system

Abstract

We provide the system. [Solution] Means for obtaining curriculum information, A means for automatically generating teaching materials based on the aforementioned curriculum information, A means of sending the generated teaching materials to the teacher's terminal, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The shortage of teachers in the educational field and the resulting decline in the quality of education are serious problems. The overwork and increased stress of teachers cause resignations and leaves of absence, resulting in a vicious cycle that further exacerbates the shortage of teachers. In addition, it is also difficult to grasp the individual learning needs of each student and provide corresponding educational support. As a result, the quality of education has declined, and the learning effect of students has not been maximized. The purpose of the present invention is to solve these problems and provide a system for improving the quality of education.

Means for Solving the Problems

[0005] This invention is a system that combines educational support AI and educational data analysis AI to solve problems in educational settings. Specifically, it comprises the following means.

[0006] 1. The system includes means for acquiring curriculum information, means for automatically generating teaching materials based on this curriculum information, and means for transmitting the generated teaching materials to teachers' terminals, thereby reducing the burden of teaching material creation on teachers.

[0007] 2. The system includes means for collecting student response data, means for comparing the response data with a correct answer key and scoring, and means for notifying the teacher of the scoring results as grades on the teacher's terminal, thereby streamlining the teacher's scoring work.

[0008] 3. The system includes means for collecting student learning progress data, means for analyzing this learning progress data to identify students' learning tendencies and areas where they are lacking, means for generating supplementary materials and activities based on the analysis results, and means for transmitting the generated supplementary materials to the terminals of teachers and students, thereby providing individualized learning support for each student.

[0009] 4. The system includes means for collecting students' learning history and performance data, means for analyzing this learning history and performance data, means for proposing an optimal learning approach based on the analysis results, and means for notifying the teacher of the proposal via their terminal, thereby providing an optimal learning method for each student.

[0010] 5. The system provides individually optimized educational plans, including means for collecting data related to students' learning needs, means for generating individualized educational plans based on this data, means for optimizing the educational plans, and means for transmitting the optimized educational plans to the terminals of teachers and students.

[0011] 6. Proposals to improve the overall quality of education include means for collecting data on the educational process, means for analyzing this data to identify areas for improvement in the educational process and curriculum, and means for notifying teachers of these areas for improvement via their terminals.

[0012] This will reduce the workload of teachers, maximize the learning effectiveness for students, and improve the overall quality of the educational environment.

[0013] "Curriculum information" refers to data that includes the educational content and learning plans set by educational institutions.

[0014] "Teaching materials" refer to educational materials such as documents, workbooks, and instruction manuals that learners use to advance their studies.

[0015] "Teacher's devices" refer to electronic devices such as computers, tablets, and smartphones that teachers use to perform their duties.

[0016] "Student response data" refers to digital data that includes answers and submissions that students have given to exams and assignments.

[0017] A "correct answer key" is a set of reference data that indicates the correct answer to a test or assignment.

[0018] "Scoring results" refer to data that shows the grades and evaluations obtained by comparing students' answer data with the correct answer key.

[0019] "Learning progress data" refers to data that records the progress and results of students' learning activities.

[0020] "Supplementary materials" are additional educational materials designed to complement the learning of the basic materials.

[0021] An "activity" refers to exercises, experiments, projects, and other activities that learners undertake for educational purposes.

[0022] "Learning history" refers to record data such as the content a student has studied in the past, the subjects they have taken, and their grades.

[0023] "Performance data" refers to data that shows the results and evaluations that students have achieved through their learning and activities.

[0024] The "learning approach" refers to the methods, means, and strategies for students to progress in their learning.

[0025] The "learning needs" refer to the support, resources, and specific requirements in the educational plan that students need to progress in their learning.

[0026] The "educational plan" refers to the learning plan and curriculum designed for each individual student.

[0027] The "educational process" refers to a series of processes including the procedures and methods of educational activities.

[0028] The "areas for improvement" refer to the parts that need to be improved in the current educational process and curriculum.

Brief Explanation of Drawings

[0029] [Figure 1] It is a conceptual diagram showing an example of the configuration of the data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of the data processing device and the smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of the data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of the data processing device and the smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of the data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of the data processing device and the headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of the data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of the data processing device and the robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0030] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0031] First, let's explain the terminology used in the following explanation.

[0032] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0033] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0034] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0035] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0036] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0037] [First Embodiment]

[0038] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0039] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0040] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0041] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0042] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0043] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0044] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0045] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0046] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0047] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0048] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0049] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0050] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade response data and notify teachers of their grades on their terminals, to analyze students' learning progress data and provide supplementary materials and activities, to analyze individual students' learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[0051] 1. Automated creation of educational materials

[0052] The server retrieves the latest curriculum information from the curriculum database and automatically generates teaching materials based on that information. For example, the server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra." The server then sends the generated teaching materials to the teacher's terminal, and the teacher distributes the materials to the students.

[0053] 2. Scoring Tool

[0054] The server collects answer data submitted from students' devices and scores it by comparing it to the correct answer key. For example, the server collects answer data for a math test, and the AI ​​compares it to the correct answer key and scores it at 90 points. The result is then notified to the teacher's device as grade data, and the teacher can check the grade.

[0055] 3. Learning support

[0056] The server periodically collects student learning progress data, and AI analyzes this data. It identifies students' learning trends and areas where they are lacking, and generates supplementary materials and activities. For example, the server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[0057] 4. Analysis of learning progress and recommendations

[0058] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, it proposes the optimal learning approach and notifies the teacher of the proposal on their terminal. For example, the server collects student C's math learning history and suggests that "lessons using a lot of visual aids" would be effective, and notifies the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[0059] 5. Creating an Individualized Education Plan

[0060] The server collects data on students' learning needs, and AI generates individualized educational plans based on that data. The generated plans are then optimized and sent to the teacher's and student's devices. For example, the server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[0061] 6. Suggestions for improving the educational process

[0062] The server collects data on the educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and creates detailed improvement suggestions. These suggestions are then notified to teachers' terminals, and teachers consider them. For example, the server analyzes school-wide lesson evaluation data and suggests "increasing reading and writing time," and notifies teachers of this suggestion. Teachers then adjust their lesson content based on the suggestion.

[0063] This invention reduces the workload of teachers while simultaneously providing optimal educational support to each student, thereby improving the overall quality of the educational environment.

[0064] The following describes the processing flow.

[0065] Automated creation of educational materials

[0066] Step 1:

[0067] The server accesses the curriculum database to retrieve the latest curriculum information.

[0068] Step 2:

[0069] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[0070] Step 3:

[0071] The server sends the generated teaching material data to the teacher's terminal.

[0072] Step 4:

[0073] The teacher receives the teaching materials on a device and checks their contents.

[0074] Step 5:

[0075] The teacher distributes teaching materials to the students, and the students use the materials to study.

[0076] Scoring tool

[0077] Step 1:

[0078] The server collects the response data submitted from the students' devices.

[0079] Step 2:

[0080] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[0081] Step 3:

[0082] The server calculates each student's score and generates grade data.

[0083] Step 4:

[0084] The server sends the grade data to the teacher's terminal.

[0085] Step 5:

[0086] Teachers check grades on their devices and provide feedback to students.

[0087] Learning support

[0088] Step 1:

[0089] The server periodically collects learning progress data from students' devices.

[0090] Step 2:

[0091] The server collects progress data, which is then input into an AI model for analysis.

[0092] Step 3:

[0093] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[0094] Step 4:

[0095] The server automatically generates supplementary materials and activities.

[0096] Step 5:

[0097] The server sends the generated supplementary materials to the teachers' and students' devices.

[0098] Step 6:

[0099] Teachers use their devices to review supplementary materials and provide instruction to students.

[0100] Learning progress analysis and suggestions

[0101] Step 1:

[0102] The server collects students' learning history and performance data.

[0103] Step 2:

[0104] The server inputs the collected data into an AI model for detailed analysis.

[0105] Step 3:

[0106] The AI ​​identifies the optimal learning approach based on the analysis results.

[0107] Step 4:

[0108] The server notifies the teacher's terminal of the proposed content.

[0109] Step 5:

[0110] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[0111] Creating an individualized education plan

[0112] Step 1:

[0113] The server collects data related to students' learning needs.

[0114] Step 2:

[0115] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[0116] Step 3:

[0117] The AI ​​optimizes the educational plans it generates.

[0118] Step 4:

[0119] The server sends optimized lesson plans to teachers' and students' devices.

[0120] Step 5:

[0121] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[0122] Suggestions for improving the education process

[0123] Step 1:

[0124] The server collects data about the entire school's educational process.

[0125] Step 2:

[0126] The server collects data, which is then input into an AI model for analysis.

[0127] Step 3:

[0128] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[0129] Step 4:

[0130] The server will notify teachers' terminals of the identified areas for improvement.

[0131] Step 5:

[0132] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[0133] (Example 1)

[0134] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0135] In today's education system, teacher shortages and a decline in the quality of education are serious problems. In addition, providing individualized instruction to each student and preparing diverse teaching materials is often difficult. As a result, education is becoming more homogenized, and the individual learning needs of students cannot be met. To solve these problems, effective and efficient creation and distribution of teaching materials, automated grading, and individualized instruction based on students' progress are required.

[0136] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0137] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials using a generation AI model based on the curriculum information, means for sending prompt messages to the generation AI model to generate teaching materials, and means for transmitting the generated teaching materials to the teacher's information terminal. This reduces the workload of teachers and enables optimal educational support tailored to the learning needs of each student.

[0138] "Curriculum information" refers to educational data that includes detailed information such as the content of lessons, learning objectives, teaching materials, and progress schedules set by educational institutions.

[0139] A "generative AI model" is an artificial intelligence technique that learns from large amounts of data and automatically generates educational materials and problem sets according to specific instructions.

[0140] A "prompt message" is text data used to give specific instructions to a generative AI model, and it plays a role in prompting the generation of educational materials and problem sets.

[0141] "Teaching materials" refer to educational materials used to support students' learning, and include textbooks, workbooks, supplementary materials, and other similar items.

[0142] "Teacher information terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers that are capable of sending and receiving data via email and applications.

[0143] "Student learning progress data" refers to data that shows the results, evaluations, level of understanding, and progress that students have achieved during the learning process, and is important information for understanding the progress of learning based on this data.

[0144] A "correct answer key" is a standard set of answers that indicates the correct answers in tests and workbooks, and serves as a standard for evaluating and grading learning.

[0145] "Grades" are numerical values ​​or evaluations that quantitatively show academic achievement, and are calculated based on factors such as test results and evaluations of submitted work.

[0146] "Supplementary materials" are educational resources added to deepen understanding of existing materials, and include additional problems, exercises, and activities.

[0147] An "activity" is a practical activity or exercise designed to support students' learning and to reinforce the learning content.

[0148] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade student response data and notify teachers of their grades on their terminals, to analyze student learning progress data and provide supplementary materials and activities, to analyze individual student learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[0149] The basic configuration of the system is as follows:

[0150] 1. Automatic generation and distribution of educational materials

[0151] The server connects to the educational institution's curriculum database and retrieves the latest curriculum information. Based on this curriculum information, it automatically generates teaching materials using a generative AI model. Specifically, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics" and sends a prompt message to the generative AI model saying, "Please generate a basic algebra problem set for Junior High School 2nd Year Mathematics." The generated teaching materials are sent to the teacher's terminal in PDF or link format, and the teacher reviews the received materials and distributes them to students.

[0152] 2. Automated scoring and grade notification

[0153] The server collects answer data submitted from students' devices. Based on this data, a generative AI model is used to match it with the correct answer key and perform automatic scoring. For example, the server receives answer data for a math test and sends a prompt message to the generative AI model saying, "Please score the math test answer data." The generative AI model calculates a score for each answer and notifies the teacher's device of the result. The teacher then reviews the score and provides feedback to the students.

[0154] 3. Learning support functions

[0155] The server periodically collects learning progress data from students' devices. This data is analyzed by a generative AI model to identify learning trends and areas where students are lacking. For example, a prompt message such as "Generate supplementary materials based on student B's learning progress data" is sent to the generative AI model, which then generates additional practice problems and materials. The generated materials are sent to the teacher's and student's devices, and the teacher uses them to provide instruction.

[0156] 4. Analysis and suggestions regarding learning progress

[0157] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. This provides a function to suggest the optimal learning approach. For example, the server might send a prompt to the generative AI model saying, "Suggest the optimal learning approach based on student C's learning history," and the generative AI model might suggest a lesson that makes extensive use of visual aids. This suggestion is then notified to the teacher's terminal, and the teacher can incorporate it into their teaching methods.

[0158] 5. Creating an Individualized Education Plan

[0159] The server collects student learning needs data and uses a generative AI model to generate individualized learning plans. For example, it might send a prompt message to the generative AI model saying, "Generate an individualized learning plan based on student D's learning needs data." The generated plan is optimized and sent to the teacher's and student's devices. The teacher then uses the plan to provide appropriate instruction.

[0160] 6. Suggestions for improving the educational process

[0161] The server collects data on the educational process and analyzes it using a generative AI model. Based on this, it creates suggestions for improving the educational process and curriculum. For example, it might send a prompt message to the generative AI model such as, "Please suggest improvements to the curriculum based on school-wide lesson evaluation data," to identify areas for improvement and generate suggestions. These suggestions are then notified to teachers' terminals and used by teachers to adjust lesson content.

[0162] As described above, the present invention, by utilizing a generated AI model and prompt text, can reduce the workload of teachers in educational settings and provide optimal educational support to each student. This makes it possible to improve the quality of education.

[0163] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0164] Step 1: Obtain curriculum information

[0165] Server: Connects to the curriculum database and retrieves the latest curriculum information. As a specific example, it retrieves curriculum information for "Junior High School 2nd Year Mathematics" from the database.

[0166] Input: Target grade and subject (e.g., 2nd year of junior high school, mathematics)

[0167] Output: Curriculum information (e.g., Fundamentals of Algebra, Fundamentals of Geometry)

[0168] Step 2: Sending prompts to the generative AI model

[0169] Server: Based on the acquired curriculum information, it sends appropriate prompts to the generating AI model. For example, it sends the prompt, "Please generate a basic algebra problem set for 2nd year junior high school mathematics."

[0170] Input: Curriculum information (e.g., Basic Algebra)

[0171] Output: Prompt message (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[0172] Step 3: Generating the teaching materials

[0173] Generative AI Model: Automatically generates educational materials based on the submitted prompt text. As a specific example, it generates a set of problems related to "Basic Algebra."

[0174] Input: Prompt text (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[0175] Output: Generated learning materials (e.g., a workbook in PDF format)

[0176] Step 4: Send the generated materials

[0177] Server: Sends the generated teaching materials to the teacher's terminal. For example, it sends a PDF file to the teacher's email address.

[0178] Input: Generated learning materials (e.g., a workbook in PDF format)

[0179] Output: Notification to the teacher's terminal and transmission of teaching materials (e.g., email transmission)

[0180] Step 5: Collecting response data

[0181] Server: Collects response data submitted from students' devices. For example, it retrieves response data submitted by students from an online testing platform.

[0182] Input: Student response data (e.g., response data in JSON format)

[0183] Output: Saving collected response data (e.g., storing in a database)

[0184] Step 6: Scoring of response data

[0185] Server: Using an AI model, the server automatically scores collected answer data by comparing it to the correct answer key. For example, it calculates the score for each question in a math test by comparing it to the correct answer key.

[0186] Input: Collected response data and correct answer key (e.g., response data in JSON format and answer set)

[0187] Output: Graded performance data (e.g., CSV file containing graded results)

[0188] Step 7: Notification of Grades

[0189] Server: Notifies teachers of grading results on their terminals. For example, it might compile the grading results into an Excel file and send it to the teacher's email address.

[0190] Input: Graded grade data (e.g., a CSV file containing graded results)

[0191] Output: Notification to the teacher's terminal and transmission of grade data (e.g., email transmission)

[0192] Step 8: Collecting learning progress data

[0193] Server: Regularly collects learning progress data from students' devices. For example, it saves students' daily learning logs to a cloud server.

[0194] Input: Student learning progress data (e.g., learning log data)

[0195] Output: Saving collected learning progress data (e.g., storing in a database)

[0196] Step 9: Analyze learning progress data

[0197] Server: Uses a generative AI model to analyze collected learning progress data. Specifically, it detects learning trends and areas of weakness in specific subjects or fields.

[0198] Input: Collected learning progress data (e.g., learning log data)

[0199] Output: Analysis results (e.g., identification of areas with deficiencies)

[0200] Step 10: Generating supplementary materials and activities

[0201] Server: Based on the analysis results, it sends prompt messages to the generating AI model to generate supplementary materials and activities. For example, it sends the prompt message, "Please generate additional problems for solving word problems."

