System

Abstract

An object of a system according to an embodiment is to efficiently and effectively generate examination questions and correct a paper.SOLUTION: A system includes an examination question generation part and a paper correction part. The examination question generation section learns past examination questions and generates examination questions based on parameters set by a teacher. The essay correction department analyzes essays and reports created by students, detects syntax errors, missing information, jumps in logic, citation errors, and the like, and makes concrete improvement proposals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of lacking efficient and effective support for generating test questions and correcting essays.

[0005] The system according to the embodiment aims to generate test questions and correct essays efficiently and effectively. [Means for solving the problem]

[0006] The system according to the embodiment includes a test question generation unit and an essay correction unit. The test question generation unit studies past test questions and generates test questions based on parameters set by the teacher. The essay correction unit analyzes essays and reports written by students, detecting syntax errors, missing information, logical leaps, citation errors, and other issues, and makes specific suggestions for improvement. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently and effectively generate test questions and correct essays. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An education support system according to an embodiment of the present invention is a system that includes a generation AI that studies past exam questions and generates exam questions based on parameters set by the teacher, and a generation AI that analyzes essays and reports written by students, detecting syntax errors, missing information, logical leaps, citation errors, etc., and makes specific suggestions for improvement. As a result, the education support system can improve the efficiency of exam question generation and essay correction, providing significant benefits to both teachers and students.

[0029] An education support system according to an embodiment includes a test question generation unit and an essay correction unit. The test question generation unit studies past test questions and generates test questions based on parameters set by a teacher. For example, the test question generation unit studies past mathematics test questions and generates a balanced mix of different types of questions, such as multiple-choice and essay questions. The test question generation unit also generates test questions based on parameters set by a teacher, such as the type of test, difficulty level, and subject. For example, when generating mathematics test questions, the test question generation unit may set 50% multiple-choice questions and 50% essay questions, and set the difficulty level to intermediate. The essay correction unit analyzes essays and reports written by students, detects syntax errors, missing information, logical leaps, citation errors, and other errors, and makes specific suggestions for improvement. For example, the essay correction unit analyzes English essays submitted by students, detects grammatical errors and spelling mistakes, and proposes appropriate revisions. The essay correction unit also points out missing information and logical leaps and makes specific suggestions for improvement. For example, the essay correction unit provides advice on digging deeper into the essay topic and maintaining logical consistency. This allows the education support system according to the embodiment to improve the efficiency of generating exam questions and correcting essays, thereby providing great benefits to both teachers and students.

[0030] The test question generation unit adds a real-time difficulty adjustment function to the questions it generates, allowing it to dynamically change the difficulty of questions depending on the student's answering status. For example, the test question generation unit uses a generation AI to analyze the student's answering status in real time and dynamically adjust the difficulty of the questions. For example, if a student answers a series of questions easily, the difficulty of the next question will be increased. The test question generation unit also builds a system in which the generation AI adjusts the difficulty of questions in real time based on the student's answering time and accuracy rate. For example, if the answering time is short, the difficulty will be increased, and if the answering time is long, the difficulty will be decreased. The test question generation unit also uses a generation AI to collect student answer data and dynamically change the difficulty of questions using a difficulty adjustment algorithm. For example, if a student answers correctly consecutively, the difficulty of the next question will be increased. This allows the difficulty of questions to be dynamically adjusted depending on the student's answering status.

[0031] The test question generation unit introduces question formats that accommodate different learning styles, making it possible to provide questions that are optimal for each individual student. For example, the test question generation unit uses a generation AI to generate questions that make extensive use of diagrams and graphs for visual learners. For example, it provides math questions that use figures and graphs. The test question generation unit also adds a function to present questions via audio for auditory learners. For example, it generates English listening questions and presents the questions via audio. The test question generation unit also introduces interactive question formats for tactile learners. For example, it generates questions that can be answered by drag and drop using a tablet or smartphone. This makes it possible to provide questions that are optimal for each individual student.

[0032] The test question generation unit can add a function to generate not only test questions, but also questions for everyday study assignments and homework. For example, the test question generation unit adds a function for the generation AI to generate questions for everyday study assignments and homework, allowing students to study on a daily basis. For example, it generates mathematics questions as daily homework. The test question generation unit also adds a function to generate study assignments, allowing students to study independently at home. For example, it generates English vocabulary practice questions and reading comprehension questions. The test question generation unit also builds a system in which the generation AI generates study assignments and homework of an appropriate level of difficulty according to the student's learning progress. For example, the difficulty level can be gradually increased towards the end of the semester. This makes it possible to generate questions for everyday study assignments and homework.

[0033] The test question generation unit can meet international educational needs by including questions that correspond to the educational curricula of different cultures and regions. For example, the test question generation unit adds a function in which the generation AI generates questions that correspond to the educational curricula of different cultures and regions. For example, it generates mathematics questions based on the American educational curriculum. In addition, to meet international educational needs, the test question generation unit builds a system in which the generation AI generates questions in multiple languages. For example, it generates questions in English, French, Chinese, etc. In addition, the test question generation unit allows the generation AI to study the educational curricula of different regions and generate questions specific to those regions. For example, it generates history questions based on the Japanese educational curriculum. This makes it possible to meet international educational needs.

[0034] The essay correction department refers to students' past submissions when correcting essays and can provide feedback that corresponds to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and provide feedback that corresponds to their growth based on that data. For example, it points out areas for improvement based on past mistakes. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides feedback that shows growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal feedback to each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide feedback that corresponds to each student's growth.

