can create a test in which the generating AI presents a balanced mix of medium-difficulty questions. The creation unit uses the generating AI to create a test in which medium-difficulty questions are presented a balanced mix of medium-difficulty questions if the teacher is tired. For example, if a teacher is fatigued, the creation unit can generate a test in which the generative AI presents a balanced mix of moderately difficult questions. This reduces the teacher's burden by adjusting the order of questions based on the teacher's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI is not limited to, but could be a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] The creation unit can generate tests in different formats depending on the student's learning style. For example, if the student prefers multiple-choice questions, the generation AI will create a test that contains many multiple-choice questions. The creation unit uses generation AI to generate tests in different formats depending on the student's learning style. For example, if the student prefers multiple-choice questions, the generation AI can create a test that contains many multiple-choice questions. The creation unit can also use generation AI to create a test that contains many written-response questions if the student prefers written-response questions. The creation unit uses generation AI to create a test that contains many written-response questions if the student prefers written-response questions. For example, if the student prefers written-response questions, the generation AI can create a test that contains many written-response questions. Furthermore, if the student prefers practical skills problems, the generation AI can create a test that contains many practical skills problems. The creation unit uses generation AI to create a test that contains many practical skills problems if the student prefers practical skills problems. For example, if the creation department knows that students prefer practical skills-based questions, the generation AI can create a test that includes many practical skills-based questions. This allows for the creation of tests tailored to students' learning styles, thereby improving their learning effectiveness.

[0094] The creation unit can generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the creation unit's generative AI will create a test that includes many science-related questions. The creation unit uses generative AI to generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the creation unit's generative AI can create a test that includes many science-related questions. The creation unit can also use generative AI to create tests that include many history-related questions if a student is interested in history. The creation unit uses generative AI to create tests that include many history-related questions if a student is interested in history. For example, if a student is interested in history, the creation unit's generative AI can create a test that includes many history-related questions. Furthermore, if a student is interested in literature, the creation unit's generative AI can create a test that includes many literature-related questions. The creation unit uses generative AI to create tests that include many literature-related questions if a student is interested in literature. For example, if a student is interested in literature, the creation unit's generative AI can create a test that includes many literature-related questions. This allows for the generation of tests based on students' areas of interest, thereby improving their motivation to learn.

[0095] The grading system can estimate a student's emotions and adjust the content of the feedback based on those emotions. For example, if a student is stressed, the grading system can use the generative AI to provide positive feedback. The grading system uses the generative AI to estimate a student's emotions and adjust the content of the feedback based on those emotions. For example, if a student is stressed, the grading system can use the generative AI to provide positive feedback. The grading system can also use the generative AI to provide detailed feedback if a student is relaxed. The grading system uses the generative AI to provide detailed feedback if a student is relaxed. For example, if a student is relaxed, the grading system can use the generative AI to provide detailed feedback. Furthermore, if a student is tired, the grading system can use the generative AI to provide concise feedback. The grading system uses the generative AI to provide concise feedback if a student is tired. For example, if a student is tired, the grading system can use the generative AI to provide concise feedback. By adjusting the content of the feedback based on the student's emotions, it is possible to improve the student's motivation to learn. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The scoring unit can improve the accuracy of scoring by referring to past answer patterns during scoring. For example, the scoring unit can score similar answers with high accuracy based on the student's past answer patterns. The scoring unit uses generative AI to improve the accuracy of scoring by referring to past answer patterns during scoring. For example, the scoring unit can score similar answers with high accuracy based on the student's past answer patterns. The scoring unit can also analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. The scoring unit uses generative AI to analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. For example, the scoring unit can analyze the tendency of incorrect answers based on the student's past answer patterns and score accordingly. Furthermore, the scoring unit can appropriately allocate partial points based on the student's past answer patterns and score accordingly. The scoring unit uses generative AI to appropriately allocate partial points based on the student's past answer patterns and score accordingly. For example, the scoring unit can appropriately allocate partial points based on the student's past answer patterns and score accordingly. This allows for improved scoring accuracy by referencing past answer patterns.

[0097] The scoring unit can score essay questions using multiple evaluation criteria. For example, the scoring unit can score essay questions using accuracy of content and expressiveness as evaluation criteria. The scoring unit uses generative AI to score essay questions using multiple evaluation criteria. For example, the scoring unit can score essay questions using accuracy of content and expressiveness as evaluation criteria. The scoring unit can also score essay questions using logical structure and persuasiveness as evaluation criteria. The scoring unit uses generative AI to score essay questions using logical structure and persuasiveness as evaluation criteria. For example, the scoring unit can score essay questions using logical structure and persuasiveness as evaluation criteria. Furthermore, the scoring unit can score essay questions using creativity and originality as evaluation criteria. The scoring unit uses generative AI to score essay questions using creativity and originality as evaluation criteria. For example, the scoring unit can score essay questions using creativity and originality as evaluation criteria. This allows for improved accuracy in grading essay-type questions by using multiple evaluation criteria.