[0202] Input: Analysis results and prompt message (e.g., "Generate teaching materials to cover the missing sections")

[0203] Output: Generated supplementary materials (e.g., PDF file of practice problems)

[0204] Step 11: Sending supplementary materials

[0205] Server: Sends the generated supplementary materials to the teacher's and students' devices. For example, it sends a link to practice problems via email.

[0206] Input: Generated supplementary materials (e.g., PDF file of practice problems)

[0207] Output: Notifications to teacher and student devices and delivery of educational materials (e.g., email).

[0208] Step 12: Collecting Learning History

[0209] Server: Regularly collects students' learning history and performance data. Specifically, it collects students' test results and classroom performance data.

[0210] Input: Student learning history and performance data (e.g., test result data)

[0211] Output: Storage of collected learning history and performance data (e.g., storage in a database)

[0212] Step 13: Proposing a Learning Approach

[0213] Server: Using a generative AI model, it analyzes learning history and performance data in detail to propose the optimal learning approach. For example, it might generate a suggestion that "lessons that heavily utilize visual materials are effective."

[0214] Input: Learning history and performance data (e.g., test result data)

[0215] Output: Proposal of the optimal learning approach (e.g., a report including the proposal)

[0216] Step 14: Notification of Proposal

[0217] Server: Notifies the instructor's terminal of the proposed content. For example, it sends a report containing the proposed content via email in PDF format.

[0218] Input: Proposal of the optimal learning approach (e.g., a report including the proposed approach)

[0219] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[0220] Step 15: Collecting Educational Process Data

[0221] Server: Collects data related to the educational process. Specifically, it regularly collects lesson evaluation data and teacher feedback.

[0222] Input: Educational process data (e.g., course evaluation data)

[0223] Output: Storage of collected educational process data (e.g., storage in a database)

[0224] Step 16: Create proposals for improving the educational process.

[0225] Server: Uses a generative AI model to analyze collected educational process data and generate specific improvement suggestions. For example, it generates a suggestion to "increase reading and writing time."

[0226] Input: Analysis results of educational process data (e.g., analysis results of lesson evaluation data)

[0227] Output: Improvement suggestions (e.g., a report including the suggested content)

[0228] Step 17: Notification of improvement suggestions

[0229] Server: Notifies teachers of the created improvement suggestions on their terminals. For example, it sends a report containing the suggestions via email in PDF format.

[0230] Input: Improvement suggestion (e.g., a report including the suggestion)

[0231] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[0232] The above processing steps represent the specific operational flow of this system. This will reduce the workload of teachers and enable the provision of optimal educational support to each individual student.

[0233] (Application Example 1)

[0234] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0235] In recent years, teacher shortages and a decline in the quality of education have become serious problems in the education sector. This problem significantly impacts educational effectiveness, particularly because it makes it difficult to provide detailed, individualized instruction to each student. Furthermore, providing learning materials and plans tailored to individual learning needs is challenging, and conventional educational support systems require more efficient solutions. Additionally, improving the quality of educational content sales and user experience in virtual stores presents significant challenges.

[0236] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0237] In this invention, the server includes means for acquiring curriculum information, means for generating educational content based on the curriculum information, means for transmitting the generated educational content to a terminal, means for recommending educational content based on the user's learning history, means for collecting user learning progress data and tracking progress, and means for generating individualized educational plans based on the user's learning needs. This makes it possible to provide detailed educational support that addresses individual learning needs while also addressing teacher shortages and the problem of declining educational quality. Furthermore, by applying this system to a virtual store, it is possible to improve the sales efficiency of educational content and the quality of the user experience.

[0238] "Curriculum information" refers to information that details the learning content, objectives, and lesson plans set by an educational institution.

[0239] "Educational content" refers to information used for educational purposes, such as textbooks, workbooks, and supplementary materials provided to learners.

[0240] "Terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers and students.

[0241] "Learning history" refers to data that records the learning activities and results that individual students have undertaken to date.

[0242] "Progress tracking" is a method of monitoring and recording learners' learning progress in real time and reporting their status as it occurs.

[0243] An "individualized learning plan" is an optimal learning plan tailored to each student's learning needs and progress.

[0244] A "generative AI model" is a model that uses artificial intelligence to create new information, and is particularly used to automatically generate educational materials and learning plans.

[0245] A "prompt statement" is an input statement used to elicit a specific response from a generative AI model.

[0246] This invention relates to a system that uses an educational support system to automatically generate and distribute educational content based on curriculum information and to provide learning plans tailored to individual learning needs. The system's hardware includes servers, a high-performance server farm, terminals (smartphones, tablets, computers), and head-mounted displays. The software utilizes educational support AI, educational data analysis AI, generative AI models (e.g., GPT-4), and a virtual reality engine (e.g., Unity).

[0247] Program Outline

[0248] 1. Acquisition of curriculum information and generation of educational content

[0249] The server retrieves curriculum information from a database and generates educational content using a generative AI model (GPT-4) based on that information. For example, it retrieves curriculum information for second-year junior high school mathematics and generates a workbook on "Basic Algebra." An example of the prompt used in this process is, "Generate educational content based on curriculum information. Second-year junior high school mathematics: Basic Algebra." The generated educational content is then sent from the server to the terminal.

[0250] 2. Recommendation of educational content

[0251] Based on the user's learning history data, the server recommends the most suitable educational content for each individual user. In this case, a generative AI model is also used to provide appropriate recommendations. For example, a request is sent to the AI ​​with the prompt message, "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization."

[0252] 3. Tracking learning progress

[0253] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. Progress is tracked in real time, and the percentage of learning progress is calculated. For example, it may be reported in the format of "Learning progress rate: 70%".

[0254] 4. Generating an individualized education plan

[0255] The server collects the user's learning needs and uses a generative AI model to generate personalized learning plans. For example, it might use a prompt message like, "Generate an appropriate learning plan if the user is struggling to solve word problems." This generated plan is then sent to the terminal.

[0256] Specific example

[0257] The following outlines the specific steps of the present invention:

[0258] 1. The server retrieves curriculum information for "Junior High School 2nd Year Mathematics," and the generating AI model generates a set of problems on "Basic Algebra."

[0259] 2. The server analyzes the user's learning history and recommends the next most suitable content based on "basic algebra and factorization."

[0260] 3. Collect learning progress data and report "7 out of 10 items completed, progress rate 70%."

[0261] 4. Based on the learning needs analysis, the generating AI model generates "additional problems for solving word problems," and an individualized education plan is generated.

[0262] Thus, the present invention enables personalized and effective educational support in educational settings and virtual stores.

[0263] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0264] Step 1:

[0265] The server retrieves curriculum information from the database. This curriculum information includes grade level, subject, and learning content. This curriculum information is used as input to generate educational content. For example, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics: Basic Algebra."

[0266] Step 2:

[0267] Based on the curriculum information acquired by the server, a prompt message is sent to the generation AI model. The specific prompt message is "Generate educational content based on the curriculum information. Junior High School 2nd Year Mathematics: Basic Algebra." The generation AI model takes this prompt message as input and generates the corresponding educational content (such as a workbook).

[0268] Step 3:

[0269] The server sends the generated educational content to the device. The device displays the content so that teachers and students can access it. The generated educational content is delivered to the device, and users can review and use it.

[0270] Step 4:

[0271] The server collects the user's learning history. The collected learning history data includes content already studied and their performance on it. This data is used as input for data processing to identify the next educational content to recommend. For example, the learning history of "basic algebra" and "factorization" in mathematics is collected.

[0272] Step 5:

[0273] The server sends a prompt to the generating AI model based on the user's learning history data. The specific prompt is: "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization." The generating AI model then recommends the following appropriate educational content.

[0274] Step 6:

[0275] The server sends recommended educational content to the device. The device displays the recommended content in a user-friendly format. The user can review the recommended content and continue learning.

[0276] Step 7:

[0277] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. The collected data includes the number of completed assignments and the total number of assignments. This data is used as input to calculate the progress rate. For example, if 7 out of 10 items have been completed, the progress rate is 70%.

[0278] Step 8:

[0279] The server notifies the terminal of the progress. The terminal visually displays the progress to the user and guides them to the next learning step. The user can check the progress report and understand the remaining learning tasks.

[0280] Step 9:

[0281] The server collects the learning needs of the user and sends a prompt sentence to the generative AI model. The specific prompt sentence is "If the user is having trouble solving the topic of the article, please generate an appropriate education plan." Based on this data, the generative AI model generates an optimal individualized education plan.

[0282] Step 10:

[0283] The server sends the generated individualized education plan to the terminal. The terminal displays the plan in a format that is easy for the user to access and provides it as a learning guideline. The user can proceed with learning based on this education plan.

[0284] Through the above steps, the education support system of the present invention can function smoothly and provide an effective educational experience for teachers and students.

[0285] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0286] The present invention is a system for solving the shortage of teachers and the decline in the quality of education in the educational field by combining educational support AI, educational data analysis AI, and an emotion engine. This system includes the following functions:

[0287] 1. Automated teaching material creation

[0288] The server accesses the curriculum database and obtains the latest curriculum information. Based on that information, AI automatically generates teaching materials. The generated teaching materials are sent from the server to the teacher's terminal. The teacher checks the teaching materials on the terminal and distributes them to the students.

[0289] Specific example:

[0290] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra" and sends it to the teacher's terminal. The teacher then distributes the materials to the students.

[0291] 2. Scoring Tool

[0292] The server collects the answer data submitted by students from their devices, compares it against the correct answer key, and scores the answers. The grade data is sent from the server to the teacher's device. The teacher reviews the grades and provides feedback to the students.

[0293] Specific example:

[0294] The server collects student A's math test answers, matches them against the correct answer key, assigns a score of 90, and notifies the teacher's terminal of the result. The teacher then checks the grade.

[0295] 3. Learning support

[0296] The server periodically collects learning progress data from students' devices, and AI analyzes this data to identify areas where students are particularly struggling. Supplementary materials and activities are generated and sent to both teachers' and students' devices.

[0297] Specific example:

[0298] The server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[0299] 4. Analysis of learning progress and recommendations

[0300] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, the AI ​​proposes the optimal learning approach, and this information is sent to the teacher's terminal. The teacher then adjusts the lesson content based on the proposal.

[0301] Specific example:

[0302] The server collects the learning history of student C in mathematics, proposes that "classes using a lot of visual teaching materials" are effective, and notifies the proposal to the teacher's terminal. The teacher adjusts the class content based on the proposal.

[0303] 5. Creation of Individual Education Plan

[0304] The server collects the learning needs data of students, and the AI generates and optimizes an individual education plan based on that data. The optimized education plan is sent to the terminals of teachers and students. The teacher checks the plan and provides appropriate guidance to the students.

[0305] Specific example:

[0306] The server analyzes the learning needs of student D, generates and optimizes a "reading and writing support program", and sends it to the terminals of teachers and students. The teacher checks the plan and provides appropriate guidance to the students.

[0307] 6. Proposal for Improving the Education Process

[0308] The server collects data on the education process of the entire school, and the AI analyzes that data. Based on the data, the improvement points of the education process and curriculum are identified, and the content is notified to the teacher's terminal. The teacher reviews the education process and curriculum based on the notified proposal.

[0309] Specific example:

[0310] The server analyzes the class evaluation data of the entire school, proposes to "increase the time for reading and writing", and notifies the proposal to the teacher. The teacher adjusts the class content based on the proposal.

[0311] 7. Utilization of the Emotion Engine

[0312] The server includes an emotion engine that recognizes user emotions and collects and analyzes user emotion data. Based on this data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials and relaxation activities.

[0313] Specific example:

[0314] The server collects emotional data from student E, and the AI ​​detects when the student is experiencing stress. Based on the analysis, it suggests relaxation exercises and sends them to the teacher's and student's devices. The teacher reviews the suggestions and instructs the student on additional relaxation activities.

[0315] 8. Utilization of teacher sentiment data

[0316] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[0317] Specific example:

[0318] The server collects emotional data from teacher F, and the AI ​​detects when the teacher is experiencing stress. Based on this, it sends suggestions to the teacher's terminal to help distribute tasks. The teacher then uses these suggestions to distribute tasks and reduce stress.

[0319] In summary, the present invention is a system that alleviates the shortage of teachers in educational settings, improves the quality of education, and further utilizes emotional data of students and teachers to provide optimal learning and guidance.

[0320] The following describes the processing flow.

[0321] Automated creation of educational materials

[0322] Step 1:

[0323] The server accesses the school's curriculum database to retrieve the latest curriculum information.

[0324] Step 2:

[0325] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[0326] Step 3:

[0327] The server sends the generated teaching material data to the teacher's terminal.

[0328] Step 4:

[0329] The teacher receives the teaching materials on a device and checks their contents.

[0330] Step 5:

[0331] The teacher will distribute the materials they have reviewed to the students, and the students will use the materials to study.

[0332] Scoring tool

[0333] Step 1:

[0334] The server collects the response data submitted from the students' devices.

[0335] Step 2:

[0336] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[0337] Step 3:

[0338] The server calculates each student's score and generates grade data.

[0339] Step 4:

[0340] The server sends the grade data to the teacher's terminal.

[0341] Step 5:

[0342] Teachers check grades on their devices and provide feedback to students.

[0343] Learning support

[0344] Step 1:

[0345] The server periodically collects learning progress data from students' devices.

[0346] Step 2:

[0347] The server collects progress data, which is then input into an AI model for analysis.

[0348] Step 3:

[0349] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[0350] Step 4:

[0351] The server automatically generates supplementary materials and activities.

[0352] Step 5:

[0353] The server sends the generated supplementary materials to the teachers' and students' devices.

[0354] Step 6:

[0355] Teachers use their devices to review supplementary materials and provide instruction to students.

[0356] Learning progress analysis and suggestions

[0357] Step 1:

[0358] The server collects students' learning history and performance data.

[0359] Step 2:

[0360] The server inputs the collected data into an AI model for detailed analysis.

[0361] Step 3:

[0362] The AI ​​proposes the optimal learning approach based on the analysis results.

[0363] Step 4:

[0364] The server notifies the teacher's terminal of the proposed content.

[0365] Step 5:

[0366] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[0367] Creating an individualized education plan

[0368] Step 1:

[0369] The server collects data related to students' learning needs.

[0370] Step 2:

[0371] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[0372] Step 3:

[0373] The AI ​​optimizes the educational plans it generates.

[0374] Step 4:

[0375] The server sends optimized lesson plans to teachers' and students' devices.

[0376] Step 5:

[0377] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[0378] Suggestions for improving the education process

[0379] Step 1:

[0380] The server collects data about the entire school's educational process.

[0381] Step 2:

[0382] The server collects data, which is then input into an AI model for analysis.

[0383] Step 3:

[0384] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[0385] Step 4:

[0386] The server will notify teachers' terminals of the identified areas for improvement.

[0387] Step 5:

[0388] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[0389] Utilizing the Emotion Engine

[0390] Step 1:

[0391] The server activates the emotion engine to collect user emotion data.

[0392] Step 2:

[0393] The emotion engine analyzes the user's facial expressions and behavioral data to generate emotion data.

[0394] Step 3:

[0395] The server inputs the generated emotion data into the AI ​​model, which then adjusts the learning materials and activities.

[0396] Step 4:

[0397] The server sends the prepared teaching materials and activities to the teachers' and students' devices.

[0398] Step 5:

[0399] Teachers check the adjustments on their devices and provide guidance to students.

[0400] Stress management using emotional data

[0401] Step 1:

[0402] The server collects emotional data from students and teachers.

[0403] Step 2:

[0404] AI analyzes emotional data to detect signs of stress.

[0405] Step 3:

[0406] The server generates supplementary materials and relaxation activities to help with stress management.

[0407] Step 4:

[0408] The server sends the generated supplementary materials and activities to the teachers' and students' devices.

[0409] Step 5:

[0410] Teachers use their devices to check supplementary materials and activities and provide instruction.

[0411] (Example 2)

[0412] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0413] In the education sector, teacher shortages and a decline in the quality of education are serious problems. In particular, creating teaching materials tailored to the individual learning needs of students and providing appropriate feedback is difficult, which further contributes to the decline in quality. Furthermore, understanding the emotional states of students and teachers and responding appropriately based on that understanding is also challenging. A system is needed to solve these problems and improve the quality of education.

[0414] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0415] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, and means for transmitting the generated teaching materials to teachers' terminals. This enables the automatic generation and distribution of teaching materials based on the latest curriculum. It also includes means for generating teaching materials using an AI model and means for sending instructions to the generation AI model using prompt statements, thereby enabling the efficient creation of high-quality teaching materials and improving the quality of education. Furthermore, it includes means for collecting and analyzing student and teacher emotional data using an emotion engine, allowing for the adjustment of teaching materials and activities to maximize learning effectiveness based on the analysis results, thus contributing to the improvement of educational quality from an emotional perspective as well.