[0035] The essay correction unit can provide multifaceted feedback based on different evaluation criteria when correcting an essay. For example, when the generative AI corrects an essay, the essay correction unit provides feedback based on different evaluation criteria, such as creativity, logic, and expressiveness. For example, it provides feedback to evaluate creative ideas. The essay correction unit also builds a system that provides feedback based on different evaluation criteria. For example, it provides separate feedback on logic and feedback on expressiveness. The essay correction unit also allows the generative AI to learn different evaluation criteria and provide multifaceted feedback. For example, it provides feedback on creativity and feedback on logic simultaneously. This makes it possible to provide multifaceted feedback.

[0036] The essay correction unit can provide feedback in different languages ​​when correcting essays, thereby realizing a multilingual educational environment. For example, the essay correction unit can add a function that enables the generation AI to provide feedback in different languages, thereby realizing a multilingual educational environment. For example, feedback can be provided in English, French, Chinese, etc. The essay correction unit can also build a system that provides multilingual feedback. For example, it can enable students to receive feedback in the language of their choice. The essay correction unit can also enable the generation AI to learn different languages ​​and provide multilingual feedback. For example, feedback can be provided in English for essays submitted in English. This can realize a multilingual educational environment.

[0037] The test question generation unit can refer to past test results when setting the type and difficulty of test questions, and introduce the most effective settings for improving students' grades. For example, the test question generation unit uses a generation AI to analyze past test results and set the type and difficulty of questions that are most effective for improving students' grades. For example, it determines the optimal level of difficulty based on past data. The test question generation unit also references students' past test results and builds a system that sets the type and difficulty of questions that are effective for improving grades. For example, it adjusts the balance of questions based on past grade data. The test question generation unit also uses a generation AI to learn past test results and introduce the most effective settings for improving students' grades. For example, it sets more question formats and difficulty levels that have earned high scores in past tests. This makes it possible to introduce the most effective settings for improving students' grades.

[0038] The test question generation unit can provide settings according to different learning goals when setting the type and difficulty of test questions. In the test question generation unit, for example, the generation AI sets the type and difficulty of questions according to different learning goals. For example, a good balance is set between basic questions for assessing comprehension and applied questions for assessing applied ability. The test question generation unit also builds a system that sets the type and difficulty of questions according to learning goals. For example, open-ended questions are set to assess creativity. In addition, the test question generation unit sets the type and difficulty of questions based on the learning goals. For example, questions that require detailed explanations to deepen understanding and practical questions to test applied ability are set. This makes it possible to provide settings according to different learning goals.

[0039] The test question generation unit can add a function to set not only the type and difficulty of test questions, but also the test format. For example, the test question generation unit adds a function that enables the generation AI to set the test format, allowing the selection of formats such as online tests and paper tests. For example, it generates interactive questions for online tests. The test question generation unit also adds a test format setting function, building a system that generates questions according to the format selected by the student. For example, it generates printable questions for paper tests. The test question generation unit also allows the generation AI to learn the test format and set the optimal format. For example, it generates time-limited questions for online tests and long-answer questions for paper tests. This makes it possible to set the test format.

[0040] The test question generation unit can provide settings that correspond to different educational systems when setting the type and difficulty of test questions. For example, the test question generation unit adds a function in which the generation AI sets the type and difficulty of questions that correspond to different educational systems. For example, it generates questions that correspond to the IB (International Baccalaureate) or AP (Advanced Placement). The test question generation unit also builds a system that sets the type and difficulty of questions that correspond to the educational system. For example, it generates questions that correspond to GCSE (Grade 12 Standard). The test question generation unit also allows the generation AI to learn about different educational systems and set the type and difficulty of questions that are specific to that system. For example, it generates questions based on the IB curriculum. This makes it possible to provide settings that correspond to different educational systems.

[0041] The essay correction department refers to students' past submissions when analyzing essay syntax and detecting errors, and can provide revision suggestions tailored to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and, based on that data, provide revision suggestions tailored to their growth. For example, it points out areas for improvement based on past errors. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides revision suggestions that show growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal revision suggestions for each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide revision suggestions tailored to each student's growth.

[0042] The essay correction unit can add functions to perform syntax analysis and error detection not only for essays but also for other text formats such as short sentences and poetry. For example, the essay correction unit adds functions to the generative AI to perform syntax analysis and error detection for other text formats such as short sentences and poetry, allowing students to learn from multiple angles. For example, it provides suggestions for correcting grammatical errors in short sentences. The essay correction unit also builds a system that performs syntax analysis and error detection for short sentences and poetry. For example, it analyzes the rhythm and rhyme of poetry and points out areas for improvement. The essay correction unit also trains the generative AI on data from short sentences and poems to perform syntax analysis and error detection. For example, it provides suggestions for correcting grammatical errors in short sentences and suggestions for improving the rhythm of poetry. This allows syntax analysis and error detection for other text formats such as short sentences and poetry.

[0043] The paper correction unit can provide analysis and error detection in different languages ​​when performing paper syntax analysis and error detection, thereby realizing a multilingual educational environment. For example, the paper correction unit adds a function to the generative AI to perform syntax analysis and error detection in different languages, thereby realizing a multilingual educational environment. For example, syntax analysis and error detection is performed in English, French, Chinese, etc. The paper correction unit also builds a system that provides multilingual syntax analysis and error detection. For example, it allows students to receive syntax analysis and error detection in the language of their choice. The paper correction unit also allows the generative AI to learn different languages ​​and provide multilingual syntax analysis and error detection. For example, syntax analysis and error detection is performed in English for papers submitted in English. This makes it possible to realize a multilingual educational environment.

[0044] The essay correction department refers to students' past submissions when making suggestions for improving the logical structure of a paper, and can provide suggestions tailored to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and provide suggestions tailored to their growth based on that data. For example, it points out areas for improvement based on past mistakes. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides suggestions that show growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal suggestions for each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide suggestions tailored to each student's growth.