[0098] The grading system can estimate students' emotions and adjust the timing of feedback based on those emotions. For example, if a student is stressed, the grading system can use generative AI to provide quick feedback. The grading system uses generative AI to estimate students' emotions and adjust the timing of feedback based on those emotions. For example, if a student is stressed, the grading system can use generative AI to provide quick feedback. The grading system can also use generative AI to provide detailed feedback if a student is relaxed. The grading system uses generative AI to provide detailed feedback if a student is relaxed. For example, if a student is relaxed, the grading system can use generative AI to provide detailed feedback. Furthermore, if a student is tired, the grading system can use generative AI to provide concise feedback. The grading system uses generative AI to provide concise feedback if a student is tired. For example, if a student is tired, the grading system can use generative AI to provide concise feedback. By adjusting the timing of feedback based on students' emotions, it is possible to improve students' motivation to learn. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The grading system can provide individualized feedback based on students' learning history during grading. For example, the grading system can provide feedback on areas where students have a low level of understanding, based on their learning history. The grading system can use generative AI to provide individualized feedback based on students' learning history during grading. For example, the grading system can provide feedback on areas where students have a low level of understanding, based on their learning history. The grading system can also provide feedback on areas where students have a high level of understanding, based on their learning history. The grading system can use generative AI to provide feedback on areas where students have a high level of understanding, based on their learning history. For example, the grading system can provide feedback on areas where students have a high level of understanding, based on their learning history. Furthermore, the grading system can provide feedback tailored to the student's learning progress, based on their learning history. The grading system can use generative AI to provide feedback tailored to the student's learning progress, based on their learning history. For example, the grading system can provide feedback tailored to the student's learning progress, based on their learning history. By providing individualized feedback based on students' learning history, the effectiveness of students' learning can be improved.

[0100] The scoring department can adjust the scope of the next test based on the scoring results. For example, the scoring department can include areas where students have a low level of understanding in the scope of the next test. The scoring department uses generative AI to adjust the scope of the next test based on the scoring results. For example, the scoring department can include areas where students have a low level of understanding in the scope of the next test. The scoring department can also exclude areas where students have a high level of understanding from the scope of the next test. The scoring department uses generative AI to exclude areas where students have a high level of understanding from the scope of the next test based on the scoring results. For example, the scoring department can exclude areas where students have a high level of understanding from the scope of the next test. Furthermore, the scoring department can set a scope of questions that takes into account the balance of understanding. The scoring department uses generative AI to set a scope of questions that takes into account the balance of understanding based on the scoring results. For example, the scoring department can set a scope of questions that takes into account the balance of understanding. This allows for adjustments to the scope of the next test based on the scoring results, thereby improving students' learning effectiveness.

[0101] The analysis department can estimate students' emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if a student is stressed, the analysis department can use a generating AI to provide a simple and easy-to-understand display method. The analysis department uses a generating AI to estimate students' emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if a student is stressed, the analysis department can use a generating AI to provide a simple and easy-to-understand display method. The analysis department can also use a generating AI to provide a display method that includes detailed information if a student is relaxed. The analysis department uses a generating AI to provide a display method that includes detailed information if a student is relaxed. For example, if a student is relaxed, the analysis department can use a generating AI to provide a display method that includes detailed information. Furthermore, if a student is tired, the analysis department can use a generating AI to provide a concise display method. The analysis department uses a generating AI to provide a concise display method if a student is tired. For example, if a student is tired, the analysis department can use a generating AI to provide a concise display method. This allows for adjusting how analysis results are displayed based on students' emotions, thereby aiding student comprehension. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The analysis department can include not only students' learning history but also their lifestyle and health status in its analysis. For example, the analysis department can analyze learning efficiency based on students' lifestyle. The analysis department uses generative AI to include not only students' learning history but also their lifestyle and health status in its analysis. For example, the analysis department can analyze learning efficiency based on students' lifestyle. Furthermore, the analysis department can analyze learning progress based on students' health status. The analysis department uses generative AI to analyze learning progress based on students' health status. For example, the analysis department can analyze learning progress based on students' health status. In addition, the analysis department can analyze the effectiveness of learning based on students' lifestyle and health status. The analysis department uses generative AI to analyze the effectiveness of learning based on students' lifestyle and health status. For example, the analysis department can analyze the effectiveness of learning based on students' lifestyle and health status. This allows for a more comprehensive learning analysis by considering lifestyle and health status.

[0103] The analysis department can provide individualized learning advice based on the analysis results. For example, the analysis department can provide learning advice for areas where understanding is low. The analysis department can provide individualized learning advice based on the analysis results using generative AI. For example, the analysis department can provide learning advice for areas where understanding is low. The analysis department can also provide learning advice for areas where understanding is high. The analysis department can provide learning advice for areas where understanding is high using generative AI. For example, the analysis department can provide learning advice for areas where understanding is high. Furthermore, the analysis department can provide learning advice tailored to the student's learning progress. The analysis department can provide learning advice tailored to the student's learning progress using generative AI. For example, the analysis department can provide learning advice tailored to the student's learning progress. By providing individualized learning advice, the effectiveness of students' learning can be improved.