[0416] "Curriculum information" refers to information that includes teaching objectives, content, and evaluation criteria within the educational curriculum.

[0417] "Learning materials" refer to materials and tools that learners use for their studies, and include textbooks, workbooks, reference books, and digital learning materials.

[0418] A "terminal" refers to a device used by a user to interact with a system, and includes personal computers, tablets, smartphones, and other similar devices.

[0419] An "AI model" is a model that uses artificial intelligence algorithms to perform a specific task, and includes, for example, generative AI models and analytical AI models.

[0420] A "prompt message" is text data used to provide specific instructions or input information to a generative AI model.

[0421] "Response data" refers to the answers that learners submit to tests and assignments.

[0422] A "correct answer key" is a reference data that indicates the correct answer to a test or assignment, and is used for grading and performance evaluation.

[0423] "Learning progress data" refers to data that shows how far a learner has progressed in their studies, and includes study time, progress rate, and level of understanding.

[0424] An "emotion engine" is an artificial intelligence system designed to recognize and analyze a user's emotional state, and includes features such as facial recognition, voice analysis, and text analysis.

[0425] "Feedback" refers to evaluation results and suggestions for improvement provided to learners and teachers, with the aim of improving learning methods and comprehension.

[0426] An "activity" refers to a specific activity or exercise performed while progressing through learning, and includes problem-solving games and experiments.

[0427] This invention is a system designed to address teacher shortages and declining quality of education in educational settings, and operates primarily through servers, terminals, and users. Specifically, it operates by combining the following functions.

[0428] 1. Acquisition of curriculum information and automatic generation of teaching materials

[0429] The server accesses the curriculum database to retrieve the latest curriculum information. Based on this information, the server automatically generates teaching materials using a generative AI model (e.g., "GPT-4"). The generated teaching materials are sent from the server to the teacher's terminal. The teacher then uses that terminal to review the materials and distribute them to students.

[0430] Specific example:

[0431] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics" and sends the following prompt to the generating AI model to generate a set of problems on "Basic Algebra."

[0432] "Please create a workbook of basic algebra problems based on the curriculum for second-year junior high school mathematics."

[0433] 2. Scoring Tool

[0434] The server collects the answer data submitted by students from their devices and scores it by comparing it with the correct answer key. The correct answer key is stored in a database on the server. The scoring results are sent from the server to the teacher's device, where the teacher can check the grades and provide feedback to the students.

[0435] Specific example:

[0436] The server collects the answers to student A's math test and uses a generative AI model to grade them with the following prompt messages.

[0437] "Please compare Student A's answer with the correct answer key, grade it, and notify the teacher of the score." The result is a score of 90 points, which is then notified to the teacher.

[0438] 3. Learning support

[0439] The server periodically collects learning progress data from students' devices and analyzes it using a generative AI model. This identifies areas where students are particularly struggling and generates supplementary materials and activities. These are then sent to both teachers' and students' devices.

[0440] Specific example:

[0441] The server analyzes student B's progress data and uses a generating AI model to send the following prompt message, thereby generating "additional problems for solving word problems."

[0442] "Analyze student B's progress data and generate supplementary materials to address their weak areas." The teacher checks this on their device and provides instruction to the student.

[0443] 4. Analysis of learning progress and recommendations

[0444] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. Based on the analysis results, the optimal learning approach is proposed and notified to the teacher's terminal. The teacher adjusts the lesson content based on this proposal.

[0445] Specific example:

[0446] The server analyzes student C's math learning history and suggests that "lessons that heavily utilize visual aids" would be effective. This suggestion is sent to the teacher's terminal with the following prompt message.

[0447] "Analyze student C's learning history and propose the optimal learning approach."

[0448] 5. Creating an Individualized Education Plan

[0449] The server collects student learning needs data and uses a generative AI model to generate and optimize individualized learning plans. The optimized plans are sent to the teacher's and student's devices. Teachers review the plans and provide appropriate instruction to students.

[0450] Specific example:

[0451] The server analyzes student D's learning needs and generates a "reading and writing support program" by sending the following prompt message using a generative AI model.

[0452] "Generate and optimize an individualized learning plan based on student D's learning needs." The teacher will then provide appropriate instruction based on this plan.

[0453] 6. Suggestions for improving the educational process

[0454] The server collects data on the school's overall educational process and analyzes it using a generative AI model. Based on the data, it identifies areas for improvement in the educational process and curriculum, and notifies teachers of these improvements on their terminals. Teachers then revise their educational processes and curriculum based on the suggestions they receive.

[0455] Specific example:

[0456] The server analyzes the school-wide lesson evaluation data and sends the following prompt message using a generative AI model.

[0457] "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum." As a result, "increasing reading and writing time" is suggested and communicated to the teachers.

[0458] 7. Utilizing the Emotional Engine

[0459] The server includes an emotion engine that recognizes user emotions. User emotion data is collected on the server and analyzed by the emotion engine. Based on the user's emotion data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials or relaxation activities.

[0460] Specific example:

[0461] The server collects student E's emotional data and uses the emotional engine to send the following prompt message.

[0462] "Analyze student E's emotional data and suggest relaxation exercises to reduce stress." The teacher will then use this suggestion to instruct the student on additional relaxation activities.

[0463] 8. Utilization of teacher sentiment data

[0464] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[0465] Specific example:

[0466] The server collects teacher F's emotional data and uses the emotion engine to send the following prompt message.

[0467] "Analyze teacher F's emotional data and propose approaches to reduce their workload." Based on these proposals, the teacher will distribute tasks and reduce stress.

[0468] As described above, the system of the present invention not only alleviates the shortage of teachers in educational settings and improves the quality of education, but also makes it possible to provide optimal learning and guidance by utilizing emotional data of students and teachers.

[0469] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0470] Automated creation of educational materials

[0471] Step 1:

[0472] The server accesses the curriculum database.

[0473] input:

[0474] Request to access the curriculum database

[0475] Data processing:

[0476] Execute a query to extract curriculum information.

[0477] output:

[0478] Latest curriculum information

[0479] Specific actions:

[0480] The server sends a query to the curriculum database with the condition "Junior High School 2nd Year Mathematics" and retrieves the corresponding curriculum information.

[0481] Step 2:

[0482] The server inputs the acquired curriculum information into a generating AI model.

[0483] input:

[0484] Latest curriculum information

[0485] Data processing:

[0486] Convert curriculum information into prompt messages

[0487] output:

[0488] Instruction prompts for the AI ​​model

[0489] Specific actions:

[0490] The server generates a prompt message, "Generate a set of problems on the basics of algebra based on the curriculum for second-year junior high school mathematics," and sends it to the AI ​​model.

[0491] Step 3:

[0492] The AI ​​model automatically generates educational materials.

[0493] input:

[0494] Instruction prompt message

[0495] Data processing:

[0496] Creating educational materials using generative AI models

[0497] output:

[0498] Automatically generated teaching materials

[0499] Specific actions:

[0500] A generative AI model (e.g., GPT-4) generates a set of problems on fundamental algebraic concepts based on a prompt.

[0501] Step 4:

[0502] The server sends the generated teaching materials to the teacher's terminal.

[0503] input:

[0504] Automatically generated teaching materials

[0505] Data processing:

[0506] Preparing to send teaching material data

[0507] output:

[0508] Sending teaching materials data to teachers' devices

[0509] Specific actions:

[0510] The server converts the generated teaching materials into PDF format and sends them to the teacher's terminal.

[0511] Scoring tool

[0512] Step 1:

[0513] Students submit their answers to the server from their devices.

[0514] input:

[0515] Student response data

[0516] Data processing:

[0517] Collection of response data

[0518] output:

[0519] Response data sent to the server

[0520] Specific actions:

[0521] The student clicks the "end" button on the online test, and the answer data is uploaded to the server.

[0522] Step 2:

[0523] The server compares the response data with the correct key.

[0524] input:

[0525] Student response data, correct answer key

[0526] Data processing:

[0527] Scoring by comparison

[0528] output:

[0529] Scoring results

[0530] Specific actions:

[0531] The server compares student A's answer data with the correct answer key previously stored in the database and calculates the score.

[0532] Step 3:

[0533] The server notifies the teacher's terminal of the grading results as grades.

[0534] input:

[0535] Scoring results

[0536] Data processing:

[0537] Preparing to send result data

[0538] output:

[0539] Grade notification to the teacher's device

[0540] Specific actions:

[0541] The server notifies teachers of the grading results in real time on their terminals, allowing teachers to review them and provide feedback to students.

[0542] Learning support

[0543] Step 1:

[0544] Students' devices send learning progress data to the server.

[0545] input:

[0546] Student learning progress data

[0547] Data processing:

[0548] Collection of progress data

[0549] output:

[0550] Progress data sent to the server

[0551] Specific actions:

[0552] Students record their daily learning progress using a learning app, and this information is automatically sent to a server.

[0553] Step 2:

[0554] The server inputs progress data into the AI ​​model.

[0555] input:

[0556] Student learning progress data

[0557] Data processing:

[0558] Generating prompts for analyzing progress data

[0559] output:

[0560] Analysis prompts for AI models

[0561] Specific actions:

[0562] The server generates a prompt message saying, "Analyze student B's progress data and generate supplementary materials to address their weak areas," and sends it to the AI ​​model.

[0563] Step 3:

[0564] The generative AI model generates supplementary materials and activities.

[0565] input:

[0566] Analysis prompt message

[0567] Data processing:

[0568] Generating supplementary materials and activities

[0569] output:

[0570] Supplementary materials and activities that are generated

[0571] Specific actions:

[0572] The generative AI model generates "additional problems for solving word problems" based on the prompt text.

[0573] Step 4:

[0574] The server sends the generated supplementary materials to the teachers' and students' devices.

[0575] input:

[0576] Supplementary materials and activities that are generated

[0577] Data processing:

[0578] Preparing to send teaching material data

[0579] output:

[0580] Sending teaching materials data to teachers' and students' devices

[0581] Specific actions:

[0582] The server converts supplementary materials into PDF format and sends them to the teacher's and students' devices. The teacher reviews them and provides instruction to the students.

[0583] Learning progress analysis and suggestions

[0584] Step 1:

[0585] The server collects students' learning history and performance data.

[0586] input:

[0587] Student learning history and performance data

[0588] Data processing:

[0589] Data collection

[0590] output:

[0591] Learning history and performance data collected on the server

[0592] Specific actions:

[0593] The server periodically collects student C's math learning data for the past six months.

[0594] Step 2:

[0595] The server inputs the learning history and performance data into the generated AI model.

[0596] input:

[0597] Student learning history and performance data

[0598] Data processing:

[0599] Generating prompts for analysis

[0600] output:

[0601] Analysis prompts for AI models

[0602] Specific actions:

[0603] The server generates a prompt message saying, "Analyze student C's learning history and suggest the optimal learning approach," and sends it to the AI ​​model.

[0604] Step 3:

[0605] Generative AI models analyze data in detail and propose the optimal learning approach.

[0606] input:

[0607] Analysis prompt message

[0608] Data processing:

[0609] Generating learning approach proposals

[0610] output:

[0611] Proposal details

[0612] Specific actions:

[0613] The generative AI model analyzes student C's data and generates a suggestion that "lessons that heavily utilize visual aids" are effective.

[0614] Step 4:

[0615] The server sends the proposal to the teacher's terminal.

[0616] input:

[0617] Proposal details

[0618] Data processing:

[0619] Preparing to send proposal data

[0620] output:

[0621] Sending proposal content to the teacher's terminal

[0622] Specific actions:

[0623] The server sends the proposed content to the teacher's terminal, and the teacher adjusts the lesson content to make extensive use of visual aids.

[0624] Creating an individualized education plan

[0625] Step 1:

[0626] Student devices send learning needs data to the server.

[0627] input:

[0628] Student learning needs data

[0629] Data processing:

[0630] Collection of needs data

[0631] output:

[0632] Needs data sent to the server

[0633] Specific actions:

[0634] Students record their special learning needs, and this information is sent to a server.

[0635] Step 2:

[0636] The server generates learning needs data and inputs it into the AI ​​model.

[0637] input:

[0638] Student learning needs data

[0639] Data processing:

[0640] Prompt message generation for plan generation

[0641] output:

[0642] Prompt for generating a plan for the AI ​​model

[0643] Specific actions:

[0644] The server generates a prompt message, "Generate and optimize an individualized learning plan based on student D's learning needs," and sends it to the AI ​​model.

[0645] Step 3:

[0646] The generative AI model generates and optimizes individualized educational plans.

[0647] input:

[0648] Plan generation prompt message

[0649] Data processing:

[0650] Generating and optimizing individualized education plans

[0651] output:

[0652] Generated Individual Education Plan

[0653] Specific actions:

[0654] The generative AI model generates and optimizes a "reading and writing support program" based on student D's data.

[0655] Step 4:

[0656] The server sends the generated individualized education plans to the teachers' and students' devices.

[0657] input:

[0658] Generated Individual Education Plan

[0659] Data processing:

[0660] Preparing to send plan data

[0661] output:

[0662] Sending plan data to teachers' and students' devices

[0663] Specific actions:

[0664] The server converts the generated lesson plan into PDF format and sends it to the teacher's and student's devices. The teacher then provides appropriate instruction based on the plan.

[0665] Suggestions for improving the education process

[0666] Step 1:

[0667] The server collects data about the entire school's educational process.

[0668] input:

[0669] Educational process data

[0670] Data processing:

[0671] Data collection

[0672] output:

[0673] Educational process data collected on the server

[0674] Specific actions:

[0675] The server collects school-wide lesson evaluation survey data.

[0676] Step 2:

[0677] The server inputs educational process data into the AI ​​model.

[0678] input:

[0679] Educational process data

[0680] Data processing:

[0681] Generating prompt messages for improvement suggestions

[0682] output:

[0683] Prompt for suggesting improvements to the AI ​​model

[0684] Specific actions:

[0685] The server generates a prompt message that reads, "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum," and sends it to the AI ​​model.

[0686] Step 3:

[0687] The generative AI model analyzes data and suggests improvements to the educational process and curriculum.

[0688] input:

[0689] Improvement suggestion prompt message

[0690] Data processing:

[0691] Generating proposals for educational improvement

[0692] output:

[0693] Improvement proposal details

[0694] Specific actions:

[0695] The generative AI model analyzes the data and generates suggestions such as "increase reading and writing time."

[0696] Step 4:

[0697] The server sends the improvement suggestions to the teacher's terminal.

[0698] input:

[0699] Improvement proposal details

[0700] Data processing:

[0701] Preparing to send improvement suggestion data

[0702] output:

[0703] Sending proposal content to the teacher's terminal

[0704] Specific actions:

[0705] The server sends the proposal to the teacher's terminal, and the teacher adjusts the curriculum timetable to increase reading and writing time.

[0706] Utilizing the Emotion Engine

[0707] Step 1:

[0708] The user's device sends emotional data to the server.

[0709] input:

[0710] User sentiment data

[0711] Data processing:

[0712] Collection of emotional data

[0713] output:

[0714] Emotional data sent to the server

[0715] Specific actions:

[0716] The user records their emotional state on their device, and that information is sent to the server.

[0717] Step 2:

[0718] The server inputs emotional data into the emotion engine.

[0719] input:

[0720] Emotional data

[0721] Data processing:

[0722] Analysis of emotional data

[0723] output:

[0724] Analysis results regarding emotional state

[0725] Specific actions:

[0726] The server inputs emotional data into the emotion engine, which then performs analysis.

[0727] Step 3:

[0728] The emotion engine analyzes emotional data and adjusts supplementary materials and activities accordingly.

[0729] input:

[0730] Analysis results regarding emotional state

[0731] Data processing:

[0732] Adjusting teaching materials and activities

[0733] output:

[0734] Customized teaching materials and activities

[0735] Specific actions:

[0736] The emotion engine analyzes student E's data and suggests "relaxation exercises" if it detects a high stress level.

[0737] Step 4:

[0738] The server sends the adjusted learning materials and activities to the user.

[0739] input:

[0740] Customized teaching materials and activities

[0741] Data processing:

[0742] Preparing to send teaching material data

[0743] output:

[0744] Sending educational material data to the user's device

[0745] Specific actions:

[0746] The server sends the suggested content to the teacher's and student's devices, and the teacher then instructs them on relaxation activities.

[0747] Utilizing teacher sentiment data

[0748] Step 1:

[0749] Teachers send emotional data from their devices to the server.