[0045] The paper correction unit can provide multifaceted suggestions based on different evaluation criteria when making suggestions for improving the logical structure of a paper. For example, when the generative AI makes suggestions for improving the logical structure of a paper, the paper correction unit provides suggestions based on different evaluation criteria, such as logic, consistency, and persuasiveness. For example, it makes suggestions to improve logical consistency. The paper correction unit also builds a system that provides suggestions based on different evaluation criteria. For example, it provides separate suggestions for logic and suggestions for persuasiveness. The paper correction unit also allows the generative AI to learn different evaluation criteria and provide multifaceted suggestions. For example, it simultaneously provides suggestions to improve logic and suggestions to maintain consistency. This makes it possible to provide multifaceted suggestions.

[0046] The essay correction unit can add a function that suggests improvements to the logical structure of not only essays but also presentations and oral examinations. For example, the essay correction unit could add a function where the generative AI suggests improvements to the logical structure of presentations and oral examinations, allowing students to learn from multiple angles. For example, it could provide suggestions regarding the structure of a presentation and how the speech is delivered. The essay correction unit could also build a system that suggests improvements to the logical structure of presentations and oral examinations. For example, it could analyze the content of a student's presentation and how they speak, and point out specific areas for improvement. The essay correction unit could also learn from data on presentations and oral examinations and suggest improvements to the logical structure. For example, it could provide suggestions regarding the flow of the presentation and the logical structure. This would allow it to suggest improvements to the logical structure of presentations and oral examinations.

[0047] The paper correction unit can provide suggestions in different languages ​​when making suggestions for improving the logical structure of a paper, thereby realizing a multilingual educational environment. For example, the paper correction unit can add a function whereby the generative AI makes suggestions for improving the logical structure in different languages, thereby realizing a multilingual educational environment. For example, suggestions can be provided in English, French, Chinese, etc. The paper correction unit can also build a system that provides multilingual suggestions for improving the logical structure. For example, it can enable students to receive suggestions in the language of their choice. The paper correction unit can also have the generative AI learn different languages ​​and provide multilingual suggestions for improving the logical structure. For example, it can make suggestions in English for a paper submitted in English. This can realize a multilingual educational environment.

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

[0049] The test question generation unit can refer to a student's learning history when generating questions and prioritize questions that address each student's weaknesses. For example, if the generation AI analyzes a student's past test results and learning history and finds that they lack understanding in a particular area, it will generate many questions related to that area. The test question generation unit can also provide review questions at an appropriate time according to the student's learning progress. For example, it can generate questions to review previously learned content after a certain period of time has passed. The test question generation unit can also provide a good balance of visual and auditory questions according to the student's learning style. This makes it possible to generate questions that meet the individual learning needs of each student.

[0050] The test question generation unit can provide feedback based on the student's learning goals for the questions it generates. For example, the generation AI can analyze the student's learning goals and provide feedback that matches those goals. For example, it can provide detailed explanations to improve comprehension. The test question generation unit can also provide immediate feedback for questions answered by students. For example, it can determine whether the answer is correct immediately after the answer is given, and if it is correct, it can present the reason why, and if it is incorrect, it can present the correct answer and the reason why. The test question generation unit can also adjust the content of the feedback according to the student's learning progress. For example, it can provide basic explanations to beginners and applied explanations to advanced learners. This makes it possible to provide feedback that matches the student's learning goals.

[0051] The test question generation unit can generate questions that are suited to the student's learning environment. For example, the generation AI can analyze the student's learning environment and generate questions that are suited to that environment. For example, interactive questions can be provided in an online learning environment, and printable questions can be provided in an offline learning environment. The test question generation unit can also adjust the question format depending on the student's learning device. For example, if a student uses a tablet or smartphone, questions suited to touch operation can be provided. The test question generation unit can also provide a good balance of questions that can be answered in a short time and questions that take a long time to answer, depending on the student's study time. This makes it possible to provide questions that are suited to the student's learning environment.

[0052] The test question generation unit can incorporate gamification elements into the questions it generates to increase students' motivation to learn. For example, the generation AI can award points each time a question is solved, allowing students to earn badges and titles based on those points. The test question generation unit can also provide a ranking function that allows students to compete with other students. For example, it can display rankings based on the speed at which students solve questions or the percentage of correct answers. The test question generation unit can also provide a goal setting function that allows students to feel a sense of accomplishment. For example, it can set a goal that gives students a sense of accomplishment each time they solve a certain number of questions. This can increase students' motivation to learn.

[0053] The test question generation unit can provide a function that visualizes a student's learning progress for the questions it generates. For example, the generation AI can analyze a student's learning progress and display that progress in graphs and charts. The test question generation unit can also provide a dashboard function that allows students to check their own learning progress. For example, it can make it possible to check at a glance the number of questions answered, the percentage of correct answers, and the amount of time spent studying. The test question generation unit can also suggest what content a student should study next based on their learning progress. For example, if they lack understanding in a particular area, it will prioritize providing questions related to that area. This makes it possible to visualize a student's learning progress and support effective learning.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The test question generation unit studies past test questions and generates test questions based on parameters set by the teacher. For example, the test question generation unit studies past mathematics test questions and generates a balanced mix of different types of questions, such as multiple-choice and written questions. The test question generation unit also generates test questions based on parameters set by the teacher, such as the type of test, difficulty level, and subject. For example, when generating mathematics test questions, the test question generation unit can set 50% multiple-choice questions and 50% written questions, and set the difficulty level to intermediate. Step 2: The essay correction department analyzes essays and reports written by students, detecting syntax errors, missing information, logical leaps, and citation errors, and makes specific suggestions for improvement. For example, the essay correction department analyzes English essays submitted by students, detects grammatical errors and spelling mistakes, and suggests appropriate revisions. The essay correction department also points out missing information and logical leaps and makes specific suggestions for improvement. For example, the essay correction department provides advice on digging deeper into the essay's topic and maintaining logical consistency.