[0104] The analysis department can estimate students' emotions and prioritize analysis results based on those estimated emotions. For example, if a student is stressed, the analysis department's generating AI will prioritize displaying important information. The analysis department uses generating AI to estimate students' emotions and prioritize analysis results based on those estimated emotions. For example, if a student is stressed, the analysis department's generating AI can prioritize displaying important information. The analysis department can also prioritize displaying detailed information if a student is relaxed. The analysis department uses generating AI to prioritize displaying detailed information if a student is relaxed. For example, if a student is relaxed, the analysis department's generating AI can prioritize displaying detailed information. Furthermore, if a student is tired, the analysis department's generating AI can prioritize displaying concise information. The analysis department uses generating AI to prioritize displaying concise information if a student is tired. For example, if a student is tired, the analysis department's generating AI can prioritize displaying concise information. By prioritizing analysis results based on students' emotions, the analysis department can prioritize providing important information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The analysis department can perform analyses while considering the student's learning environment. For example, if a student is studying at home, the generative AI can analyze the efficiency of their home learning. The analysis department uses generative AI to perform analyses while considering the student's learning environment. For example, if a student is studying at home, the generative AI can analyze the efficiency of their home learning. The analysis department can also use generative AI to analyze the efficiency of students studying at school. For example, if a student is studying at school, the generative AI can analyze the efficiency of their school learning. Furthermore, if a student is studying in the library, the generative AI can analyze the efficiency of their library learning. The analysis department uses generative AI to analyze the efficiency of students studying in the library. For example, if a student is studying in the library, the generative AI can analyze the efficiency of their library learning. This allows for more accurate learning analysis by considering the learning environment.

[0106] The analysis department can propose the formation of learning groups based on the analysis results. For example, the analysis department can group students with low levels of understanding together. The analysis department can also propose the formation of learning groups based on the analysis results using generative AI. For example, the analysis department can group students with low levels of understanding together. The analysis department can also group students with high levels of understanding together. The analysis department can use generative AI to form groups of students with high levels of understanding together based on the analysis results. For example, the analysis department can form groups of students with high levels of understanding together. Furthermore, the analysis department can form groups that take into account a balance of understanding levels. The analysis department uses generative AI to form groups that take into account a balance of understanding levels based on the analysis results. For example, the analysis department can form groups that take into account a balance of understanding levels. In this way, by proposing the formation of learning groups, collaborative learning among students can be promoted.

[0107] The generation unit can estimate students' emotions and adjust the difficulty level of the learning materials based on those emotions. For example, if a student is stressed, the generation unit can provide easy learning materials using the generation AI. The generation unit uses the generation AI to estimate students' emotions and adjust the difficulty level of the learning materials based on those emotions. For example, if a student is stressed, the generation unit can provide easy learning materials using the generation AI. The generation unit can also provide more difficult learning materials if a student is relaxed. The generation unit uses the generation AI to provide more difficult learning materials if a student is relaxed. For example, if a student is relaxed, the generation unit can provide more difficult learning materials using the generation AI. Furthermore, if a student is tired, the generation unit can provide learning materials of moderate difficulty using the generation AI. The generation unit uses the generation AI to provide learning materials of moderate difficulty if a student is tired. For example, if a student is tired, the generation unit can provide learning materials of moderate difficulty using the generation AI. This allows for improved learning effectiveness by adjusting the difficulty level of the learning materials based on students' emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The generation unit can generate learning materials to reinforce students' weaknesses based on the analysis results. For example, the generation unit can generate materials specifically tailored to areas where students have a low level of understanding. The generation unit uses a generation AI to generate learning materials to reinforce students' weaknesses based on the analysis results. For example, the generation unit can generate materials specifically tailored to areas where students have a low level of understanding. The generation unit can also generate supplementary materials for questions that students frequently get wrong. The generation unit uses a generation AI to generate supplementary materials for questions that students frequently get wrong based on the analysis results. For example, the generation unit can generate supplementary materials for questions that students frequently get wrong. Furthermore, the generation unit can generate supplementary materials tailored to the student's learning progress. The generation unit uses a generation AI to generate supplementary materials tailored to the student's learning progress based on the analysis results. For example, the generation unit can generate supplementary materials tailored to the student's learning progress. By generating learning materials to reinforce students' weaknesses, the learning effect can be improved.

[0109] The generation unit can incorporate the latest research findings and case studies into the content of educational materials. For example, the generation unit can generate scientific educational materials based on the latest research findings. The generation unit uses generational AI to incorporate the latest research findings and case studies into the content of educational materials. For example, the generation unit can generate scientific educational materials based on the latest research findings. The generation unit can also generate practical educational materials based on the latest case studies. The generation unit uses generational AI to generate practical educational materials based on the latest case studies. For example, the generation unit can generate practical educational materials based on the latest case studies. Furthermore, the generation unit can generate technical educational materials based on the latest technological trends. The generation unit uses generational AI to generate technical educational materials based on the latest technological trends. For example, the generation unit can generate technical educational materials based on the latest technological trends. This allows for an improvement in the quality of educational materials by incorporating the latest research findings and case studies.