[0750] input:

[0751] Teacher sentiment data

[0752] Data processing:

[0753] Collection of emotional data

[0754] output:

[0755] Emotional data sent to the server

[0756] Specific actions:

[0757] Teachers record their emotional state, and this information is sent to a server.

[0758] Step 2:

[0759] The server inputs emotional data into the emotion engine.

[0760] input:

[0761] Teacher sentiment data

[0762] Data processing:

[0763] Analysis of emotional data

[0764] output:

[0765] Analysis results regarding emotional state

[0766] Specific actions:

[0767] The server inputs emotional data into the emotion engine, which then performs analysis.

[0768] Step 3:

[0769] The emotion engine analyzes emotional data and generates stress management suggestions.

[0770] input:

[0771] Analysis results regarding emotional state

[0772] Data processing:

[0773] Generating stress management proposals

[0774] output:

[0775] Generated stress management proposals

[0776] Specific actions:

[0777] The emotion engine analyzes teacher F's data and generates suggestions for "dividing the workload."

[0778] Step 4:

[0779] The server sends the proposal to the teacher's terminal.

[0780] input:

[0781] Generated stress management proposals

[0782] Data processing:

[0783] Preparing to send proposal data

[0784] output:

[0785] Sending proposal content to the teacher's terminal

[0786] Specific actions:

[0787] The server sends the proposed content to the teachers' terminals, and based on the proposals, tasks are divided and stress is reduced.

[0788] Through the above processing steps, the system of the present invention alleviates the shortage of teachers in educational settings, improves the quality of education, and provides optimal learning and guidance by utilizing emotional data.

[0789] (Application Example 2)

[0790] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0791] Teacher shortages and declining quality of education are significant challenges in the modern educational environment. Efficient training and education of new operators in factories are also crucial. Traditional methods place an excessive burden on teachers and trainers, risking a decline in the quality of education. Furthermore, inadequate stress management among operators makes effective training difficult. This invention provides a system to solve these problems.

[0792] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0793] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, means for transmitting the generated teaching materials to a teacher's terminal, means for automatically generating training materials based on factory operating procedures and safety guidelines, means for providing the generated training materials to an operator's terminal, means for collecting operator progress data and emotional data, and means for analyzing the progress data and emotional data and suggesting relaxation exercises if stress is detected. This makes it possible to alleviate teacher shortages and the decline in the quality of education, as well as manage operator stress.

[0794] "Curriculum information" refers to information about learning content and teaching policies established for educational purposes.

[0795] "Educational materials" refer to materials and content used to achieve specific educational objectives.

[0796] A "terminal" is a device used to communicate with a server and receive information.

[0797] "Operating procedures" refer to the steps and methods for correctly performing tasks and operations in a factory.

[0798] "Safety guidelines" are standards and guidelines for performing work safely within a factory.

[0799] "Training materials" are educational materials used to acquire specific skills or knowledge.

[0800] An "operator" is a worker who operates machinery and equipment in a factory or work site.

[0801] "Progress data" refers to information about the progress of learning or work.

[0802] "Emotional data" refers to information about an individual's emotional state.

[0803] "Relaxation exercise" refers to activities and movements designed to reduce stress and promote mental and physical relaxation.

[0804] "Outcome data" refers to information about grades and performance obtained as a result of education or training.

[0805] "Stress" refers to a reaction or state of tension to physical, psychological, or environmental factors.

[0806] "Feedback" refers to evaluations and advice given regarding the results of learning or work.

[0807] "Educational methods" refer to the methods and means used to effectively carry out educational activities.

[0808] This invention is a system that combines educational support AI, educational data analysis AI, and an emotion engine to address teacher shortages and declining quality of education in educational settings. It can also be applied to training and educational support for new operators in factories. The following provides a detailed description of the system that realizes this application.

[0809] Hardware configuration

[0810] server:

[0811] The server plays a central role in managing curriculum information, factory operating procedures, and safety guidelines, and in automatically generating educational materials. It also includes a database for collecting and analyzing student and operator progress and sentiment data.

[0812] Terminal:

[0813] The devices include tablets and personal computers for teachers and operators. These devices are used to receive generated teaching materials and feedback.

[0814] Emotion sensor:

[0815] The emotion sensor is a sensor used to collect emotional data from operators and students. This allows for appropriate responses if stress is detected.

[0816] Software Configuration

[0817] Educational support AI:

[0818] The educational support AI automatically generates teaching materials and training materials based on curriculum information and factory operating procedures. The generated materials are then sent to the terminals of teachers and operators.

[0819] AI for educational data analysis:

[0820] The educational data analysis AI analyzes progress and performance data from students and operators. This allows it to identify learning trends and areas of weakness, and then suggest optimal teaching methods and supplementary materials.

[0821] Emotional engine:

[0822] The emotion engine collects and analyzes emotional data from students and operators. Based on this, if stress is detected, it suggests relaxation exercises or other responses.

[0823] Processing flow

[0824] 1. Automated creation of educational materials:

[0825] The server retrieves curriculum information, factory operating procedures, and safety guidelines, and uses educational support AI to automatically generate teaching materials and training materials.

[0826] 2. Provision of generated teaching materials:

[0827] The generated teaching materials and training materials are sent to terminals for instructors and operators and provided to users.

[0828] 3. Collection and analysis of progress data and sentiment data:

[0829] The server collects progress and emotional data from students and operators, and analyzes it using educational data analysis AI and an emotional engine.

[0830] 4. Feedback and suggestions for additional materials:

[0831] Based on the analysis results, optimal teaching methods and supplementary materials are suggested and sent to terminals for teachers and operators. If stress is detected, relaxation exercises are suggested.

[0832] Specific example

[0833] For example, if a factory robot is training a new operator on "wiring a power distribution panel," the robot automatically generates training materials based on operating procedures and safety guidelines and provides them to the operator's tablet. Once the operator completes the training, the robot collects progress data and emotional data and sends it to a server. An AI for analyzing educational data evaluates the progress, and an emotional engine determines whether or not stress is present. Additional supplementary materials or relaxation exercises are suggested as needed.

[0834] Example of a prompt

[0835] "Automatically generate training materials for new operators to learn how to wire distribution panels. Also, analyze training progress and operator emotional data, and suggest necessary additional materials and relaxation exercises."

[0836] This system will help address teacher shortages and the decline in the quality of education, as well as enable efficient training and stress management for operators.

[0837] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0838] Step 1:

[0839] The server retrieves curriculum information, factory operating procedures, and safety guidelines. This information is collected as input data and used in the following steps.

[0840] Input: Curriculum information, operating procedures, safety guidelines

[0841] Output: Acquired curriculum information and guideline data

[0842] Step 2:

[0843] The educational support AI automatically generates teaching materials and training materials based on the curriculum information and operating procedures acquired in the previous step. The generated materials are diverse and include text, video, and interactive content.

[0844] Input: Curriculum information, operating procedures, safety guidelines

[0845] Data processing: Generating educational materials using AI models.

[0846] Output: Generated teaching materials, training materials

[0847] Step 3:

[0848] The generated teaching materials and training materials are sent to terminals for instructors and operators. Users can then view these materials on their terminals and conduct their learning or training.

[0849] Input: Generated teaching materials, training materials

[0850] Output: Provided teaching materials and training materials (on the device)

[0851] Specific operation: Sending data from the server to the terminal.

[0852] Step 4:

[0853] Users perform training and learning using their devices, and progress data and emotional data are collected. Data is collected from emotional sensors, usage logs, test results, etc.

[0854] Input: User's action progress, sentiment data

[0855] Output: Progress data, sentiment data (sent to the server)

[0856] Specific actions: Real-time collection of progress and sentiment data.

[0857] Step 5:

[0858] The server passes the collected progress and emotional data to the educational data analysis AI and emotion engine for analysis. This analysis includes identifying areas of difficulty and stress levels.

[0859] Input: Progress data, sentiment data

[0860] Data processing: AI-based progress analysis and sentiment analysis.

[0861] Output: Analysis results (issue areas, stress levels, etc.)

[0862] Step 6:

[0863] The educational data analysis AI generates supplementary materials and activities based on the progress analysis results, and the server sends the generated supplementary materials and relaxation exercises to terminals for teachers and operators.

[0864] Input: Progress analysis results, city situation analysis results

[0865] Data processing: Generation of supplementary materials and relaxation exercises.

[0866] Output: Generated supplementary materials, relaxation exercises (sent to the device)

[0867] Specific operation: Sending additional learning materials from the server to the terminal.

[0868] Step 7:

[0869] Teachers and operators can access and apply supplementary materials and relaxation exercises on their devices. This helps improve comprehension and reduce stress.

[0870] Input: Supplementary materials, relaxation exercises

[0871] Output: Application results (user progress and emotional changes)

[0872] Specific actions: The user completes the instructed learning materials and exercises.

[0873] Through the steps described above, the system of this invention can achieve effective educational support, operator training, and stress management.

[0874] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0875] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0876] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0877] [Second Embodiment]

[0878] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0879] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0880] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0881] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0882] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0883] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0884] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0885] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0886] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0887] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0888] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0889] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0890] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade response data and notify teachers of their grades on their terminals, to analyze students' learning progress data and provide supplementary materials and activities, to analyze individual students' learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[0891] 1. Automated creation of educational materials

[0892] The server retrieves the latest curriculum information from the curriculum database and automatically generates teaching materials based on that information. For example, the server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra." The server then sends the generated teaching materials to the teacher's terminal, and the teacher distributes the materials to the students.

[0893] 2. Scoring Tool

[0894] The server collects answer data submitted from students' devices and scores it by comparing it to the correct answer key. For example, the server collects answer data for a math test, and the AI ​​compares it to the correct answer key and scores it at 90 points. The result is then notified to the teacher's device as grade data, and the teacher can check the grade.

[0895] 3. Learning support

[0896] The server periodically collects student learning progress data, and AI analyzes this data. It identifies students' learning trends and areas where they are lacking, and generates supplementary materials and activities. For example, the server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[0897] 4. Analysis of learning progress and recommendations

[0898] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, it proposes the optimal learning approach and notifies the teacher of the proposal on their terminal. For example, the server collects student C's math learning history and suggests that "lessons using a lot of visual aids" would be effective, and notifies the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[0899] 5. Creating an Individualized Education Plan

[0900] The server collects data on students' learning needs, and AI generates individualized educational plans based on that data. The generated plans are then optimized and sent to the teacher's and student's devices. For example, the server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[0901] 6. Suggestions for improving the educational process

[0902] The server collects data on the educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and creates detailed improvement suggestions. These suggestions are then notified to teachers' terminals, and teachers consider them. For example, the server analyzes school-wide lesson evaluation data and suggests "increasing reading and writing time," and notifies teachers of this suggestion. Teachers then adjust their lesson content based on the suggestion.

[0903] This invention reduces the workload of teachers while simultaneously providing optimal educational support to each student, thereby improving the overall quality of the educational environment.

[0904] The following describes the processing flow.

[0905] Automated creation of educational materials

[0906] Step 1:

[0907] The server accesses the curriculum database to retrieve the latest curriculum information.

[0908] Step 2:

[0909] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[0910] Step 3:

[0911] The server sends the generated teaching material data to the teacher's terminal.

[0912] Step 4:

[0913] The teacher receives the teaching materials on a device and checks their contents.

[0914] Step 5:

[0915] The teacher distributes teaching materials to the students, and the students use the materials to study.

[0916] Scoring tool

[0917] Step 1:

[0918] The server collects the response data submitted from the students' devices.

[0919] Step 2:

[0920] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[0921] Step 3:

[0922] The server calculates each student's score and generates grade data.

[0923] Step 4:

[0924] The server sends the grade data to the teacher's terminal.

[0925] Step 5:

[0926] Teachers check grades on their devices and provide feedback to students.

[0927] Learning support

[0928] Step 1:

[0929] The server periodically collects learning progress data from students' devices.

[0930] Step 2:

[0931] The server collects progress data, which is then input into an AI model for analysis.

[0932] Step 3:

[0933] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[0934] Step 4:

[0935] The server automatically generates supplementary materials and activities.

[0936] Step 5:

[0937] The server sends the generated supplementary materials to the teachers' and students' devices.

[0938] Step 6:

[0939] Teachers use their devices to review supplementary materials and provide instruction to students.

[0940] Learning progress analysis and suggestions

[0941] Step 1:

[0942] The server collects students' learning history and performance data.

[0943] Step 2:

[0944] The server inputs the collected data into an AI model for detailed analysis.

[0945] Step 3:

[0946] The AI ​​identifies the optimal learning approach based on the analysis results.

[0947] Step 4:

[0948] The server notifies the teacher's terminal of the proposed content.

[0949] Step 5:

[0950] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[0951] Creating an individualized education plan

[0952] Step 1:

[0953] The server collects data related to students' learning needs.

[0954] Step 2:

[0955] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[0956] Step 3:

[0957] The AI ​​optimizes the educational plans it generates.

[0958] Step 4:

[0959] The server sends optimized lesson plans to teachers' and students' devices.

[0960] Step 5:

[0961] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[0962] Suggestions for improving the education process

[0963] Step 1:

[0964] The server collects data about the entire school's educational process.

[0965] Step 2:

[0966] The server collects data, which is then input into an AI model for analysis.

[0967] Step 3:

[0968] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[0969] Step 4:

[0970] The server will notify teachers' terminals of the identified areas for improvement.

[0971] Step 5:

[0972] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[0973] (Example 1)

[0974] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0975] In today's education system, teacher shortages and a decline in the quality of education are serious problems. In addition, providing individualized instruction to each student and preparing diverse teaching materials is often difficult. As a result, education is becoming more homogenized, and the individual learning needs of students cannot be met. To solve these problems, effective and efficient creation and distribution of teaching materials, automated grading, and individualized instruction based on students' progress are required.

[0976] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0977] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials using a generation AI model based on the curriculum information, means for sending prompt messages to the generation AI model to generate teaching materials, and means for transmitting the generated teaching materials to the teacher's information terminal. This reduces the workload of teachers and enables optimal educational support tailored to the learning needs of each student.

[0978] "Curriculum information" refers to educational data that includes detailed information such as the content of lessons, learning objectives, teaching materials, and progress schedules set by educational institutions.

[0979] A "generative AI model" is an artificial intelligence technique that learns from large amounts of data and automatically generates educational materials and problem sets according to specific instructions.

[0980] A "prompt message" is text data used to give specific instructions to a generative AI model, and it plays a role in prompting the generation of educational materials and problem sets.

[0981] "Teaching materials" refer to educational materials used to support students' learning, and include textbooks, workbooks, supplementary materials, and other similar items.

[0982] "Teacher information terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers that are capable of sending and receiving data via email and applications.

[0983] "Student learning progress data" refers to data that shows the results, evaluations, level of understanding, and progress that students have achieved during the learning process, and is important information for understanding the progress of learning based on this data.

[0984] A "correct answer key" is a standard set of answers that indicates the correct answers in tests and workbooks, and serves as a standard for evaluating and grading learning.

[0985] "Grades" are numerical values ​​or evaluations that quantitatively show academic achievement, and are calculated based on factors such as test results and evaluations of submitted work.

[0986] "Supplementary materials" are educational resources added to deepen understanding of existing materials, and include additional problems, exercises, and activities.

[0987] An "activity" is a practical activity or exercise designed to support students' learning and to reinforce the learning content.

[0988] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade student response data and notify teachers of their grades on their terminals, to analyze student learning progress data and provide supplementary materials and activities, to analyze individual student learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[0989] The basic configuration of the system is as follows:

[0990] 1. Automatic generation and distribution of educational materials

[0991] The server connects to the educational institution's curriculum database and retrieves the latest curriculum information. Based on this curriculum information, it automatically generates teaching materials using a generative AI model. Specifically, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics" and sends a prompt message to the generative AI model saying, "Please generate a basic algebra problem set for Junior High School 2nd Year Mathematics." The generated teaching materials are sent to the teacher's terminal in PDF or link format, and the teacher reviews the received materials and distributes them to students.

[0992] 2. Automated scoring and grade notification

[0993] The server collects answer data submitted from students' devices. Based on this data, a generative AI model is used to match it with the correct answer key and perform automatic scoring. For example, the server receives answer data for a math test and sends a prompt message to the generative AI model saying, "Please score the math test answer data." The generative AI model calculates a score for each answer and notifies the teacher's device of the result. The teacher then reviews the score and provides feedback to the students.

[0994] 3. Learning support functions

[0995] The server periodically collects learning progress data from students' devices. This data is analyzed by a generative AI model to identify learning trends and areas where students are lacking. For example, a prompt message such as "Generate supplementary materials based on student B's learning progress data" is sent to the generative AI model, which then generates additional practice problems and materials. The generated materials are sent to the teacher's and student's devices, and the teacher uses them to provide instruction.