[0056] (Example 2) An education support system according to an embodiment of the present invention is a system that includes a generation AI that studies past exam questions and generates exam questions based on parameters set by the teacher, and a generation AI that analyzes essays and reports written by students, detecting syntax errors, missing information, logical leaps, citation errors, etc., and makes specific suggestions for improvement. As a result, the education support system can improve the efficiency of exam question generation and essay correction, providing significant benefits to both teachers and students.

[0057] An education support system according to an embodiment includes a test question generation unit and an essay correction unit. The test question generation unit studies past test questions and generates test questions based on parameters set by a teacher. For example, the test question generation unit studies past mathematics test questions and generates a balanced mix of different types of questions, such as multiple-choice and essay questions. The test question generation unit also generates test questions based on parameters set by a teacher, such as the type of test, difficulty level, and subject. For example, when generating mathematics test questions, the test question generation unit may set 50% multiple-choice questions and 50% essay questions, and set the difficulty level to intermediate. The essay correction unit analyzes essays and reports written by students, detects syntax errors, missing information, logical leaps, citation errors, and other errors, and makes specific suggestions for improvement. For example, the essay correction unit analyzes English essays submitted by students, detects grammatical errors and spelling mistakes, and proposes appropriate revisions. The essay correction unit also points out missing information and logical leaps and makes specific suggestions for improvement. For example, the essay correction unit provides advice on digging deeper into the essay topic and maintaining logical consistency. This allows the education support system according to the embodiment to improve the efficiency of generating exam questions and correcting essays, thereby providing great benefits to both teachers and students.

[0058] The test question generation unit uses an emotion estimation function to analyze students' emotional reactions to the generated questions and prioritizes generating questions that will interest students the most. For example, the test question generation unit analyzes students' facial expressions and voices to calculate an emotion score for test questions generated by the generation AI. For example, if a student smiles or has an interested tone of voice, it prioritizes generating questions that match that. The test question generation unit also collects data showing students' emotional reactions to test questions in real time, and the generation AI evaluates the interest level of the questions based on that data. For example, if a student shows a positive reaction when solving a question, it will generate more questions in that format. The test question generation unit also uses an emotion estimation function to identify questions on topics and formats that students are most interested in, and the generation AI generates questions based on that information. For example, if a student shows a high interest in a particular topic, it will generate more questions related to that topic. This allows it to prioritize generating questions that will interest students.

[0059] The test question generation unit adds a real-time difficulty adjustment function to the questions it generates, allowing it to dynamically change the difficulty of questions depending on the student's answering status. For example, the test question generation unit uses a generation AI to analyze the student's answering status in real time and dynamically adjust the difficulty of the questions. For example, if a student answers a series of questions easily, the difficulty of the next question will be increased. The test question generation unit also builds a system in which the generation AI adjusts the difficulty of questions in real time based on the student's answering time and accuracy rate. For example, if the answering time is short, the difficulty will be increased, and if the answering time is long, the difficulty will be decreased. The test question generation unit also uses a generation AI to collect student answer data and dynamically change the difficulty of questions using a difficulty adjustment algorithm. For example, if a student answers correctly consecutively, the difficulty of the next question will be increased. This allows the difficulty of questions to be dynamically adjusted depending on the student's answering status.

[0060] The test question generation unit introduces question formats that accommodate different learning styles, making it possible to provide questions that are optimal for each individual student. For example, the test question generation unit uses a generation AI to generate questions that make extensive use of diagrams and graphs for visual learners. For example, it provides math questions that use figures and graphs. The test question generation unit also adds a function to present questions via audio for auditory learners. For example, it generates English listening questions and presents the questions via audio. The test question generation unit also introduces interactive question formats for tactile learners. For example, it generates questions that can be answered by drag and drop using a tablet or smartphone. This makes it possible to provide questions that are optimal for each individual student.

[0061] The test question generation unit can add a function to generate not only test questions, but also questions for everyday study assignments and homework. For example, the test question generation unit adds a function for the generation AI to generate questions for everyday study assignments and homework, allowing students to study on a daily basis. For example, it generates mathematics questions as daily homework. The test question generation unit also adds a function to generate study assignments, allowing students to study independently at home. For example, it generates English vocabulary practice questions and reading comprehension questions. The test question generation unit also builds a system in which the generation AI generates study assignments and homework of an appropriate level of difficulty according to the student's learning progress. For example, the difficulty level can be gradually increased towards the end of the semester. This makes it possible to generate questions for everyday study assignments and homework.

[0062] The test question generation unit can meet international educational needs by including questions that correspond to the educational curricula of different cultures and regions. For example, the test question generation unit adds a function in which the generation AI generates questions that correspond to the educational curricula of different cultures and regions. For example, it generates mathematics questions based on the American educational curriculum. In addition, to meet international educational needs, the test question generation unit builds a system in which the generation AI generates questions in multiple languages. For example, it generates questions in English, French, Chinese, etc. In addition, the test question generation unit allows the generation AI to study the educational curricula of different regions and generate questions specific to those regions. For example, it generates history questions based on the Japanese educational curriculum. This makes it possible to meet international educational needs.

[0063] The test question generation unit uses the emotion estimation function to analyze teachers' emotional reactions to the questions it generates, and can prioritize generating questions that teachers will rate highly. The test question generation unit, for example, analyzes teachers' emotional reactions to questions generated by the generation AI and calculates an emotional score. For example, it prioritizes generating questions that teachers have given high marks to. The test question generation unit also collects data showing teachers' emotional reactions to the generation AI in real time and evaluates questions based on that data. For example, it generates many questions to which teachers have given positive reactions. The test question generation unit also uses the emotion estimation function to identify questions that teachers will rate highly, and the generation AI generates questions based on that information. For example, it generates many question formats and topics that teachers have given high marks to. This allows it to prioritize generating questions that teachers will rate highly.