[0110] The generation unit can estimate students' emotions and adjust the format of the learning materials based on those emotions. For example, if a student is feeling stressed, the generation unit can provide text-based learning materials using the generation AI. The generation unit uses the generation AI to estimate students' emotions and adjust the format of the learning materials based on those emotions. For example, if a student is feeling stressed, the generation unit can provide text-based learning materials using the generation AI. The generation unit can also provide video-based learning materials if a student is relaxed. The generation unit uses the generation AI to provide video-based learning materials if a student is relaxed. For example, if a student is relaxed, the generation unit can provide video-based learning materials using the generation AI. Furthermore, if a student is tired, the generation unit can provide interactive-based learning materials using the generation AI. The generation unit uses the generation AI to provide interactive-based learning materials if a student is tired. For example, if a student is tired, the generation unit can provide interactive-based learning materials using the generation AI. By adjusting the format of the learning materials based on students' emotions, learning effectiveness can be improved. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The generation unit can generate different formats of learning materials depending on the student's learning style. For example, if a student prefers visual learning, the generation AI can provide video-format learning materials. The generation unit uses the generation AI to generate different formats of learning materials depending on the student's learning style. For example, if a student prefers visual learning, the generation AI can provide video-format learning materials. The generation unit can also use the generation AI to provide audio-format learning materials if a student prefers auditory learning. The generation unit uses the generation AI to provide audio-format learning materials if a student prefers auditory learning. For example, if a student prefers auditory learning, the generation AI can provide audio-format learning materials. Furthermore, if a student prefers experiential learning, the generation unit can provide interactive-format learning materials. The generation unit uses the generation AI to provide interactive-format learning materials if a student prefers experiential learning. For example, if a student prefers experiential learning, the generation AI can provide interactive-format learning materials. By generating learning materials tailored to the student's learning style, learning effectiveness can be improved.

[0112] The generation unit can generate educational materials that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can provide science-related educational materials. The generation unit uses the generation AI to generate educational materials that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can provide science-related educational materials. The generation unit can also use the generation AI to provide history-related educational materials if a student is interested in history. For example, if a student is interested in history, the generation AI can provide history-related educational materials. Furthermore, if a student is interested in literature, the generation AI can provide literature-related educational materials. The generation unit uses the generation AI to provide literature-related educational materials if a student is interested in literature. For example, if a student is interested in literature, the generation AI can provide literature-related educational materials. This allows for increased motivation to learn by generating educational materials based on students' areas of interest.

[0113] The customization function can estimate a student's emotions and adjust the content of the learning plan based on those emotions. For example, if a student is feeling stressed, the customization function's generating AI can provide a simple learning plan. The customization function uses generating AI to estimate a student's emotions and adjust the content of the learning plan based on those emotions. For example, if a student is feeling stressed, the customization function's generating AI can provide a simple learning plan. The customization function can also use generating AI to provide a more challenging learning plan if a student is relaxed. The customization function uses generating AI to provide a more challenging learning plan if a student is relaxed. For example, if a student is relaxed, the customization function's generating AI can provide a more challenging learning plan. Furthermore, if a student is tired, the customization function's generating AI can provide a learning plan of moderate difficulty. The customization function uses generating AI to provide a learning plan of moderate difficulty if a student is tired. For example, if a student is tired, the customization function's generating AI can provide a learning plan of moderate difficulty. By adjusting the content of the learning plan based on the student's emotions, learning effectiveness can be improved. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The customization function can create optimal learning plans based on a student's past learning history. For example, the customization function can create learning plans specifically tailored to areas where the student has a low level of understanding. The customization function uses generative AI to create optimal learning plans based on a student's past learning history. For example, the customization function can create learning plans specifically tailored to areas where the student has a low level of understanding. The customization function can also create learning plans for questions that the student frequently gets wrong. The customization function uses generative AI to create learning plans for questions that the student frequently gets wrong, based on a student's past learning history. For example, the customization function can create learning plans for questions that the student frequently gets wrong. Furthermore, the customization function can create learning plans that are tailored to the student's learning progress. The customization function uses generative AI to create learning plans that are tailored to the student's learning progress, based on a student's past learning history. For example, the customization function can create learning plans that are tailored to the student's learning progress. By creating optimal learning plans based on a student's past learning history, the effectiveness of learning can be improved.

[0115] The customization function can take into account students' lifestyles and health conditions when creating learning plans. For example, the customization function can create learning plans that consider learning efficiency based on students' lifestyles. The customization function uses generative AI to take students' lifestyles and health conditions into account when creating learning plans. For example, the customization function can create learning plans that consider learning efficiency based on students' lifestyles. The customization function can also create learning plans that consider learning progress based on students' health conditions. The customization function uses generative AI to create learning plans that consider learning progress based on students' health conditions. For example, the customization function can create learning plans that consider learning progress based on students' health conditions. Furthermore, the customization function can create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. The customization function uses generative AI to create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. For example, the customization function can create learning plans that consider learning effectiveness based on students' lifestyles and health conditions. This allows for improved learning effectiveness by taking students' lifestyles and health conditions into consideration.