[0996] 4. Analysis and suggestions regarding learning progress

[0997] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. This provides a function to suggest the optimal learning approach. For example, the server might send a prompt to the generative AI model saying, "Suggest the optimal learning approach based on student C's learning history," and the generative AI model might suggest a lesson that makes extensive use of visual aids. This suggestion is then notified to the teacher's terminal, and the teacher can incorporate it into their teaching methods.

[0998] 5. Creating an Individualized Education Plan

[0999] The server collects student learning needs data and uses a generative AI model to generate individualized learning plans. For example, it might send a prompt message to the generative AI model saying, "Generate an individualized learning plan based on student D's learning needs data." The generated plan is optimized and sent to the teacher's and student's devices. The teacher then uses the plan to provide appropriate instruction.

[1000] 6. Suggestions for improving the educational process

[1001] The server collects data on the educational process and analyzes it using a generative AI model. Based on this, it creates suggestions for improving the educational process and curriculum. For example, it might send a prompt message to the generative AI model such as, "Please suggest improvements to the curriculum based on school-wide lesson evaluation data," to identify areas for improvement and generate suggestions. These suggestions are then notified to teachers' terminals and used by teachers to adjust lesson content.

[1002] As described above, the present invention, by utilizing a generated AI model and prompt text, can reduce the workload of teachers in educational settings and provide optimal educational support to each student. This makes it possible to improve the quality of education.

[1003] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1004] Step 1: Obtain curriculum information

[1005] Server: Connects to the curriculum database and retrieves the latest curriculum information. As a specific example, it retrieves curriculum information for "Junior High School 2nd Year Mathematics" from the database.

[1006] Input: Target grade and subject (e.g., 2nd year of junior high school, mathematics)

[1007] Output: Curriculum information (e.g., Fundamentals of Algebra, Fundamentals of Geometry)

[1008] Step 2: Sending prompts to the generative AI model

[1009] Server: Based on the acquired curriculum information, it sends appropriate prompts to the generating AI model. For example, it sends the prompt, "Please generate a basic algebra problem set for 2nd year junior high school mathematics."

[1010] Input: Curriculum information (e.g., Basic Algebra)

[1011] Output: Prompt message (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[1012] Step 3: Generating the teaching materials

[1013] Generative AI Model: Automatically generates educational materials based on the submitted prompt text. As a specific example, it generates a set of problems related to "Basic Algebra."

[1014] Input: Prompt text (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[1015] Output: Generated learning materials (e.g., a workbook in PDF format)

[1016] Step 4: Send the generated materials

[1017] Server: Sends the generated teaching materials to the teacher's terminal. For example, it sends a PDF file to the teacher's email address.

[1018] Input: Generated learning materials (e.g., a workbook in PDF format)

[1019] Output: Notification to the teacher's terminal and transmission of teaching materials (e.g., email transmission)

[1020] Step 5: Collecting response data

[1021] Server: Collects response data submitted from students' devices. For example, it retrieves response data submitted by students from an online testing platform.

[1022] Input: Student response data (e.g., response data in JSON format)

[1023] Output: Saving collected response data (e.g., storing in a database)

[1024] Step 6: Scoring of response data

[1025] Server: Using an AI model, the server automatically scores collected answer data by comparing it to the correct answer key. For example, it calculates the score for each question in a math test by comparing it to the correct answer key.

[1026] Input: Collected response data and correct answer key (e.g., response data in JSON format and answer set)

[1027] Output: Graded performance data (e.g., CSV file containing graded results)

[1028] Step 7: Notification of Grades

[1029] Server: Notifies teachers of grading results on their terminals. For example, it might compile the grading results into an Excel file and send it to the teacher's email address.

[1030] Input: Graded grade data (e.g., a CSV file containing graded results)

[1031] Output: Notification to the teacher's terminal and transmission of grade data (e.g., email transmission)

[1032] Step 8: Collecting learning progress data

[1033] Server: Regularly collects learning progress data from students' devices. For example, it saves students' daily learning logs to a cloud server.

[1034] Input: Student learning progress data (e.g., learning log data)

[1035] Output: Saving collected learning progress data (e.g., storing in a database)

[1036] Step 9: Analyze learning progress data

[1037] Server: Uses a generative AI model to analyze collected learning progress data. Specifically, it detects learning trends and areas of weakness in specific subjects or fields.

[1038] Input: Collected learning progress data (e.g., learning log data)

[1039] Output: Analysis results (e.g., identification of areas with deficiencies)

[1040] Step 10: Generating supplementary materials and activities

[1041] Server: Based on the analysis results, it sends prompt messages to the generating AI model to generate supplementary materials and activities. For example, it sends the prompt message, "Please generate additional problems for solving word problems."

[1042] Input: Analysis results and prompt message (e.g., "Generate teaching materials to cover the missing sections")

[1043] Output: Generated supplementary materials (e.g., PDF file of practice problems)

[1044] Step 11: Sending supplementary materials

[1045] Server: Sends the generated supplementary materials to the teacher's and students' devices. For example, it sends a link to practice problems via email.

[1046] Input: Generated supplementary materials (e.g., PDF file of practice problems)

[1047] Output: Notifications to teacher and student devices and delivery of educational materials (e.g., email).

[1048] Step 12: Collecting Learning History

[1049] Server: Regularly collects students' learning history and performance data. Specifically, it collects students' test results and classroom performance data.

[1050] Input: Student learning history and performance data (e.g., test result data)

[1051] Output: Storage of collected learning history and performance data (e.g., storage in a database)

[1052] Step 13: Proposing a Learning Approach

[1053] Server: Using a generative AI model, it analyzes learning history and performance data in detail to propose the optimal learning approach. For example, it might generate a suggestion that "lessons that heavily utilize visual materials are effective."

[1054] Input: Learning history and performance data (e.g., test result data)

[1055] Output: Proposal of the optimal learning approach (e.g., a report including the proposal)

[1056] Step 14: Notification of Proposal

[1057] Server: Notifies the instructor's terminal of the proposed content. For example, it sends a report containing the proposed content via email in PDF format.

[1058] Input: Proposal of the optimal learning approach (e.g., a report including the proposed approach)

[1059] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[1060] Step 15: Collecting Educational Process Data

[1061] Server: Collects data related to the educational process. Specifically, it regularly collects lesson evaluation data and teacher feedback.

[1062] Input: Educational process data (e.g., course evaluation data)

[1063] Output: Storage of collected educational process data (e.g., storage in a database)

[1064] Step 16: Create proposals for improving the educational process.

[1065] Server: Uses a generative AI model to analyze collected educational process data and generate specific improvement suggestions. For example, it generates a suggestion to "increase reading and writing time."

[1066] Input: Analysis results of educational process data (e.g., analysis results of lesson evaluation data)

[1067] Output: Improvement suggestions (e.g., a report including the suggested content)

[1068] Step 17: Notification of improvement suggestions

[1069] Server: Notifies teachers of the created improvement suggestions on their terminals. For example, it sends a report containing the suggestions via email in PDF format.

[1070] Input: Improvement suggestion (e.g., a report including the suggestion)

[1071] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[1072] The above processing steps represent the specific operational flow of this system. This will reduce the workload of teachers and enable the provision of optimal educational support to each individual student.

[1073] (Application Example 1)

[1074] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1075] In recent years, teacher shortages and a decline in the quality of education have become serious problems in the education sector. This problem significantly impacts educational effectiveness, particularly because it makes it difficult to provide detailed, individualized instruction to each student. Furthermore, providing learning materials and plans tailored to individual learning needs is challenging, and conventional educational support systems require more efficient solutions. Additionally, improving the quality of educational content sales and user experience in virtual stores presents significant challenges.

[1076] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1077] In this invention, the server includes means for acquiring curriculum information, means for generating educational content based on the curriculum information, means for transmitting the generated educational content to a terminal, means for recommending educational content based on the user's learning history, means for collecting user learning progress data and tracking progress, and means for generating individualized educational plans based on the user's learning needs. This makes it possible to provide detailed educational support that addresses individual learning needs while also addressing teacher shortages and the problem of declining educational quality. Furthermore, by applying this system to a virtual store, it is possible to improve the sales efficiency of educational content and the quality of the user experience.

[1078] "Curriculum information" refers to information that details the learning content, objectives, and lesson plans set by an educational institution.

[1079] "Educational content" refers to information used for educational purposes, such as textbooks, workbooks, and supplementary materials provided to learners.

[1080] "Terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers and students.

[1081] "Learning history" refers to data that records the learning activities and results that individual students have undertaken to date.

[1082] "Progress tracking" is a method of monitoring and recording learners' learning progress in real time and reporting their status as it occurs.

[1083] An "individualized learning plan" is an optimal learning plan tailored to each student's learning needs and progress.

[1084] A "generative AI model" is a model that uses artificial intelligence to create new information, and is particularly used to automatically generate educational materials and learning plans.

[1085] A "prompt statement" is an input statement used to elicit a specific response from a generative AI model.

[1086] This invention relates to a system that uses an educational support system to automatically generate and distribute educational content based on curriculum information and to provide learning plans tailored to individual learning needs. The system's hardware includes servers, a high-performance server farm, terminals (smartphones, tablets, computers), and head-mounted displays. The software utilizes educational support AI, educational data analysis AI, generative AI models (e.g., GPT-4), and a virtual reality engine (e.g., Unity).

[1087] Program Outline

[1088] 1. Acquisition of curriculum information and generation of educational content

[1089] The server retrieves curriculum information from a database and generates educational content using a generative AI model (GPT-4) based on that information. For example, it retrieves curriculum information for second-year junior high school mathematics and generates a workbook on "Basic Algebra." An example of the prompt used in this process is, "Generate educational content based on curriculum information. Second-year junior high school mathematics: Basic Algebra." The generated educational content is then sent from the server to the terminal.

[1090] 2. Recommendation of educational content

[1091] Based on the user's learning history data, the server recommends the most suitable educational content for each individual user. In this case, a generative AI model is also used to provide appropriate recommendations. For example, a request is sent to the AI ​​with the prompt message, "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization."

[1092] 3. Tracking learning progress

[1093] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. Progress is tracked in real time, and the percentage of learning progress is calculated. For example, it may be reported in the format of "Learning progress rate: 70%".

[1094] 4. Generating an individualized education plan

[1095] The server collects the user's learning needs and uses a generative AI model to generate personalized learning plans. For example, it might use a prompt message like, "Generate an appropriate learning plan if the user is struggling to solve word problems." This generated plan is then sent to the terminal.

[1096] Specific example

[1097] The following outlines the specific steps of the present invention:

[1098] 1. The server retrieves curriculum information for "Junior High School 2nd Year Mathematics," and the generating AI model generates a set of problems on "Basic Algebra."

[1099] 2. The server analyzes the user's learning history and recommends the next most suitable content based on "basic algebra and factorization."

[1100] 3. Collect learning progress data and report "7 out of 10 items completed, progress rate 70%."

[1101] 4. Based on the learning needs analysis, the generating AI model generates "additional problems for solving word problems," and an individualized education plan is generated.

[1102] Thus, the present invention enables personalized and effective educational support in educational settings and virtual stores.

[1103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1104] Step 1:

[1105] The server retrieves curriculum information from the database. This curriculum information includes grade level, subject, and learning content. This curriculum information is used as input to generate educational content. For example, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics: Basic Algebra."

[1106] Step 2:

[1107] Based on the curriculum information acquired by the server, a prompt message is sent to the generation AI model. The specific prompt message is "Generate educational content based on the curriculum information. Junior High School 2nd Year Mathematics: Basic Algebra." The generation AI model takes this prompt message as input and generates the corresponding educational content (such as a workbook).

[1108] Step 3:

[1109] The server sends the generated educational content to the device. The device displays the content so that teachers and students can access it. The generated educational content is delivered to the device, and users can review and use it.

[1110] Step 4:

[1111] The server collects the user's learning history. The collected learning history data includes content already studied and their performance on it. This data is used as input for data processing to identify the next educational content to recommend. For example, the learning history of "basic algebra" and "factorization" in mathematics is collected.

[1112] Step 5:

[1113] The server sends a prompt to the generating AI model based on the user's learning history data. The specific prompt is: "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization." The generating AI model then recommends the following appropriate educational content.

[1114] Step 6:

[1115] The server sends recommended educational content to the device. The device displays the recommended content in a user-friendly format. The user can review the recommended content and continue learning.

[1116] Step 7:

[1117] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. The collected data includes the number of completed assignments and the total number of assignments. This data is used as input to calculate the progress rate. For example, if 7 out of 10 items have been completed, the progress rate is 70%.

[1118] Step 8:

[1119] The server notifies the terminal of the progress. The terminal visually displays the progress to the user and guides them to the next learning step. The user can check the progress report and understand the remaining learning tasks.

[1120] Step 9:

[1121] The server collects the user's learning needs and sends a prompt to the generative AI model. The specific prompt is, "If the user is struggling to solve word problems, generate an appropriate learning plan." Based on this data, the generative AI model generates the optimal individualized learning plan.

[1122] Step 10:

[1123] The server sends the generated individualized learning plan to the device. The device displays the plan in a user-friendly format, providing it as a learning guide. The user can then proceed with their learning based on this learning plan.

[1124] By following the steps described above, the educational support system of the present invention can function smoothly and provide an effective educational experience for teachers and students.

[1125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1126] This invention is a system that combines educational support AI, educational data analysis AI, and an emotion engine to solve the teacher shortage and decline in the quality of education in educational settings. This system includes the following functions:

[1127] 1. Automated creation of educational materials

[1128] The server accesses the curriculum database to retrieve the latest curriculum information. Based on this information, the AI ​​automatically generates teaching materials. The generated materials are sent from the server to the teacher's terminal. The teacher reviews the materials on their terminal and distributes them to students.

[1129] Specific example:

[1130] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra" and sends it to the teacher's terminal. The teacher then distributes the materials to the students.

[1131] 2. Scoring Tool

[1132] The server collects the answer data submitted by students from their devices, compares it against the correct answer key, and scores the answers. The grade data is sent from the server to the teacher's device. The teacher reviews the grades and provides feedback to the students.

[1133] Specific example:

[1134] The server collects student A's math test answers, matches them against the correct answer key, assigns a score of 90, and notifies the teacher's terminal of the result. The teacher then checks the grade.

[1135] 3. Learning support

[1136] The server periodically collects learning progress data from students' devices, and AI analyzes this data to identify areas where students are particularly struggling. Supplementary materials and activities are generated and sent to both teachers' and students' devices.

[1137] Specific example:

[1138] The server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[1139] 4. Analysis of learning progress and recommendations

[1140] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, the AI ​​proposes the optimal learning approach, and this information is sent to the teacher's terminal. The teacher then adjusts the lesson content based on the proposal.

[1141] Specific example:

[1142] The server collects student C's math learning history and suggests that "lessons that heavily utilize visual aids" would be effective, notifying the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[1143] 5. Creating an Individualized Education Plan

[1144] The server collects data on students' learning needs, and AI generates and optimizes individualized learning plans based on that data. The optimized learning plans are sent to the teachers' and students' devices. Teachers review the plans and provide appropriate instruction to students.

[1145] Specific example:

[1146] The server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[1147] 6. Suggestions for improving the educational process

[1148] The server collects data on the entire school's educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and notifies teachers of these improvements on their terminals. Teachers then revise their educational processes and curriculum based on the suggestions they receive.

[1149] Specific example:

[1150] The server analyzes the school-wide lesson evaluation data and proposes to "increase reading and writing time," then notifies teachers of this proposal. Teachers then adjust their lesson content based on the proposal.

[1151] 7. Utilizing the Emotional Engine

[1152] The server includes an emotion engine that recognizes user emotions and collects and analyzes user emotion data. Based on this data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials and relaxation activities.

[1153] Specific example:

[1154] The server collects emotional data from student E, and the AI ​​detects when the student is experiencing stress. Based on the analysis, it suggests relaxation exercises and sends them to the teacher's and student's devices. The teacher reviews the suggestions and instructs the student on additional relaxation activities.

[1155] 8. Utilization of teacher sentiment data

[1156] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[1157] Specific example:

[1158] The server collects emotional data from teacher F, and the AI ​​detects when the teacher is experiencing stress. Based on this, it sends suggestions to the teacher's terminal to help distribute tasks. The teacher then uses these suggestions to distribute tasks and reduce stress.

[1159] In summary, the present invention is a system that alleviates the shortage of teachers in educational settings, improves the quality of education, and further utilizes emotional data of students and teachers to provide optimal learning and guidance.

[1160] The following describes the processing flow.

[1161] Automated creation of educational materials

[1162] Step 1:

[1163] The server accesses the school's curriculum database to retrieve the latest curriculum information.