[0064] The essay correction unit uses an emotion estimation function to analyze students' emotional reactions when correcting essays, and can provide feedback that students find most acceptable. For example, when the generation AI corrects a paper, the essay correction unit analyzes students' facial expressions and voices and calculates an emotion score. For example, it prioritizes providing feedback to which students have responded positively. The essay correction unit also collects data on students' real-time emotional reactions to essay corrections and adjusts the content of the feedback based on that data. For example, it uses expressions that are easy for students to accept. The essay correction unit also uses an emotion estimation function to identify feedback that students find most acceptable, and the generation AI provides feedback based on that information. For example, it often uses feedback formats to which students have responded positively. This allows it to provide feedback that students find most acceptable.

[0065] The essay correction department refers to students' past submissions when correcting essays and can provide feedback that corresponds to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and provide feedback that corresponds to their growth based on that data. For example, it points out areas for improvement based on past mistakes. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides feedback that shows growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal feedback to each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide feedback that corresponds to each student's growth.

[0066] The essay correction unit can provide multifaceted feedback based on different evaluation criteria when correcting an essay. For example, when the generative AI corrects an essay, the essay correction unit provides feedback based on different evaluation criteria, such as creativity, logic, and expressiveness. For example, it provides feedback to evaluate creative ideas. The essay correction unit also builds a system that provides feedback based on different evaluation criteria. For example, it provides separate feedback on logic and feedback on expressiveness. The essay correction unit also allows the generative AI to learn different evaluation criteria and provide multifaceted feedback. For example, it provides feedback on creativity and feedback on logic simultaneously. This makes it possible to provide multifaceted feedback.

[0067] The essay correction unit can provide feedback in different languages ​​when correcting essays, thereby realizing a multilingual educational environment. For example, the essay correction unit can add a function that enables the generation AI to provide feedback in different languages, thereby realizing a multilingual educational environment. For example, feedback can be provided in English, French, Chinese, etc. The essay correction unit can also build a system that provides multilingual feedback. For example, it can enable students to receive feedback in the language of their choice. The essay correction unit can also enable the generation AI to learn different languages ​​and provide multilingual feedback. For example, feedback can be provided in English for essays submitted in English. This can realize a multilingual educational environment.

[0068] The essay correction unit uses the emotion estimation function to analyze the teacher's emotional response to the feedback provided by the generation AI, and can prioritize providing the feedback that the teacher values ​​most. For example, the essay correction unit analyzes the teacher's emotional response to the feedback provided by the generation AI and calculates an emotion score. For example, it prioritizes providing feedback that the teacher gave a high rating to. The essay correction unit also collects data showing the teacher's emotional response to the generation AI in real time, and adjusts the content of the feedback based on that data. For example, it provides more feedback to which the teacher gave a positive response. The essay correction unit also uses the emotion estimation function to identify feedback that the teacher values ​​most, and the generation AI provides feedback based on that information. For example, it provides more feedback formats and content that the teacher gave a high rating to. This makes it possible to prioritize providing feedback that the teacher values ​​most.

[0069] The test question generation unit uses an emotion estimation function to analyze students' emotional responses when setting the type and difficulty of test questions, and can prioritize settings that students find most challenging. For example, when the generation AI sets the type and difficulty of test questions, the test question generation unit analyzes students' facial expressions and voices and calculates an emotion score. For example, it prioritizes setting questions that students find challenging. The test question generation unit also collects data showing students' real-time emotional responses to the type and difficulty of test questions, and adjusts settings based on that data. For example, it sets a difficulty level that students find challenging. The test question generation unit also uses an emotion estimation function to identify the type and difficulty of questions that students find most challenging, and the generation AI sets settings based on that information. For example, it sets more question types and difficulty levels that students show a high willingness to take on. This allows it to prioritize settings that students find most challenging.

[0070] The test question generation unit can refer to past test results when setting the type and difficulty of test questions, and introduce the most effective settings for improving students' grades. For example, the test question generation unit uses a generation AI to analyze past test results and set the type and difficulty of questions that are most effective for improving students' grades. For example, it determines the optimal level of difficulty based on past data. The test question generation unit also references students' past test results and builds a system that sets the type and difficulty of questions that are effective for improving grades. For example, it adjusts the balance of questions based on past grade data. The test question generation unit also uses a generation AI to learn past test results and introduce the most effective settings for improving students' grades. For example, it sets more question formats and difficulty levels that have earned high scores in past tests. This makes it possible to introduce the most effective settings for improving students' grades.

[0071] The test question generation unit can provide settings according to different learning goals when setting the type and difficulty of test questions. In the test question generation unit, for example, the generation AI sets the type and difficulty of questions according to different learning goals. For example, a good balance is set between basic questions for assessing comprehension and applied questions for assessing applied ability. The test question generation unit also builds a system that sets the type and difficulty of questions according to learning goals. For example, open-ended questions are set to assess creativity. In addition, the test question generation unit sets the type and difficulty of questions based on the learning goals. For example, questions that require detailed explanations to deepen understanding and practical questions to test applied ability are set. This makes it possible to provide settings according to different learning goals.

[0072] The test question generation unit can add a function to set not only the type and difficulty of test questions, but also the test format. For example, the test question generation unit adds a function that enables the generation AI to set the test format, allowing the selection of formats such as online tests and paper tests. For example, it generates interactive questions for online tests. The test question generation unit also adds a test format setting function, building a system that generates questions according to the format selected by the student. For example, it generates printable questions for paper tests. The test question generation unit also allows the generation AI to learn the test format and set the optimal format. For example, it generates time-limited questions for online tests and long-answer questions for paper tests. This makes it possible to set the test format.