[0116] The customization function can estimate a student's emotions and prioritize learning plans based on those emotions. For example, if a student is stressed, the customization function's generative AI will prioritize providing important learning plans. The customization function uses generative AI to estimate a student's emotions and prioritize learning plans based on those emotions. For example, if a student is stressed, the customization function's generative AI can prioritize providing important learning plans. The customization function can also prioritize providing detailed learning plans if a student is relaxed. The customization function uses generative AI to prioritize providing detailed learning plans if a student is relaxed. For example, if a student is relaxed, the customization function's generative AI can prioritize providing detailed learning plans. Furthermore, if a student is tired, the customization function's generative AI can prioritize providing concise learning plans. The customization function uses generative AI to prioritize providing concise learning plans if a student is tired. For example, if a student is tired, the customization function's generative AI can prioritize providing concise learning plans. This allows for improved learning effectiveness by prioritizing learning plans based on students' emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The customization function can create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at home. The customization function uses generative AI to create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at home. Furthermore, if a student is studying at school, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at school. The customization function uses generative AI to create learning plans that take into account the efficiency of studying at school. For example, if a student is studying at school, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying at school. Furthermore, if a student is studying in the library, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying in the library. The customization function uses generative AI to create learning plans that take into account the efficiency of studying in the library. For example, if a student is studying in the library, the customization function's generative AI can create a learning plan that takes into account the efficiency of studying in the library. This allows us to improve learning effectiveness by taking into account the students' learning environment.

[0118] The customization function can reflect students' areas of interest in their learning plans. For example, if a student is interested in science, the customization function's generative AI can create a science-related learning plan. The customization function uses generative AI to reflect students' areas of interest in their learning plans. For example, if a student is interested in science, the customization function's generative AI can create a science-related learning plan. The customization function can also use generative AI to create a history-related learning plan if a student is interested in history. For example, if a student is interested in history, the customization function's generative AI can create a history-related learning plan. Furthermore, if a student is interested in literature, the customization function's generative AI can create a literature-related learning plan. The customization function uses generative AI to create a literature-related learning plan if a student is interested in literature. For example, if a student is interested in literature, the customization function's generative AI can create a literature-related learning plan. By reflecting students' areas of interest, this can improve their motivation to learn.

[0119] The support unit can estimate the teacher's emotions and adjust the support content based on the estimated emotions. For example, if the teacher is stressed, the support unit can use a generative AI to provide simple support. The support unit uses a generative AI to estimate the teacher's emotions and adjust the support content based on the estimated emotions. For example, if the teacher is stressed, the support unit can use a generative AI to provide simple support. The support unit can also use a generative AI to provide detailed support if the teacher is relaxed. The support unit uses a generative AI to provide detailed support if the teacher is relaxed. For example, if the teacher is relaxed, the support unit can use a generative AI to provide detailed support. Furthermore, if the teacher is tired, the support unit can use a generative AI to provide moderate support. The support unit uses a generative AI to provide moderate support if the teacher is tired. For example, if the teacher is tired, the support unit can use a generative AI to provide moderate support. This reduces the teacher's burden by adjusting the support content based on the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0120] The support department can provide optimal support methods based on the teacher's past teaching history. For example, the support department can provide support methods for areas where students have a low level of understanding. The support department uses generative AI to provide optimal support methods based on the teacher's past teaching history. For example, the support department can provide support methods for areas where students have a low level of understanding. The support department can also provide support methods for problems that students frequently get wrong. The support department uses generative AI to provide support methods for problems that students frequently get wrong, based on the teacher's past teaching history. For example, the support department can provide support methods for problems that students frequently get wrong. Furthermore, the support department can provide support methods tailored to the student's learning progress. The support department uses generative AI to provide support methods tailored to the student's learning progress, based on the teacher's past teaching history. For example, the support department can provide support methods tailored to the student's learning progress. This reduces the burden on teachers by providing optimal support methods based on their past teaching history.

[0121] The support department can incorporate the latest educational theories and case studies into its support services. For example, the support department can provide scientific support services based on the latest educational theories. The support department can use generative AI to incorporate the latest educational theories and case studies into its support services. For example, the support department can provide scientific support services based on the latest educational theories. The support department can also provide practical support services based on the latest case studies. The support department can use generative AI to provide practical support services based on the latest case studies. For example, the support department can provide practical support services based on the latest case studies. Furthermore, the support department can provide technical support services based on the latest technological trends. The support department can use generative AI to provide technical support services based on the latest technological trends. For example, the support department can provide technical support services based on the latest technological trends. By incorporating the latest educational theories and case studies, the quality of support services can be improved.

[0122] The support unit can estimate the teacher's emotions and adjust the timing of support based on the estimated emotions. For example, if the teacher is stressed, the support unit can use a generative AI to quickly provide support. The support unit uses a generative AI to estimate the teacher's emotions and adjust the timing of support based on the estimated emotions. For example, if the teacher is stressed, the support unit can use a generative AI to quickly provide support. The support unit can also use a generative AI to provide detailed support if the teacher is relaxed. The support unit uses a generative AI to provide detailed support if the teacher is relaxed. For example, if the teacher is relaxed, the support unit can use a generative AI to provide detailed support. Furthermore, if the teacher is tired, the support unit can use a generative AI to provide concise support. The support unit uses a generative AI to provide concise support if the teacher is tired. For example, if the teacher is tired, the support unit can use a generative AI to provide concise support. This reduces the teacher's burden by adjusting the timing of support based on the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0123] The support system can provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the support system can use its generative AI to provide visual support methods. The support system can use its generative AI to provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the support system can use its generative AI to provide visual support methods. The support system can also use its generative AI to provide auditory support methods if a teacher prefers auditory instruction. For example, if a teacher prefers auditory instruction, the support system can use its generative AI to provide auditory support methods. Furthermore, if a teacher prefers experiential instruction, the support system can use its generative AI to provide experiential support methods. The support system can use its generative AI to provide experiential support methods if a teacher prefers experiential instruction. For example, if a teacher prefers experiential instruction, the support system can use its generative AI to provide experiential support methods. By providing support methods tailored to the teacher's teaching style, the support system can reduce the burden on teachers.