[1164] Step 2:

[1165] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[1166] Step 3:

[1167] The server sends the generated teaching material data to the teacher's terminal.

[1168] Step 4:

[1169] The teacher receives the teaching materials on a device and checks their contents.

[1170] Step 5:

[1171] The teacher will distribute the materials they have reviewed to the students, and the students will use the materials to study.

[1172] Scoring tool

[1173] Step 1:

[1174] The server collects the response data submitted from the students' devices.

[1175] Step 2:

[1176] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[1177] Step 3:

[1178] The server calculates each student's score and generates grade data.

[1179] Step 4:

[1180] The server sends the grade data to the teacher's terminal.

[1181] Step 5:

[1182] Teachers check grades on their devices and provide feedback to students.

[1183] Learning support

[1184] Step 1:

[1185] The server periodically collects learning progress data from students' devices.

[1186] Step 2:

[1187] The server collects progress data, which is then input into an AI model for analysis.

[1188] Step 3:

[1189] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[1190] Step 4:

[1191] The server automatically generates supplementary materials and activities.

[1192] Step 5:

[1193] The server sends the generated supplementary materials to the teachers' and students' devices.

[1194] Step 6:

[1195] Teachers use their devices to review supplementary materials and provide instruction to students.

[1196] Learning progress analysis and suggestions

[1197] Step 1:

[1198] The server collects students' learning history and performance data.

[1199] Step 2:

[1200] The server inputs the collected data into an AI model for detailed analysis.

[1201] Step 3:

[1202] The AI ​​proposes the optimal learning approach based on the analysis results.

[1203] Step 4:

[1204] The server notifies the teacher's terminal of the proposed content.

[1205] Step 5:

[1206] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[1207] Creating an individualized education plan

[1208] Step 1:

[1209] The server collects data related to students' learning needs.

[1210] Step 2:

[1211] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[1212] Step 3:

[1213] The AI ​​optimizes the educational plans it generates.

[1214] Step 4:

[1215] The server sends optimized lesson plans to teachers' and students' devices.

[1216] Step 5:

[1217] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[1218] Suggestions for improving the education process

[1219] Step 1:

[1220] The server collects data about the entire school's educational process.

[1221] Step 2:

[1222] The server collects data, which is then input into an AI model for analysis.

[1223] Step 3:

[1224] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[1225] Step 4:

[1226] The server will notify teachers' terminals of the identified areas for improvement.

[1227] Step 5:

[1228] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[1229] Utilizing the Emotion Engine

[1230] Step 1:

[1231] The server activates the emotion engine to collect user emotion data.

[1232] Step 2:

[1233] The emotion engine analyzes the user's facial expressions and behavioral data to generate emotion data.

[1234] Step 3:

[1235] The server inputs the generated emotion data into the AI ​​model, which then adjusts the learning materials and activities.

[1236] Step 4:

[1237] The server sends the prepared teaching materials and activities to the teachers' and students' devices.

[1238] Step 5:

[1239] Teachers check the adjustments on their devices and provide guidance to students.

[1240] Stress management using emotional data

[1241] Step 1:

[1242] The server collects emotional data from students and teachers.

[1243] Step 2:

[1244] AI analyzes emotional data to detect signs of stress.

[1245] Step 3:

[1246] The server generates supplementary materials and relaxation activities to help with stress management.

[1247] Step 4:

[1248] The server sends the generated supplementary materials and activities to the teachers' and students' devices.

[1249] Step 5:

[1250] Teachers use their devices to check supplementary materials and activities and provide instruction.

[1251] (Example 2)

[1252] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[1253] In the education sector, teacher shortages and a decline in the quality of education are serious problems. In particular, creating teaching materials tailored to the individual learning needs of students and providing appropriate feedback is difficult, which further contributes to the decline in quality. Furthermore, understanding the emotional states of students and teachers and responding appropriately based on that understanding is also challenging. A system is needed to solve these problems and improve the quality of education.

[1254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1255] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, and means for transmitting the generated teaching materials to teachers' terminals. This enables the automatic generation and distribution of teaching materials based on the latest curriculum. It also includes means for generating teaching materials using an AI model and means for sending instructions to the generation AI model using prompt statements, thereby enabling the efficient creation of high-quality teaching materials and improving the quality of education. Furthermore, it includes means for collecting and analyzing student and teacher emotional data using an emotion engine, allowing for the adjustment of teaching materials and activities to maximize learning effectiveness based on the analysis results, thus contributing to the improvement of educational quality from an emotional perspective as well.

[1256] "Curriculum information" refers to information that includes teaching objectives, content, and evaluation criteria within the educational curriculum.

[1257] "Learning materials" refer to materials and tools that learners use for their studies, and include textbooks, workbooks, reference books, and digital learning materials.

[1258] A "terminal" refers to a device used by a user to interact with a system, and includes personal computers, tablets, smartphones, and other similar devices.

[1259] An "AI model" is a model that uses artificial intelligence algorithms to perform a specific task, and includes, for example, generative AI models and analytical AI models.

[1260] A "prompt message" is text data used to provide specific instructions or input information to a generative AI model.

[1261] "Response data" refers to the answers that learners submit to tests and assignments.

[1262] A "correct answer key" is a reference data that indicates the correct answer to a test or assignment, and is used for grading and performance evaluation.

[1263] "Learning progress data" refers to data that shows how far a learner has progressed in their studies, and includes study time, progress rate, and level of understanding.

[1264] An "emotion engine" is an artificial intelligence system designed to recognize and analyze a user's emotional state, and includes features such as facial recognition, voice analysis, and text analysis.

[1265] "Feedback" refers to evaluation results and suggestions for improvement provided to learners and teachers, with the aim of improving learning methods and comprehension.

[1266] An "activity" refers to a specific activity or exercise performed while progressing through learning, and includes problem-solving games and experiments.

[1267] This invention is a system designed to address teacher shortages and declining quality of education in educational settings, and operates primarily through servers, terminals, and users. Specifically, it operates by combining the following functions.

[1268] 1. Acquisition of curriculum information and automatic generation of teaching materials

[1269] The server accesses the curriculum database to retrieve the latest curriculum information. Based on this information, the server automatically generates teaching materials using a generative AI model (e.g., "GPT-4"). The generated teaching materials are sent from the server to the teacher's terminal. The teacher then uses that terminal to review the materials and distribute them to students.

[1270] Specific example:

[1271] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics" and sends the following prompt to the generating AI model to generate a set of problems on "Basic Algebra."

[1272] "Please create a workbook of basic algebra problems based on the curriculum for second-year junior high school mathematics."

[1273] 2. Scoring Tool

[1274] The server collects the answer data submitted by students from their devices and scores it by comparing it with the correct answer key. The correct answer key is stored in a database on the server. The scoring results are sent from the server to the teacher's device, where the teacher can check the grades and provide feedback to the students.

[1275] Specific example:

[1276] The server collects the answers to student A's math test and uses a generative AI model to grade them with the following prompt messages.

[1277] "Please compare Student A's answer with the correct answer key, grade it, and notify the teacher of the score." The result is a score of 90 points, which is then notified to the teacher.

[1278] 3. Learning support

[1279] The server periodically collects learning progress data from students' devices and analyzes it using a generative AI model. This identifies areas where students are particularly struggling and generates supplementary materials and activities. These are then sent to both teachers' and students' devices.

[1280] Specific example:

[1281] The server analyzes student B's progress data and uses a generating AI model to send the following prompt message, thereby generating "additional problems for solving word problems."

[1282] "Analyze student B's progress data and generate supplementary materials to address their weak areas." The teacher checks this on their device and provides instruction to the student.

[1283] 4. Analysis of learning progress and recommendations

[1284] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. Based on the analysis results, the optimal learning approach is proposed and notified to the teacher's terminal. The teacher adjusts the lesson content based on this proposal.

[1285] Specific example:

[1286] The server analyzes student C's math learning history and suggests that "lessons that heavily utilize visual aids" would be effective. This suggestion is sent to the teacher's terminal with the following prompt message.

[1287] "Analyze student C's learning history and propose the optimal learning approach."

[1288] 5. Creating an Individualized Education Plan

[1289] The server collects student learning needs data and uses a generative AI model to generate and optimize individualized learning plans. The optimized plans are sent to the teacher's and student's devices. Teachers review the plans and provide appropriate instruction to students.

[1290] Specific example:

[1291] The server analyzes student D's learning needs and generates a "reading and writing support program" by sending the following prompt message using a generative AI model.

[1292] "Generate and optimize an individualized learning plan based on student D's learning needs." The teacher will then provide appropriate instruction based on this plan.

[1293] 6. Suggestions for improving the educational process

[1294] The server collects data on the school's overall educational process and analyzes it using a generative AI model. Based on the data, it identifies areas for improvement in the educational process and curriculum, and notifies teachers of these improvements on their terminals. Teachers then revise their educational processes and curriculum based on the suggestions they receive.

[1295] Specific example:

[1296] The server analyzes the school-wide lesson evaluation data and sends the following prompt message using a generative AI model.

[1297] "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum." As a result, "increasing reading and writing time" is suggested and communicated to the teachers.

[1298] 7. Utilizing the Emotional Engine

[1299] The server includes an emotion engine that recognizes user emotions. User emotion data is collected on the server and analyzed by the emotion engine. Based on the user's emotion data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials or relaxation activities.

[1300] Specific example:

[1301] The server collects student E's emotional data and uses the emotional engine to send the following prompt message.

[1302] "Analyze student E's emotional data and suggest relaxation exercises to reduce stress." The teacher will then use this suggestion to instruct the student on additional relaxation activities.

[1303] 8. Utilization of teacher sentiment data

[1304] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[1305] Specific example:

[1306] The server collects teacher F's emotional data and uses the emotion engine to send the following prompt message.

[1307] "Analyze teacher F's emotional data and propose approaches to reduce their workload." Based on these proposals, the teacher will distribute tasks and reduce stress.

[1308] As described above, the system of the present invention not only alleviates the shortage of teachers in educational settings and improves the quality of education, but also makes it possible to provide optimal learning and guidance by utilizing emotional data of students and teachers.

[1309] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1310] Automated creation of educational materials

[1311] Step 1:

[1312] The server accesses the curriculum database.

[1313] input:

[1314] Request to access the curriculum database

[1315] Data processing:

[1316] Execute a query to extract curriculum information.

[1317] output:

[1318] Latest curriculum information

[1319] Specific actions:

[1320] The server sends a query to the curriculum database with the condition "Junior High School 2nd Year Mathematics" and retrieves the corresponding curriculum information.

[1321] Step 2:

[1322] The server inputs the acquired curriculum information into a generating AI model.

[1323] input:

[1324] Latest curriculum information

[1325] Data processing:

[1326] Convert curriculum information into prompt messages

[1327] output:

[1328] Instruction prompts for the AI ​​model

[1329] Specific actions:

[1330] The server generates a prompt message, "Generate a set of problems on the basics of algebra based on the curriculum for second-year junior high school mathematics," and sends it to the AI ​​model.

[1331] Step 3:

[1332] The AI ​​model automatically generates educational materials.

[1333] input:

[1334] Instruction prompt message

[1335] Data processing:

[1336] Creating educational materials using generative AI models

[1337] output:

[1338] Automatically generated teaching materials

[1339] Specific actions:

[1340] A generative AI model (e.g., GPT-4) generates a set of problems on fundamental algebraic concepts based on a prompt.

[1341] Step 4:

[1342] The server sends the generated teaching materials to the teacher's terminal.

[1343] input:

[1344] Automatically generated teaching materials

[1345] Data processing:

[1346] Preparing to send teaching material data

[1347] output:

[1348] Sending teaching materials data to teachers' devices

[1349] Specific actions:

[1350] The server converts the generated teaching materials into PDF format and sends them to the teacher's terminal.

[1351] Scoring tool

[1352] Step 1:

[1353] Students submit their answers to the server from their devices.

[1354] input:

[1355] Student response data

[1356] Data processing:

[1357] Collection of response data

[1358] output:

[1359] Response data sent to the server

[1360] Specific actions:

[1361] The student clicks the "end" button on the online test, and the answer data is uploaded to the server.

[1362] Step 2:

[1363] The server compares the response data with the correct key.

[1364] input:

[1365] Student response data, correct answer key

[1366] Data processing:

[1367] Scoring by comparison

[1368] output:

[1369] Scoring results

[1370] Specific actions:

[1371] The server compares student A's answer data with the correct answer key previously stored in the database and calculates the score.

[1372] Step 3:

[1373] The server notifies the teacher's terminal of the grading results as grades.

[1374] input:

[1375] Scoring results

[1376] Data processing:

[1377] Preparing to send result data

[1378] output:

[1379] Grade notification to the teacher's device

[1380] Specific actions:

[1381] The server notifies teachers of the grading results in real time on their terminals, allowing teachers to review them and provide feedback to students.

[1382] Learning support

[1383] Step 1:

[1384] Students' devices send learning progress data to the server.

[1385] input:

[1386] Student learning progress data

[1387] Data processing:

[1388] Collection of progress data

[1389] output:

[1390] Progress data sent to the server

[1391] Specific actions:

[1392] Students record their daily learning progress using a learning app, and this information is automatically sent to a server.

[1393] Step 2:

[1394] The server inputs progress data into the AI ​​model.

[1395] input:

[1396] Student learning progress data

[1397] Data processing:

[1398] Generating prompts for analyzing progress data

[1399] output:

[1400] Analysis prompts for AI models

[1401] Specific actions:

[1402] The server generates a prompt message saying, "Analyze student B's progress data and generate supplementary materials to address their weak areas," and sends it to the AI ​​model.

[1403] Step 3:

[1404] The generative AI model generates supplementary materials and activities.

[1405] input:

[1406] Analysis prompt message

[1407] Data processing:

[1408] Generating supplementary materials and activities

[1409] output:

[1410] Supplementary materials and activities that are generated

[1411] Specific actions:

[1412] The generative AI model generates "additional problems for solving word problems" based on the prompt text.

[1413] Step 4:

[1414] The server sends the generated supplementary materials to the teachers' and students' devices.

[1415] input:

[1416] Supplementary materials and activities that are generated

[1417] Data processing:

[1418] Preparing to send teaching material data

[1419] output:

[1420] Sending teaching materials data to teachers' and students' devices

[1421] Specific actions:

[1422] The server converts supplementary materials into PDF format and sends them to the teacher's and students' devices. The teacher reviews them and provides instruction to the students.

[1423] Learning progress analysis and suggestions

[1424] Step 1:

[1425] The server collects students' learning history and performance data.

[1426] input:

[1427] Student learning history and performance data

[1428] Data processing:

[1429] Data collection

[1430] output:

[1431] Learning history and performance data collected on the server

[1432] Specific actions:

[1433] The server periodically collects student C's math learning data for the past six months.

[1434] Step 2:

[1435] The server inputs the learning history and performance data into the generated AI model.

[1436] input:

[1437] Student learning history and performance data

[1438] Data processing:

[1439] Generating prompts for analysis

[1440] output:

[1441] Analysis prompts for AI models

[1442] Specific actions:

[1443] The server generates a prompt message saying, "Analyze student C's learning history and suggest the optimal learning approach," and sends it to the AI ​​model.

[1444] Step 3:

[1445] Generative AI models analyze data in detail and propose the optimal learning approach.

[1446] input:

[1447] Analysis prompt message

[1448] Data processing:

[1449] Generating learning approach proposals

[1450] output:

[1451] Proposal details

[1452] Specific actions:

[1453] The generative AI model analyzes student C's data and generates a suggestion that "lessons that heavily utilize visual aids" are effective.

[1454] Step 4:

[1455] The server sends the proposal to the teacher's terminal.

[1456] input:

[1457] Proposal details

[1458] Data processing:

[1459] Preparing to send proposal data

[1460] output:

[1461] Sending proposal content to the teacher's terminal

[1462] Specific actions:

[1463] The server sends the proposed content to the teacher's terminal, and the teacher adjusts the lesson content to make extensive use of visual aids.

[1464] Creating an individualized education plan

[1465] Step 1:

[1466] Student devices send learning needs data to the server.

[1467] input:

[1468] Student learning needs data

[1469] Data processing:

[1470] Collection of needs data

[1471] output:

[1472] Needs data sent to the server

[1473] Specific actions:

[1474] Students record their special learning needs, and this information is sent to a server.

[1475] Step 2:

[1476] The server generates learning needs data and inputs it into the AI ​​model.

[1477] input:

[1478] Student learning needs data

[1479] Data processing:

[1480] Prompt message generation for plan generation

[1481] output:

[1482] Prompt for generating a plan for the AI ​​model

[1483] Specific actions:

[1484] The server generates a prompt message, "Generate and optimize an individualized learning plan based on student D's learning needs," and sends it to the AI ​​model.