[0073] The test question generation unit can provide settings that correspond to different educational systems when setting the type and difficulty of test questions. For example, the test question generation unit adds a function in which the generation AI sets the type and difficulty of questions that correspond to different educational systems. For example, it generates questions that correspond to the IB (International Baccalaureate) or AP (Advanced Placement). The test question generation unit also builds a system that sets the type and difficulty of questions that correspond to the educational system. For example, it generates questions that correspond to GCSE (Grade 12 Standard). The test question generation unit also allows the generation AI to learn about different educational systems and set the type and difficulty of questions that are specific to that system. For example, it generates questions based on the IB curriculum. This makes it possible to provide settings that correspond to different educational systems.

[0074] The test question generation unit uses the emotion estimation function to analyze teachers' emotional reactions to the types and difficulty levels of test questions set by the generation AI, and is able to prioritize providing the settings that teachers rate highly. For example, the test question generation unit analyzes teachers' emotional reactions to the types and difficulty levels of test questions set by the generation AI and calculates an emotional score. For example, it prioritizes providing settings that teachers rate highly. The test question generation unit also collects data showing teachers' emotional reactions to the generation AI in real time and adjusts settings based on that data. For example, it provides many settings that teachers rate positively. The test question generation unit also uses the emotion estimation function to identify the types and difficulty levels of test questions that teachers rate highly, and the generation AI sets settings based on that information. For example, it sets many question formats and difficulty levels that teachers rate highly. This allows the settings that teachers rate most highly to be provided preferentially.

[0075] The essay correction unit uses an emotion estimation function to analyze students' emotional reactions when analyzing essays and detecting errors, and can provide revisions that are most acceptable to students. For example, when the generation AI performs essay syntax analysis and error detection, the essay correction unit analyzes students' facial expressions and voices and calculates an emotion score. For example, it prioritizes providing revisions to which students have responded positively. The essay correction unit also collects data on students' real-time emotional reactions to syntax analysis and error detection, and adjusts the content of the revisions based on that data. For example, it uses expressions that are more acceptable to students. The essay correction unit also uses an emotion estimation function to identify revisions that are most acceptable to students, and the generation AI provides revisions based on that information. For example, it frequently uses revision formats to which students have responded positively. This allows it to provide revisions that are most acceptable to students.

[0076] The essay correction department refers to students' past submissions when analyzing essay syntax and detecting errors, and can provide revision suggestions tailored to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and, based on that data, provide revision suggestions tailored to their growth. For example, it points out areas for improvement based on past errors. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides revision suggestions that show growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal revision suggestions for each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide revision suggestions tailored to each student's growth.

[0077] The essay correction unit can add functions to perform syntax analysis and error detection not only for essays but also for other text formats such as short sentences and poetry. For example, the essay correction unit adds functions to the generative AI to perform syntax analysis and error detection for other text formats such as short sentences and poetry, allowing students to learn from multiple angles. For example, it provides suggestions for correcting grammatical errors in short sentences. The essay correction unit also builds a system that performs syntax analysis and error detection for short sentences and poetry. For example, it analyzes the rhythm and rhyme of poetry and points out areas for improvement. The essay correction unit also trains the generative AI on data from short sentences and poems to perform syntax analysis and error detection. For example, it provides suggestions for correcting grammatical errors in short sentences and suggestions for improving the rhythm of poetry. This allows syntax analysis and error detection for other text formats such as short sentences and poetry.

[0078] The paper correction unit can provide analysis and error detection in different languages ​​when performing paper syntax analysis and error detection, thereby realizing a multilingual educational environment. For example, the paper correction unit adds a function to the generative AI to perform syntax analysis and error detection in different languages, thereby realizing a multilingual educational environment. For example, syntax analysis and error detection is performed in English, French, Chinese, etc. The paper correction unit also builds a system that provides multilingual syntax analysis and error detection. For example, it allows students to receive syntax analysis and error detection in the language of their choice. The paper correction unit also allows the generative AI to learn different languages ​​and provide multilingual syntax analysis and error detection. For example, syntax analysis and error detection is performed in English for papers submitted in English. This makes it possible to realize a multilingual educational environment.

[0079] The essay correction unit uses the emotion estimation function to analyze the teacher's emotional response to the revision suggestions provided by the generation AI, and can prioritize providing the revision suggestions that the teacher most highly evaluates. For example, the essay correction unit analyzes the teacher's emotional response to the revision suggestions provided by the generation AI and calculates an emotion score. For example, it prioritizes providing revision suggestions that the teacher highly evaluates. The essay correction unit also collects data showing the teacher's emotional response to the generation AI in real time, and adjusts the content of the revision suggestions based on that data. For example, it provides more revision suggestions that the teacher responded positively to. The essay correction unit also uses the emotion estimation function to identify the revision suggestions that the teacher most evaluates, and the generation AI provides revision suggestions based on that information. For example, it provides more revision formats and content that the teacher highly evaluates. This allows the revision suggestions that the teacher most evaluates to be prioritized.

[0080] The essay correction unit uses the emotion estimation function to analyze students' emotional reactions when making suggestions for improving the logical structure of a paper, and can provide suggestions that are most easily accepted by the student. For example, when the generation AI makes suggestions for improving the logical structure of a paper, the essay correction unit analyzes the student's facial expressions and voice to calculate an emotion score. For example, it prioritizes providing suggestions that students respond positively to. The essay correction unit also collects data showing students' real-time emotional reactions to suggestions for improving the logical structure, and adjusts the content of the suggestions based on that data. For example, it uses expressions that are easily accepted by students. The essay correction unit also uses the emotion estimation function to identify suggestions that students are most likely to accept, and the generation AI provides suggestions based on that information. For example, it often uses proposal formats that students respond positively to. This allows it to provide suggestions that students are most likely to accept.