[0124] The support department can reflect the teacher's areas of interest in the support content. For example, if a teacher is interested in science, the support department's generative AI can provide science-related support content. The support department uses generative AI to reflect the teacher's areas of interest in the support content. For example, if a teacher is interested in science, the support department's generative AI can provide science-related support content. Also, if a teacher is interested in history, the support department's generative AI can provide history-related support content. The support department uses generative AI to provide history-related support content if a teacher is interested in history. For example, if a teacher is interested in history, the support department's generative AI can provide history-related support content. Furthermore, if a teacher is interested in literature, the support department's generative AI can provide literature-related support content. In this way, the quality of support content can be improved by reflecting the teacher's areas of interest.

[0125] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0126] The test creation unit can generate tests tailored to students' learning progress based on their learning history. For example, if a student is struggling with a particular unit, the unit can create a test that includes many questions related to that unit. It can also create tests with more difficult questions in areas where students excel. Furthermore, the unit can adjust the frequency and content of tests according to the student's learning pace. This allows for improved learning effectiveness by providing tests that match the student's learning situation.

[0127] The grading system can estimate students' emotions and adjust the content of feedback based on those estimates. For example, if a student is stressed, the generating AI can provide positive feedback. If a student is relaxed, the generating AI can provide detailed feedback. Furthermore, if a student is tired, the generating AI can provide concise feedback. By adjusting the content of feedback based on students' emotions, it is possible to improve students' motivation to learn.

[0128] The analysis department can include not only students' learning history but also their lifestyle and health status in its analysis. For example, it can analyze learning efficiency based on students' lifestyle habits. It can also analyze learning progress based on students' health status. Furthermore, it can analyze the effectiveness of learning based on students' lifestyle habits and health status. This allows for a more comprehensive learning analysis by considering lifestyle habits and health status.

[0129] The generation unit can estimate the student's emotions and adjust the difficulty level of the learning materials based on those emotions. For example, if a student is stressed, the generation AI can provide easy learning materials. Conversely, if a student is relaxed, the generation AI can provide more difficult materials. Furthermore, if a student is tired, the generation AI can provide materials of moderate difficulty. By adjusting the difficulty level of the materials based on the student's emotions, learning effectiveness can be improved.

[0130] The customization function can create learning plans that take into account the student's learning environment. For example, if a student is studying at home, the generating AI can create a learning plan that considers the efficiency of home learning. Similarly, if a student is studying at school, the generating AI can create a learning plan that considers the efficiency of school learning. Furthermore, if a student is studying in the library, the generating AI can create a learning plan that considers the efficiency of library learning. By considering the student's learning environment, learning effectiveness can be improved.

[0131] The support system can estimate a teacher's emotions and adjust the support content based on those estimates. For example, if a teacher is stressed, the generating AI can provide simple support. If the teacher is relaxed, the generating AI can provide more detailed support. Furthermore, if the teacher is tired, the generating AI can provide moderate support. By adjusting the support content based on the teacher's emotions, the burden on teachers can be reduced.

[0132] The creation function can generate tests that include relevant topics based on students' areas of interest. For example, if a student is interested in science, the generation AI can create a test with many science-related questions. Similarly, if a student is interested in history, the generation AI can create a test with many history-related questions. Furthermore, if a student is interested in literature, the generation AI can create a test with many literature-related questions. This allows for the generation of tests based on students' areas of interest, thereby improving their motivation to learn.

[0133] The analysis unit can estimate students' emotions and adjust how the analysis results are displayed based on those estimates. For example, if a student is stressed, the generating AI can provide a simple and easy-to-understand display. If a student is relaxed, the generating AI can provide a display that includes more detailed information. Furthermore, if a student is tired, the generating AI can provide a concise display. By adjusting how the analysis results are displayed based on students' emotions, it is possible to help students understand the results better.

[0134] The customization feature allows for the creation of learning plans that take into account students' lifestyles and health conditions. For example, a learning plan can be created that considers learning efficiency based on the student's lifestyle. Similarly, a learning plan can be created that considers learning progress based on the student's health condition. Furthermore, a learning plan can be created that considers learning effectiveness based on the student's lifestyle and health condition. This allows for improved learning effectiveness by taking students' lifestyles and health conditions into account.

[0135] The support system can provide different support methods depending on the teacher's teaching style. For example, if a teacher prefers visual instruction, the generative AI can provide visual support methods. Similarly, if a teacher prefers auditory instruction, the generative AI can provide auditory support methods. Furthermore, if a teacher prefers experiential instruction, the generative AI can provide experiential support methods. This reduces the burden on teachers by providing support methods tailored to their teaching style.