[1485] Step 3:

[1486] The generative AI model generates and optimizes individualized educational plans.

[1487] input:

[1488] Plan generation prompt message

[1489] Data processing:

[1490] Generating and optimizing individualized education plans

[1491] output:

[1492] Generated Individual Education Plan

[1493] Specific actions:

[1494] The generative AI model generates and optimizes a "reading and writing support program" based on student D's data.

[1495] Step 4:

[1496] The server sends the generated individualized education plans to the teachers' and students' devices.

[1497] input:

[1498] Generated Individual Education Plan

[1499] Data processing:

[1500] Preparing to send plan data

[1501] output:

[1502] Sending plan data to teachers' and students' devices

[1503] Specific actions:

[1504] The server converts the generated lesson plan into PDF format and sends it to the teacher's and student's devices. The teacher then provides appropriate instruction based on the plan.

[1505] Suggestions for improving the education process

[1506] Step 1:

[1507] The server collects data about the entire school's educational process.

[1508] input:

[1509] Educational process data

[1510] Data processing:

[1511] Data collection

[1512] output:

[1513] Educational process data collected on the server

[1514] Specific actions:

[1515] The server collects school-wide lesson evaluation survey data.

[1516] Step 2:

[1517] The server inputs educational process data into the AI ​​model.

[1518] input:

[1519] Educational process data

[1520] Data processing:

[1521] Generating prompt messages for improvement suggestions

[1522] output:

[1523] Prompt for suggesting improvements to the AI ​​model

[1524] Specific actions:

[1525] The server generates a prompt message that reads, "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum," and sends it to the AI ​​model.

[1526] Step 3:

[1527] The generative AI model analyzes data and suggests improvements to the educational process and curriculum.

[1528] input:

[1529] Improvement suggestion prompt message

[1530] Data processing:

[1531] Generating proposals for educational improvement

[1532] output:

[1533] Improvement proposal details

[1534] Specific actions:

[1535] The generative AI model analyzes the data and generates suggestions such as "increase reading and writing time."

[1536] Step 4:

[1537] The server sends the improvement suggestions to the teacher's terminal.

[1538] input:

[1539] Improvement proposal details

[1540] Data processing:

[1541] Preparing to send improvement suggestion data

[1542] output:

[1543] Sending proposal content to the teacher's terminal

[1544] Specific actions:

[1545] The server sends the proposal to the teacher's terminal, and the teacher adjusts the curriculum timetable to increase reading and writing time.

[1546] Utilizing the Emotion Engine

[1547] Step 1:

[1548] The user's device sends emotional data to the server.

[1549] input:

[1550] User sentiment data

[1551] Data processing:

[1552] Collection of emotional data

[1553] output:

[1554] Emotional data sent to the server

[1555] Specific actions:

[1556] The user records their emotional state on their device, and that information is sent to the server.

[1557] Step 2:

[1558] The server inputs emotional data into the emotion engine.

[1559] input:

[1560] Emotional data

[1561] Data processing:

[1562] Analysis of emotional data

[1563] output:

[1564] Analysis results regarding emotional state

[1565] Specific actions:

[1566] The server inputs emotional data into the emotion engine, which then performs analysis.

[1567] Step 3:

[1568] The emotion engine analyzes emotional data and adjusts supplementary materials and activities accordingly.

[1569] input:

[1570] Analysis results regarding emotional state

[1571] Data processing:

[1572] Adjusting teaching materials and activities

[1573] output:

[1574] Customized teaching materials and activities

[1575] Specific actions:

[1576] The emotion engine analyzes student E's data and suggests "relaxation exercises" if it detects a high stress level.

[1577] Step 4:

[1578] The server sends the adjusted learning materials and activities to the user.

[1579] input:

[1580] Customized teaching materials and activities

[1581] Data processing:

[1582] Preparing to send teaching material data

[1583] output:

[1584] Sending educational material data to the user's device

[1585] Specific actions:

[1586] The server sends the suggested content to the teacher's and student's devices, and the teacher then instructs them on relaxation activities.

[1587] Utilizing teacher sentiment data

[1588] Step 1:

[1589] Teachers send emotional data from their devices to the server.

[1590] input:

[1591] Teacher sentiment data

[1592] Data processing:

[1593] Collection of emotional data

[1594] output:

[1595] Emotional data sent to the server

[1596] Specific actions:

[1597] Teachers record their emotional state, and this information is sent to a server.

[1598] Step 2:

[1599] The server inputs emotional data into the emotion engine.

[1600] input:

[1601] Teacher sentiment data

[1602] Data processing:

[1603] Analysis of emotional data

[1604] output:

[1605] Analysis results regarding emotional state

[1606] Specific actions:

[1607] The server inputs emotional data into the emotion engine, which then performs analysis.

[1608] Step 3:

[1609] The emotion engine analyzes emotional data and generates stress management suggestions.

[1610] input:

[1611] Analysis results regarding emotional state

[1612] Data processing:

[1613] Generating stress management proposals

[1614] output:

[1615] Generated stress management proposals

[1616] Specific actions:

[1617] The emotion engine analyzes teacher F's data and generates suggestions for "dividing the workload."

[1618] Step 4:

[1619] The server sends the proposal to the teacher's terminal.

[1620] input:

[1621] Generated stress management proposals

[1622] Data processing:

[1623] Preparing to send proposal data

[1624] output:

[1625] Sending proposal content to the teacher's terminal

[1626] Specific actions:

[1627] The server sends the proposed content to the teachers' terminals, and based on the proposals, tasks are divided and stress is reduced.

[1628] Through the above processing steps, the system of the present invention alleviates the shortage of teachers in educational settings, improves the quality of education, and provides optimal learning and guidance by utilizing emotional data.

[1629] (Application Example 2)

[1630] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1631] Teacher shortages and declining quality of education are significant challenges in the modern educational environment. Efficient training and education of new operators in factories are also crucial. Traditional methods place an excessive burden on teachers and trainers, risking a decline in the quality of education. Furthermore, inadequate stress management among operators makes effective training difficult. This invention provides a system to solve these problems.

[1632] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1633] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, means for transmitting the generated teaching materials to a teacher's terminal, means for automatically generating training materials based on factory operating procedures and safety guidelines, means for providing the generated training materials to an operator's terminal, means for collecting operator progress data and emotional data, and means for analyzing the progress data and emotional data and suggesting relaxation exercises if stress is detected. This makes it possible to alleviate teacher shortages and the decline in the quality of education, as well as manage operator stress.

[1634] "Curriculum information" refers to information about learning content and teaching policies established for educational purposes.

[1635] "Educational materials" refer to materials and content used to achieve specific educational objectives.

[1636] A "terminal" is a device used to communicate with a server and receive information.

[1637] "Operating procedures" refer to the steps and methods for correctly performing tasks and operations in a factory.

[1638] "Safety guidelines" are standards and guidelines for performing work safely within a factory.

[1639] "Training materials" are educational materials used to acquire specific skills or knowledge.

[1640] An "operator" is a worker who operates machinery and equipment in a factory or work site.

[1641] "Progress data" refers to information about the progress of learning or work.

[1642] "Emotional data" refers to information about an individual's emotional state.

[1643] "Relaxation exercise" refers to activities and movements designed to reduce stress and promote mental and physical relaxation.

[1644] "Outcome data" refers to information about grades and performance obtained as a result of education or training.

[1645] "Stress" refers to a reaction or state of tension to physical, psychological, or environmental factors.

[1646] "Feedback" refers to evaluations and advice given regarding the results of learning or work.

[1647] "Educational methods" refer to the methods and means used to effectively carry out educational activities.

[1648] This invention is a system that combines educational support AI, educational data analysis AI, and an emotion engine to address teacher shortages and declining quality of education in educational settings. It can also be applied to training and educational support for new operators in factories. The following provides a detailed description of the system that realizes this application.

[1649] Hardware configuration

[1650] server:

[1651] The server plays a central role in managing curriculum information, factory operating procedures, and safety guidelines, and in automatically generating educational materials. It also includes a database for collecting and analyzing student and operator progress and sentiment data.

[1652] Terminal:

[1653] The devices include tablets and personal computers for teachers and operators. These devices are used to receive generated teaching materials and feedback.

[1654] Emotion sensor:

[1655] The emotion sensor is a sensor used to collect emotional data from operators and students. This allows for appropriate responses if stress is detected.

[1656] Software Configuration

[1657] Educational support AI:

[1658] The educational support AI automatically generates teaching materials and training materials based on curriculum information and factory operating procedures. The generated materials are then sent to the terminals of teachers and operators.

[1659] AI for educational data analysis:

[1660] The educational data analysis AI analyzes progress and performance data from students and operators. This allows it to identify learning trends and areas of weakness, and then suggest optimal teaching methods and supplementary materials.

[1661] Emotional engine:

[1662] The emotion engine collects and analyzes emotional data from students and operators. Based on this, if stress is detected, it suggests relaxation exercises or other responses.

[1663] Processing flow

[1664] 1. Automated creation of educational materials:

[1665] The server retrieves curriculum information, factory operating procedures, and safety guidelines, and uses educational support AI to automatically generate teaching materials and training materials.

[1666] 2. Provision of generated teaching materials:

[1667] The generated teaching materials and training materials are sent to terminals for instructors and operators and provided to users.

[1668] 3. Collection and analysis of progress data and sentiment data:

[1669] The server collects progress and emotional data from students and operators, and analyzes it using educational data analysis AI and an emotional engine.

[1670] 4. Feedback and suggestions for additional materials:

[1671] Based on the analysis results, optimal teaching methods and supplementary materials are suggested and sent to terminals for teachers and operators. If stress is detected, relaxation exercises are suggested.

[1672] Specific example

[1673] For example, if a factory robot is training a new operator on "wiring a power distribution panel," the robot automatically generates training materials based on operating procedures and safety guidelines and provides them to the operator's tablet. Once the operator completes the training, the robot collects progress data and emotional data and sends it to a server. An AI for analyzing educational data evaluates the progress, and an emotional engine determines whether or not stress is present. Additional supplementary materials or relaxation exercises are suggested as needed.

[1674] Example of a prompt

[1675] "Automatically generate training materials for new operators to learn how to wire distribution panels. Also, analyze training progress and operator emotional data, and suggest necessary additional materials and relaxation exercises."

[1676] This system will help address teacher shortages and the decline in the quality of education, as well as enable efficient training and stress management for operators.

[1677] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1678] Step 1:

[1679] The server retrieves curriculum information, factory operating procedures, and safety guidelines. This information is collected as input data and used in the following steps.

[1680] Input: Curriculum information, operating procedures, safety guidelines

[1681] Output: Acquired curriculum information and guideline data

[1682] Step 2:

[1683] The educational support AI automatically generates teaching materials and training materials based on the curriculum information and operating procedures acquired in the previous step. The generated materials are diverse and include text, video, and interactive content.

[1684] Input: Curriculum information, operating procedures, safety guidelines

[1685] Data processing: Generating educational materials using AI models.

[1686] Output: Generated teaching materials, training materials

[1687] Step 3:

[1688] The generated teaching materials and training materials are sent to terminals for instructors and operators. Users can then view these materials on their terminals and conduct their learning or training.

[1689] Input: Generated teaching materials, training materials

[1690] Output: Provided teaching materials and training materials (on the device)

[1691] Specific operation: Sending data from the server to the terminal.

[1692] Step 4:

[1693] Users perform training and learning using their devices, and progress data and emotional data are collected. Data is collected from emotional sensors, usage logs, test results, etc.

[1694] Input: User's action progress, sentiment data

[1695] Output: Progress data, sentiment data (sent to the server)

[1696] Specific actions: Real-time collection of progress and sentiment data.

[1697] Step 5:

[1698] The server passes the collected progress and emotional data to the educational data analysis AI and emotion engine for analysis. This analysis includes identifying areas of difficulty and stress levels.

[1699] Input: Progress data, sentiment data

[1700] Data processing: AI-based progress analysis and sentiment analysis.

[1701] Output: Analysis results (issue areas, stress levels, etc.)

[1702] Step 6:

[1703] The educational data analysis AI generates supplementary materials and activities based on the progress analysis results, and the server sends the generated supplementary materials and relaxation exercises to terminals for teachers and operators.

[1704] Input: Progress analysis results, city situation analysis results

[1705] Data processing: Generation of supplementary materials and relaxation exercises.

[1706] Output: Generated supplementary materials, relaxation exercises (sent to the device)

[1707] Specific operation: Sending additional learning materials from the server to the terminal.

[1708] Step 7:

[1709] Teachers and operators can access and apply supplementary materials and relaxation exercises on their devices. This helps improve comprehension and reduce stress.

[1710] Input: Supplementary materials, relaxation exercises

[1711] Output: Application results (user progress and emotional changes)

[1712] Specific actions: The user completes the instructed learning materials and exercises.

[1713] Through the steps described above, the system of this invention can achieve effective educational support, operator training, and stress management.

[1714] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1715] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1716] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1717] [Third Embodiment]

[1718] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1719] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1720] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1721] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1722] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1723] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1724] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1725] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1726] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1727] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1728] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1729] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1730] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade response data and notify teachers of their grades on their terminals, to analyze students' learning progress data and provide supplementary materials and activities, to analyze individual students' learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[1731] 1. Automated creation of educational materials

[1732] The server retrieves the latest curriculum information from the curriculum database and automatically generates teaching materials based on that information. For example, the server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra." The server then sends the generated teaching materials to the teacher's terminal, and the teacher distributes the materials to the students.

[1733] 2. Scoring Tool

[1734] The server collects answer data submitted from students' devices and scores it by comparing it to the correct answer key. For example, the server collects answer data for a math test, and the AI ​​compares it to the correct answer key and scores it at 90 points. The result is then notified to the teacher's device as grade data, and the teacher can check the grade.

[1735] 3. Learning support

[1736] The server periodically collects student learning progress data, and AI analyzes this data. It identifies students' learning trends and areas where they are lacking, and generates supplementary materials and activities. For example, the server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[1737] 4. Analysis of learning progress and recommendations

[1738] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, it proposes the optimal learning approach and notifies the teacher of the proposal on their terminal. For example, the server collects student C's math learning history and suggests that "lessons using a lot of visual aids" would be effective, and notifies the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[1739] 5. Creating an Individualized Education Plan

[1740] The server collects data on students' learning needs, and AI generates individualized educational plans based on that data. The generated plans are then optimized and sent to the teacher's and student's devices. For example, the server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[1741] 6. Suggestions for improving the educational process

[1742] The server collects data on the educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and creates detailed improvement suggestions. These suggestions are then notified to teachers' terminals, and teachers consider them. For example, the server analyzes school-wide lesson evaluation data and suggests "increasing reading and writing time," and notifies teachers of this suggestion. Teachers then adjust their lesson content based on the suggestion.

[1743] This invention reduces the workload of teachers while simultaneously providing optimal educational support to each student, thereby improving the overall quality of the educational environment.

[1744] The following describes the processing flow.

[1745] Automated creation of educational materials

[1746] Step 1:

[1747] The server accesses the curriculum database to retrieve the latest curriculum information.

[1748] Step 2:

[1749] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[1750] Step 3:

[1751] The server sends the generated teaching material data to the teacher's terminal.

[1752] Step 4:

[1753] The teacher receives the teaching materials on a device and checks their contents.

[1754] Step 5:

[1755] The teacher distributes teaching materials to the students, and the students use the materials to study.

[1756] Scoring tool

[1757] Step 1:

[1758] The server collects the response data submitted from the students' devices.

[1759] Step 2:

[1760] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[1761] Step 3:

[1762] The server calculates each student's score and generates grade data.

[1763] Step 4:

[1764] The server sends the grade data to the teacher's terminal.

[1765] Step 5:

[1766] Teachers check grades on their devices and provide feedback to students.

[1767] Learning support

[1768] Step 1:

[1769] The server periodically collects learning progress data from students' devices.

[1770] Step 2:

[1771] The server collects progress data, which is then input into an AI model for analysis.

[1772] Step 3:

[1773] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[1774] Step 4:

[1775] The server automatically generates supplementary materials and activities.

[1776] Step 5:

[1777] The server sends the generated supplementary materials to the teachers' and students' devices.

[1778] Step 6:

[1779] Teachers use their devices to review supplementary materials and provide instruction to students.

[1780] Learning progress analysis and suggestions

[1781] Step 1:

[1782] The server collects students' learning history and performance data.

[1783] Step 2:

[1784] The server inputs the collected data into an AI model for detailed analysis.

[1785] Step 3:

[1786] The AI ​​identifies the optimal learning approach based on the analysis results.

[1787] Step 4:

[1788] The server notifies the teacher's terminal of the proposed content.