[0081] The essay correction department refers to students' past submissions when making suggestions for improving the logical structure of a paper, and can provide suggestions tailored to each student's growth. For example, the essay correction department uses a generative AI to analyze students' past submissions and provide suggestions tailored to their growth based on that data. For example, it points out areas for improvement based on past mistakes. The essay correction department also references students' past submissions and builds a system to evaluate their degree of growth. For example, it compares past submissions with current submissions and provides suggestions that show growth. The essay correction department also uses a generative AI to learn from students' past submissions and provide optimal suggestions for each student. For example, it re-examines points pointed out in past submissions and encourages improvement. This makes it possible to provide suggestions tailored to each student's growth.

[0082] The paper correction unit can provide multifaceted suggestions based on different evaluation criteria when making suggestions for improving the logical structure of a paper. For example, when the generative AI makes suggestions for improving the logical structure of a paper, the paper correction unit provides suggestions based on different evaluation criteria, such as logic, consistency, and persuasiveness. For example, it makes suggestions to improve logical consistency. The paper correction unit also builds a system that provides suggestions based on different evaluation criteria. For example, it provides separate suggestions for logic and suggestions for persuasiveness. The paper correction unit also allows the generative AI to learn different evaluation criteria and provide multifaceted suggestions. For example, it simultaneously provides suggestions to improve logic and suggestions to maintain consistency. This makes it possible to provide multifaceted suggestions.

[0083] The essay correction unit can add a function that suggests improvements to the logical structure of not only essays but also presentations and oral examinations. For example, the essay correction unit could add a function where the generative AI suggests improvements to the logical structure of presentations and oral examinations, allowing students to learn from multiple angles. For example, it could provide suggestions regarding the structure of a presentation and how the speech is delivered. The essay correction unit could also build a system that suggests improvements to the logical structure of presentations and oral examinations. For example, it could analyze the content of a student's presentation and how they speak, and point out specific areas for improvement. The essay correction unit could also learn from data on presentations and oral examinations and suggest improvements to the logical structure. For example, it could provide suggestions regarding the flow of the presentation and the logical structure. This would allow it to suggest improvements to the logical structure of presentations and oral examinations.

[0084] The paper correction unit can provide suggestions in different languages ​​when making suggestions for improving the logical structure of a paper, thereby realizing a multilingual educational environment. For example, the paper correction unit can add a function whereby the generative AI makes suggestions for improving the logical structure in different languages, thereby realizing a multilingual educational environment. For example, suggestions can be provided in English, French, Chinese, etc. The paper correction unit can also build a system that provides multilingual suggestions for improving the logical structure. For example, it can enable students to receive suggestions in the language of their choice. The paper correction unit can also have the generative AI learn different languages ​​and provide multilingual suggestions for improving the logical structure. For example, it can make suggestions in English for a paper submitted in English. This can realize a multilingual educational environment.

[0085] The essay correction unit uses the emotion estimation function to analyze the teacher's emotional response to the proposals provided by the generation AI, and can prioritize providing the proposals that the teacher most highly evaluates. For example, the essay correction unit analyzes the teacher's emotional response to the proposals provided by the generation AI and calculates an emotion score. For example, it prioritizes providing proposals that the teacher highly evaluates. The essay correction unit also collects data showing teachers' emotional responses to the generation AI in real time, and adjusts the content of the proposals based on that data. For example, it provides many proposals to which the teacher responded positively. The essay correction unit also uses the emotion estimation function to identify proposals that the teacher most highly evaluates, and the generation AI provides proposals based on that information. For example, it provides many proposal formats and contents that the teacher highly evaluates. This allows the proposals that the teacher most highly evaluates to be prioritized.

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

[0087] The test question generation unit can refer to a student's learning history when generating questions and prioritize questions that address each student's weaknesses. For example, if the generation AI analyzes a student's past test results and learning history and finds that they lack understanding in a particular area, it will generate many questions related to that area. The test question generation unit can also provide review questions at an appropriate time according to the student's learning progress. For example, it can generate questions to review previously learned content after a certain period of time has passed. The test question generation unit can also provide a good balance of visual and auditory questions according to the student's learning style. This makes it possible to generate questions that meet the individual learning needs of each student.

[0088] The test question generation unit can provide feedback based on the student's learning goals for the questions it generates. For example, the generation AI can analyze the student's learning goals and provide feedback that matches those goals. For example, it can provide detailed explanations to improve comprehension. The test question generation unit can also provide immediate feedback for questions answered by students. For example, it can determine whether the answer is correct immediately after the answer is given, and if it is correct, it can present the reason why, and if it is incorrect, it can present the correct answer and the reason why. The test question generation unit can also adjust the content of the feedback according to the student's learning progress. For example, it can provide basic explanations to beginners and applied explanations to advanced learners. This makes it possible to provide feedback that matches the student's learning goals.

[0089] The test question generation unit can generate questions that are suited to the student's learning environment. For example, the generation AI can analyze the student's learning environment and generate questions that are suited to that environment. For example, interactive questions can be provided in an online learning environment, and printable questions can be provided in an offline learning environment. The test question generation unit can also adjust the question format depending on the student's learning device. For example, if a student uses a tablet or smartphone, questions suited to touch operation can be provided. The test question generation unit can also provide a good balance of questions that can be answered in a short time and questions that take a long time to answer, depending on the student's study time. This makes it possible to provide questions that are suited to the student's learning environment.

[0090] The test question generation unit can incorporate gamification elements into the questions it generates to increase students' motivation to learn. For example, the generation AI can award points each time a question is solved, allowing students to earn badges and titles based on those points. The test question generation unit can also provide a ranking function that allows students to compete with other students. For example, it can display rankings based on the speed at which students solve questions or the percentage of correct answers. The test question generation unit can also provide a goal setting function that allows students to feel a sense of accomplishment. For example, it can set a goal that gives students a sense of accomplishment each time they solve a certain number of questions. This can increase students' motivation to learn.