[0136] The following briefly describes the processing flow for example form 2.

[0137] Step 1: The creation unit creates the test. The creation unit can generate tests based on past questions and textbook content. Using generation AI, it analyzes past questions and textbook content to generate new test questions. For example, the creation unit can analyze the trends in past questions and create new questions in a similar format. It can also generate questions related to specific units based on textbook content. Furthermore, using generation AI, it can adjust the difficulty level of the questions to create tests that match the students' level of understanding. For example, based on students' past performance data, it can generate tests that include a balanced mix of questions of varying difficulty levels. Step 2: The scoring unit scores the tests created by the creation unit. The scoring unit can automatically score multiple-choice and written response questions. Using a generation AI, it calculates the correct answer rate for multiple-choice questions and analyzes the content of written response questions for scoring. For example, it can assign points to multiple-choice questions based on the correct answer rate. It can also score written response questions based on the accuracy of the content and the expressiveness of the writing. Furthermore, it can use the generation AI to appropriately distribute partial credit and improve the accuracy of scoring. For example, it can assign partial credit to written response questions based on the accuracy of the content. Step 3: The analytics department analyzes student data. The analytics department can analyze students' past performance and learning history. Using generative AI, it analyzes students' performance data and learning history to identify learning trends and weaknesses. For example, it can identify areas where students have a low level of understanding based on their past test results. It can also grasp the progress of learning based on the learning history. Furthermore, it can use generative AI to analyze students' learning styles and interests and address their individual learning needs. For example, it can identify learning styles such as visual, auditory, and experiential based on students' learning history. Step 4: The generation unit generates learning materials based on the data obtained by the analysis unit. The generation unit can generate effective learning materials based on the analysis results. Using the generation AI, it generates learning materials that meet the learning needs of students. For example, it can generate materials that specialize in areas where students have a low level of understanding. It can also generate supplementary materials for questions that students frequently get wrong. Furthermore, it can generate learning materials that are tailored to the student's learning progress. For example, it can generate materials to help students move on to the next step based on their learning progress. Step 5: The customization unit adapts the materials generated by the generation unit to individual learning needs. The customization unit can create individualized learning plans based on students' understanding and interests. Using the generation AI, it creates learning plans tailored to students' learning styles and interests. For example, video materials can be provided for visually-oriented students. Audio materials can be provided for auditory-oriented students. Furthermore, interactive materials can be provided for experiential-oriented students. Step 6: The support department assists teachers based on the information provided by the customization department. The support department can assist teachers based on individual learning plans. It uses generative AI to provide appropriate support to teachers. For example, it can provide teachers with advice on teaching methods according to the students' learning progress. It can also suggest supplementary materials to teachers according to the students' level of understanding. Furthermore, it can use generative AI to help reduce the burden on teachers. For example, it can automate lesson preparation and grading so that teachers can concentrate on teaching activities.

[0138] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0139] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0140] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0141] Each of the multiple elements described above, including the creation unit, scoring unit, analysis unit, generation unit, customization unit, and support unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the creation unit is implemented by the control unit 46A of the smart device 14 and generates tests based on past questions and textbook content. The scoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically scores multiple-choice and written response questions. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes students' performance data and learning history. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates learning materials that meet students' learning needs. The customization unit is implemented by, for example, the control unit 46A of the smart device 14 and creates individual learning plans based on students' understanding and interests. The support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides appropriate support to teachers. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0142] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0143] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0150] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the creation unit, scoring unit, analysis unit, generation unit, customization unit, and support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the creation unit is implemented by the control unit 46A of the smart glasses 214 and generates tests based on past questions and textbook content. The scoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and automatically scores multiple-choice and written questions. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes student performance data and learning history. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates learning materials that meet the student's learning needs. The customization unit is implemented, for example, by the control unit 46A of the smart glasses 214 and creates individual learning plans based on the student's level of understanding and interests. The support unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and provides appropriate support to teachers. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0158] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0159] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0161] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0162] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0165] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the creation unit, scoring unit, analysis unit, generation unit, customization unit, and support unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the creation unit is implemented by the control unit 46A of the headset terminal 314 and generates tests based on past questions and textbook content. The scoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically scores multiple-choice and written response questions. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes student performance data and learning history. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates learning materials that meet the students' learning needs. The customization unit is implemented by, for example, the control unit 46A of the headset terminal 314 and creates individual learning plans based on the students' level of understanding and interests. The support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides appropriate support to teachers. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0174] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0175] As shown in Figure 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.

[0176] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0177] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0178] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0180] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0181] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0182] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0183] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0184] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0185] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0186] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0187] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0188] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0189] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0190] Each of the multiple elements described above, including the creation unit, scoring unit, analysis unit, generation unit, customization unit, and support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the creation unit is implemented by the control unit 46A of the robot 414 and generates tests based on past questions and textbook content. The scoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically scores multiple-choice and written questions. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes students' performance data and learning history. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates teaching materials that meet students' learning needs. The customization unit is implemented by, for example, the control unit 46A of the robot 414 and creates individual learning plans based on students' understanding and interests. The support unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides appropriate support to teachers. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0191] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0192] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0193] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0194] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0195] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0196] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0197] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0198] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0199] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0200] 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.

[0201] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0202] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0203] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0204] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0205] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0206] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0207] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0208] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0209] (Note 1) The creation section is responsible for creating the tests, A scoring unit that scores the tests created by the creation unit, The analysis department analyzes student data, A generation unit generates teaching materials based on the data obtained by the analysis unit, A customization unit that adapts the materials generated by the generation unit to individual learning needs, The system includes a support unit that assists teachers based on information provided by the customization unit. A system characterized by the following features. (Note 2) The aforementioned creation unit, Generate tests based on past exam questions and textbook content. The system described in Appendix 1, characterized by the features described herein. (Note 3) The scoring unit is, Automatically grades multiple-choice and written response questions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit is Analyze students' past grades and learning history. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate effective teaching materials based on analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned customization unit is We create individualized learning plans based on each student's level of understanding and interests. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned support unit, Support teachers based on individual learning plans. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned creation unit, The system estimates the teacher's emotions and adjusts the test difficulty based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned creation unit, By analyzing past test results, the system generates questions tailored to the students' level of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned creation unit, Tests are generated not only based on textbook content, but also on the latest research findings and news articles. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned creation unit, The system estimates the teacher's emotions and adjusts the order of test questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned creation unit, Generate different test formats depending on the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned creation unit, Based on students' areas of interest, generate tests that include relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 14) The scoring unit is, The system estimates the student's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The scoring unit is, During grading, we improve grading accuracy by referring to past answer patterns. The system described in Appendix 1, characterized by the features described herein. (Note 16) The scoring unit is, For essay-type questions, scoring is performed using multiple evaluation criteria. The system described in Appendix 1, characterized by the features described herein. (Note 17) The scoring unit is, The system estimates the student's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The scoring unit is, During grading, provide individualized feedback based on the student's learning history. The system described in Appendix 1, characterized by the features described herein. (Note 19) The scoring unit is, Based on the scoring results, we will adjust the scope of the next test. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit is The system estimates students' emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit is The analysis will include not only students' learning history, but also their lifestyle habits and health status. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit is Based on the analysis results, we provide personalized learning advice. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit is The system estimates students' emotions and prioritizes the analysis results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is The analysis will be conducted taking into account the students' learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is Based on the analysis results, we propose the formation of study groups. The system described in Appendix 1, characterized by the features described herein. (Note 26) The generating unit is The system estimates students' emotions and adjusts the difficulty level of the learning materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The generating unit is Based on the analysis results, we generate learning materials to reinforce students' weaknesses. The system described in Appendix 1, characterized by the features described herein. (Note 28) The generating unit is The curriculum will incorporate the latest research findings and case studies. The system described in Appendix 1, characterized by the features described herein. (Note 29) The generating unit is The system estimates students' emotions and adjusts the format of the teaching materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The generating unit is We generate different formats of learning materials according to students' learning styles. The system described in Appendix 1, characterized by the features described herein. (Note 31) The generating unit is Based on students' areas of interest, we generate learning materials that include relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned customization unit is The system estimates students' emotions and adjusts the learning plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned customization unit is We create an optimal learning plan based on the student's past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned customization unit is The learning plan takes into account the student's lifestyle and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned customization unit is The system estimates students' emotions and prioritizes learning plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned customization unit is Create a learning plan that takes into account the student's learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned customization unit is Reflect students' areas of interest in their learning plans. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned support unit, The system estimates the teacher's emotions and adjusts the support provided based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned support unit, Based on the teacher's past teaching history, we provide the most suitable support methods. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned support unit, The support provided will incorporate the latest educational theories and practical examples. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned support unit, The system estimates the teacher's emotions and adjusts the timing of support based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned support unit, Provide different support methods depending on the teacher's teaching style. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned support unit, The support provided should reflect the teacher's areas of interest. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0210] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The creation section is responsible for creating the tests, A scoring unit that scores the tests created by the creation unit, The analysis department analyzes student data, A generation unit generates teaching materials based on the data obtained by the analysis unit, A customization unit that adapts the materials generated by the generation unit to individual learning needs, The system includes a support unit that assists teachers based on information provided by the customization unit. A system characterized by the following features.

2. The aforementioned creation unit, Generate tests based on past exam questions and textbook content. The system according to feature 1.

3. The scoring unit is, Automatically grades multiple-choice and written response questions. The system according to feature 1.

4. The aforementioned analysis unit is Analyze students' past grades and learning history. The system according to feature 1.

5. The generating unit is Generate effective teaching materials based on analysis results. The system according to feature 1.

6. The aforementioned customization unit is We create individualized learning plans based on each student's level of understanding and interests. The system according to feature 1.

7. The aforementioned support unit, Support teachers based on individual learning plans. The system according to feature 1.

8. The aforementioned creation unit, The system estimates the teacher's emotions and adjusts the test difficulty based on those emotions. The system according to feature 1.

Images