[0091] The test question generation unit can provide a function that visualizes a student's learning progress for the questions it generates. For example, the generation AI can analyze a student's learning progress and display that progress in graphs and charts. The test question generation unit can also provide a dashboard function that allows students to check their own learning progress. For example, it can make it possible to check at a glance the number of questions answered, the percentage of correct answers, and the amount of time spent studying. The test question generation unit can also suggest what content a student should study next based on their learning progress. For example, if they lack understanding in a particular area, it will prioritize providing questions related to that area. This makes it possible to visualize a student's learning progress and support effective learning.

[0092] The test question generation unit can use the emotion estimation function to analyze students' emotional responses and provide an environment in which students can study in the most relaxed manner. For example, the generation AI can analyze students' facial expressions and voices to evaluate their level of relaxation. For example, it can prioritize providing questions that students answered when they were relaxed. The test question generation unit can also adjust the learning environment so that students can study in a relaxed manner. For example, it can add a function to play relaxing music. The test question generation unit can also use the emotion estimation function to identify the time of day when students can study in the most relaxed manner and provide questions at that time. This makes it possible to provide an environment in which students can study in a relaxed manner.

[0093] The test question generation unit can use the emotion estimation function to analyze students' emotional reactions and provide questions that allow students to concentrate best. For example, the generation AI can analyze students' facial expressions and voices to evaluate their level of concentration. For example, it can prioritize providing questions that students answered when they were concentrating. The test question generation unit can also adjust the difficulty and format of questions to help students concentrate. For example, it can provide more difficult questions when students are highly focused, and less difficult questions when they are less focused. The test question generation unit can also use the emotion estimation function to identify times of day when students are most able to concentrate best and provide questions at those times. This allows it to provide questions that allow students to concentrate best.

[0094] The test question generation unit can use the emotion estimation function to analyze students' emotional reactions and provide questions that will allow students to study with the most enjoyment. For example, the generation AI can analyze students' facial expressions and voices to evaluate the level of enjoyment. For example, questions that students answered when they were enjoying themselves can be provided preferentially. The test question generation unit can also devise the content and format of questions to help students enjoy studying. For example, questions that incorporate game elements can be provided. The test question generation unit can also use the emotion estimation function to identify the time of day when students are most likely to enjoy studying and provide questions at those times. This makes it possible to provide questions that will allow students to study with the most enjoyment.

[0095] The test question generation unit can use the emotion estimation function to analyze students' emotional reactions and provide them with questions that will cause them the least stress. For example, the generation AI can analyze a student's facial expressions and voice to evaluate their stress level. For example, it can prioritize providing questions that the student answered when they were not feeling stressed. The test question generation unit can also adjust the difficulty and format of the questions so that students do not feel stressed. For example, it can provide low-difficulty questions when stress is high, and high-difficulty questions when stress is low. The test question generation unit can also use the emotion estimation function to identify the time periods when students feel the least stress and provide questions at those times. This allows it to provide students with questions that will cause them the least stress.

[0096] The test question generation unit can use the emotion estimation function to analyze students' emotional reactions and provide questions that students can answer with the most confidence. For example, the generation AI can analyze a student's facial expressions and voice to evaluate their level of confidence. For example, questions that students answered when they felt confident can be preferentially provided. The test question generation unit can also adjust the difficulty and format of questions so that students can answer with confidence. For example, more difficult questions are provided when students feel confident, and less difficult questions are provided when they feel less confident. The test question generation unit can also use the emotion estimation function to identify time periods when students can answer with the most confidence and provide questions at those time periods. This makes it possible to provide questions that students can answer with the most confidence.

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

[0098] Step 1: The test question generation unit studies past test questions and generates test questions based on parameters set by the teacher. For example, the test question generation unit studies past mathematics test questions and generates a balanced mix of different types of questions, such as multiple-choice and written questions. The test question generation unit also generates test questions based on parameters set by the teacher, such as the type of test, difficulty level, and subject. For example, when generating mathematics test questions, the test question generation unit can set 50% multiple-choice questions and 50% written questions, and set the difficulty level to intermediate. Step 2: The essay correction department analyzes essays and reports written by students, detecting syntax errors, missing information, logical leaps, and citation errors, and makes specific suggestions for improvement. For example, the essay correction department analyzes English essays submitted by students, detects grammatical errors and spelling mistakes, and suggests appropriate revisions. The essay correction department also points out missing information and logical leaps and makes specific suggestions for improvement. For example, the essay correction department provides advice on digging deeper into the essay's topic and maintaining logical consistency.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0133] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0140] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0149] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0157] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0158] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0160] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0161] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0162] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

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

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a test question generation unit that learns past test questions and generates test questions based on parameters set by a teacher; The department also has a paper correction department that analyzes essays and reports written by students, detects syntax errors, missing information, logical leaps, citation errors, etc., and makes specific suggestions for improvement. A system characterized by:

2. The test question generation unit Analyzing the emotional reactions of the students to the generated questions and generating the questions that are most interesting to the students with priority.

2. The system of claim 1.

3. The test question generation unit Add a real-time difficulty adjustment function to the questions to be generated, and dynamically change the difficulty of the questions according to the student's answering status.

2. The system of claim 1.

4. The test question generation unit Introducing question formats that cater to different learning styles and provide the most suitable questions for each student 2. The system of claim 1.

5. The test question generation unit Add the ability to generate questions for everyday study and homework assignments, not just exam questions.

2. The system of claim 1.

6. The test question generation unit Addressing international educational needs by including questions that address different cultural and regional educational curricula 2. The system of claim 1.

Images