[1789] Step 5:

[1790] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[1791] Creating an individualized education plan

[1792] Step 1:

[1793] The server collects data related to students' learning needs.

[1794] Step 2:

[1795] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[1796] Step 3:

[1797] The AI ​​optimizes the educational plans it generates.

[1798] Step 4:

[1799] The server sends optimized lesson plans to teachers' and students' devices.

[1800] Step 5:

[1801] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[1802] Suggestions for improving the education process

[1803] Step 1:

[1804] The server collects data about the entire school's educational process.

[1805] Step 2:

[1806] The server collects data, which is then input into an AI model for analysis.

[1807] Step 3:

[1808] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[1809] Step 4:

[1810] The server will notify teachers' terminals of the identified areas for improvement.

[1811] Step 5:

[1812] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[1813] (Example 1)

[1814] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1815] In today's education system, teacher shortages and a decline in the quality of education are serious problems. In addition, providing individualized instruction to each student and preparing diverse teaching materials is often difficult. As a result, education is becoming more homogenized, and the individual learning needs of students cannot be met. To solve these problems, effective and efficient creation and distribution of teaching materials, automated grading, and individualized instruction based on students' progress are required.

[1816] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1817] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials using a generation AI model based on the curriculum information, means for sending prompt messages to the generation AI model to generate teaching materials, and means for transmitting the generated teaching materials to the teacher's information terminal. This reduces the workload of teachers and enables optimal educational support tailored to the learning needs of each student.

[1818] "Curriculum information" refers to educational data that includes detailed information such as the content of lessons, learning objectives, teaching materials, and progress schedules set by educational institutions.

[1819] A "generative AI model" is an artificial intelligence technique that learns from large amounts of data and automatically generates educational materials and problem sets according to specific instructions.

[1820] A "prompt message" is text data used to give specific instructions to a generative AI model, and it plays a role in prompting the generation of educational materials and problem sets.

[1821] "Teaching materials" refer to educational materials used to support students' learning, and include textbooks, workbooks, supplementary materials, and other similar items.

[1822] "Teacher information terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers that are capable of sending and receiving data via email and applications.

[1823] "Student learning progress data" refers to data that shows the results, evaluations, level of understanding, and progress that students have achieved during the learning process, and is important information for understanding the progress of learning based on this data.

[1824] A "correct answer key" is a standard set of answers that indicates the correct answers in tests and workbooks, and serves as a standard for evaluating and grading learning.

[1825] "Grades" are numerical values ​​or evaluations that quantitatively show academic achievement, and are calculated based on factors such as test results and evaluations of submitted work.

[1826] "Supplementary materials" are educational resources added to deepen understanding of existing materials, and include additional problems, exercises, and activities.

[1827] An "activity" is a practical activity or exercise designed to support students' learning and to reinforce the learning content.

[1828] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade student response data and notify teachers of their grades on their terminals, to analyze student learning progress data and provide supplementary materials and activities, to analyze individual student learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[1829] The basic configuration of the system is as follows:

[1830] 1. Automatic generation and distribution of educational materials

[1831] The server connects to the educational institution's curriculum database and retrieves the latest curriculum information. Based on this curriculum information, it automatically generates teaching materials using a generative AI model. Specifically, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics" and sends a prompt message to the generative AI model saying, "Please generate a basic algebra problem set for Junior High School 2nd Year Mathematics." The generated teaching materials are sent to the teacher's terminal in PDF or link format, and the teacher reviews the received materials and distributes them to students.

[1832] 2. Automated scoring and grade notification

[1833] The server collects answer data submitted from students' devices. Based on this data, a generative AI model is used to match it with the correct answer key and perform automatic scoring. For example, the server receives answer data for a math test and sends a prompt message to the generative AI model saying, "Please score the math test answer data." The generative AI model calculates a score for each answer and notifies the teacher's device of the result. The teacher then reviews the score and provides feedback to the students.

[1834] 3. Learning support functions

[1835] The server periodically collects learning progress data from students' devices. This data is analyzed by a generative AI model to identify learning trends and areas where students are lacking. For example, a prompt message such as "Generate supplementary materials based on student B's learning progress data" is sent to the generative AI model, which then generates additional practice problems and materials. The generated materials are sent to the teacher's and student's devices, and the teacher uses them to provide instruction.

[1836] 4. Analysis and suggestions regarding learning progress

[1837] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. This provides a function to suggest the optimal learning approach. For example, the server might send a prompt to the generative AI model saying, "Suggest the optimal learning approach based on student C's learning history," and the generative AI model might suggest a lesson that makes extensive use of visual aids. This suggestion is then notified to the teacher's terminal, and the teacher can incorporate it into their teaching methods.

[1838] 5. Creating an Individualized Education Plan

[1839] The server collects student learning needs data and uses a generative AI model to generate individualized learning plans. For example, it might send a prompt message to the generative AI model saying, "Generate an individualized learning plan based on student D's learning needs data." The generated plan is optimized and sent to the teacher's and student's devices. The teacher then uses the plan to provide appropriate instruction.

[1840] 6. Suggestions for improving the educational process

[1841] The server collects data on the educational process and analyzes it using a generative AI model. Based on this, it creates suggestions for improving the educational process and curriculum. For example, it might send a prompt message to the generative AI model such as, "Please suggest improvements to the curriculum based on school-wide lesson evaluation data," to identify areas for improvement and generate suggestions. These suggestions are then notified to teachers' terminals and used by teachers to adjust lesson content.

[1842] As described above, the present invention, by utilizing a generated AI model and prompt text, can reduce the workload of teachers in educational settings and provide optimal educational support to each student. This makes it possible to improve the quality of education.

[1843] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1844] Step 1: Obtain curriculum information

[1845] Server: Connects to the curriculum database and retrieves the latest curriculum information. As a specific example, it retrieves curriculum information for "Junior High School 2nd Year Mathematics" from the database.

[1846] Input: Target grade and subject (e.g., 2nd year of junior high school, mathematics)

[1847] Output: Curriculum information (e.g., Fundamentals of Algebra, Fundamentals of Geometry)

[1848] Step 2: Sending prompts to the generative AI model

[1849] Server: Based on the acquired curriculum information, it sends appropriate prompts to the generating AI model. For example, it sends the prompt, "Please generate a basic algebra problem set for 2nd year junior high school mathematics."

[1850] Input: Curriculum information (e.g., Basic Algebra)

[1851] Output: Prompt message (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[1852] Step 3: Generating the teaching materials

[1853] Generative AI Model: Automatically generates educational materials based on the submitted prompt text. As a specific example, it generates a set of problems related to "Basic Algebra."

[1854] Input: Prompt text (Example: "Generate a basic algebra problem set for 2nd year junior high school students")

[1855] Output: Generated learning materials (e.g., a workbook in PDF format)

[1856] Step 4: Send the generated materials

[1857] Server: Sends the generated teaching materials to the teacher's terminal. For example, it sends a PDF file to the teacher's email address.

[1858] Input: Generated learning materials (e.g., a workbook in PDF format)

[1859] Output: Notification to the teacher's terminal and transmission of teaching materials (e.g., email transmission)

[1860] Step 5: Collecting response data

[1861] Server: Collects response data submitted from students' devices. For example, it retrieves response data submitted by students from an online testing platform.

[1862] Input: Student response data (e.g., response data in JSON format)

[1863] Output: Saving collected response data (e.g., storing in a database)

[1864] Step 6: Scoring of response data

[1865] Server: Using an AI model, the server automatically scores collected answer data by comparing it to the correct answer key. For example, it calculates the score for each question in a math test by comparing it to the correct answer key.

[1866] Input: Collected response data and correct answer key (e.g., response data in JSON format and answer set)

[1867] Output: Graded performance data (e.g., CSV file containing graded results)

[1868] Step 7: Notification of Grades

[1869] Server: Notifies teachers of grading results on their terminals. For example, it might compile the grading results into an Excel file and send it to the teacher's email address.

[1870] Input: Graded grade data (e.g., a CSV file containing graded results)

[1871] Output: Notification to the teacher's terminal and transmission of grade data (e.g., email transmission)

[1872] Step 8: Collecting learning progress data

[1873] Server: Regularly collects learning progress data from students' devices. For example, it saves students' daily learning logs to a cloud server.

[1874] Input: Student learning progress data (e.g., learning log data)

[1875] Output: Saving collected learning progress data (e.g., storing in a database)

[1876] Step 9: Analyze learning progress data

[1877] Server: Uses a generative AI model to analyze collected learning progress data. Specifically, it detects learning trends and areas of weakness in specific subjects or fields.

[1878] Input: Collected learning progress data (e.g., learning log data)

[1879] Output: Analysis results (e.g., identification of areas with deficiencies)

[1880] Step 10: Generating supplementary materials and activities

[1881] Server: Based on the analysis results, it sends prompt messages to the generating AI model to generate supplementary materials and activities. For example, it sends the prompt message, "Please generate additional problems for solving word problems."

[1882] Input: Analysis results and prompt message (e.g., "Generate teaching materials to cover the missing sections")

[1883] Output: Generated supplementary materials (e.g., PDF file of practice problems)

[1884] Step 11: Sending supplementary materials

[1885] Server: Sends the generated supplementary materials to the teacher's and students' devices. For example, it sends a link to practice problems via email.

[1886] Input: Generated supplementary materials (e.g., PDF file of practice problems)

[1887] Output: Notifications to teacher and student devices and delivery of educational materials (e.g., email).

[1888] Step 12: Collecting Learning History

[1889] Server: Regularly collects students' learning history and performance data. Specifically, it collects students' test results and classroom performance data.

[1890] Input: Student learning history and performance data (e.g., test result data)

[1891] Output: Storage of collected learning history and performance data (e.g., storage in a database)

[1892] Step 13: Proposing a Learning Approach

[1893] Server: Using a generative AI model, it analyzes learning history and performance data in detail to propose the optimal learning approach. For example, it might generate a suggestion that "lessons that heavily utilize visual materials are effective."

[1894] Input: Learning history and performance data (e.g., test result data)

[1895] Output: Proposal of the optimal learning approach (e.g., a report including the proposal)

[1896] Step 14: Notification of Proposal

[1897] Server: Notifies the instructor's terminal of the proposed content. For example, it sends a report containing the proposed content via email in PDF format.

[1898] Input: Proposal of the optimal learning approach (e.g., a report including the proposed approach)

[1899] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[1900] Step 15: Collecting Educational Process Data

[1901] Server: Collects data related to the educational process. Specifically, it regularly collects lesson evaluation data and teacher feedback.

[1902] Input: Educational process data (e.g., course evaluation data)

[1903] Output: Storage of collected educational process data (e.g., storage in a database)

[1904] Step 16: Create proposals for improving the educational process.

[1905] Server: Uses a generative AI model to analyze collected educational process data and generate specific improvement suggestions. For example, it generates a suggestion to "increase reading and writing time."

[1906] Input: Analysis results of educational process data (e.g., analysis results of lesson evaluation data)

[1907] Output: Improvement suggestions (e.g., a report including the suggested content)

[1908] Step 17: Notification of improvement suggestions

[1909] Server: Notifies teachers of the created improvement suggestions on their terminals. For example, it sends a report containing the suggestions via email in PDF format.

[1910] Input: Improvement suggestion (e.g., a report including the suggestion)

[1911] Output: Notification to the teacher's terminal and sending of reports (e.g., sending via email)

[1912] The above processing steps represent the specific operational flow of this system. This will reduce the workload of teachers and enable the provision of optimal educational support to each individual student.

[1913] (Application Example 1)

[1914] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1915] In recent years, teacher shortages and a decline in the quality of education have become serious problems in the education sector. This problem significantly impacts educational effectiveness, particularly because it makes it difficult to provide detailed, individualized instruction to each student. Furthermore, providing learning materials and plans tailored to individual learning needs is challenging, and conventional educational support systems require more efficient solutions. Additionally, improving the quality of educational content sales and user experience in virtual stores presents significant challenges.

[1916] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1917] In this invention, the server includes means for acquiring curriculum information, means for generating educational content based on the curriculum information, means for transmitting the generated educational content to a terminal, means for recommending educational content based on the user's learning history, means for collecting user learning progress data and tracking progress, and means for generating individualized educational plans based on the user's learning needs. This makes it possible to provide detailed educational support that addresses individual learning needs while also addressing teacher shortages and the problem of declining educational quality. Furthermore, by applying this system to a virtual store, it is possible to improve the sales efficiency of educational content and the quality of the user experience.

[1918] "Curriculum information" refers to information that details the learning content, objectives, and lesson plans set by an educational institution.

[1919] "Educational content" refers to information used for educational purposes, such as textbooks, workbooks, and supplementary materials provided to learners.

[1920] "Terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers and students.

[1921] "Learning history" refers to data that records the learning activities and results that individual students have undertaken to date.

[1922] "Progress tracking" is a method of monitoring and recording learners' learning progress in real time and reporting their status as it occurs.

[1923] An "individualized learning plan" is an optimal learning plan tailored to each student's learning needs and progress.

[1924] A "generative AI model" is a model that uses artificial intelligence to create new information, and is particularly used to automatically generate educational materials and learning plans.

[1925] A "prompt statement" is an input statement used to elicit a specific response from a generative AI model.

[1926] This invention relates to a system that uses an educational support system to automatically generate and distribute educational content based on curriculum information and to provide learning plans tailored to individual learning needs. The system's hardware includes servers, a high-performance server farm, terminals (smartphones, tablets, computers), and head-mounted displays. The software utilizes educational support AI, educational data analysis AI, generative AI models (e.g., GPT-4), and a virtual reality engine (e.g., Unity).

[1927] Program Outline

[1928] 1. Acquisition of curriculum information and generation of educational content

[1929] The server retrieves curriculum information from a database and generates educational content using a generative AI model (GPT-4) based on that information. For example, it retrieves curriculum information for second-year junior high school mathematics and generates a workbook on "Basic Algebra." An example of the prompt used in this process is, "Generate educational content based on curriculum information. Second-year junior high school mathematics: Basic Algebra." The generated educational content is then sent from the server to the terminal.

[1930] 2. Recommendation of educational content

[1931] Based on the user's learning history data, the server recommends the most suitable educational content for each individual user. In this case, a generative AI model is also used to provide appropriate recommendations. For example, a request is sent to the AI ​​with the prompt message, "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization."

[1932] 3. Tracking learning progress

[1933] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. Progress is tracked in real time, and the percentage of learning progress is calculated. For example, it may be reported in the format of "Learning progress rate: 70%".

[1934] 4. Generating an individualized education plan

[1935] The server collects the user's learning needs and uses a generative AI model to generate personalized learning plans. For example, it might use a prompt message like, "Generate an appropriate learning plan if the user is struggling to solve word problems." This generated plan is then sent to the terminal.

[1936] Specific example

[1937] The following outlines the specific steps of the present invention:

[1938] 1. The server retrieves curriculum information for "Junior High School 2nd Year Mathematics," and the generating AI model generates a set of problems on "Basic Algebra."

[1939] 2. The server analyzes the user's learning history and recommends the next most suitable content based on "basic algebra and factorization."

[1940] 3. Collect learning progress data and report "7 out of 10 items completed, progress rate 70%."

[1941] 4. Based on the learning needs analysis, the generating AI model generates "additional problems for solving word problems," and an individualized education plan is generated.

[1942] Thus, the present invention enables personalized and effective educational support in educational settings and virtual stores.

[1943] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1944] Step 1:

[1945] The server retrieves curriculum information from the database. This curriculum information includes grade level, subject, and learning content. This curriculum information is used as input to generate educational content. For example, the server retrieves curriculum information for "Junior High School 2nd Year Mathematics: Basic Algebra."

[1946] Step 2:

[1947] Based on the curriculum information acquired by the server, a prompt message is sent to the generation AI model. The specific prompt message is "Generate educational content based on the curriculum information. Junior High School 2nd Year Mathematics: Basic Algebra." The generation AI model takes this prompt message as input and generates the corresponding educational content (such as a workbook).

[1948] Step 3:

[1949] The server sends the generated educational content to the device. The device displays the content so that teachers and students can access it. The generated educational content is delivered to the device, and users can review and use it.

[1950] Step 4:

[1951] The server collects the user's learning history. The collected learning history data includes content already studied and their performance on it. This data is used as input for data processing to identify the next educational content to recommend. For example, the learning history of "basic algebra" and "factorization" in mathematics is collected.

[1952] Step 5:

[1953] The server sends a prompt to the generating AI model based on the user's learning history data. The specific prompt is: "Recommend the most suitable educational content based on the user's learning history. math: basic algebra, factorization." The generating AI model then recommends the following appropriate educational content.

[1954] Step 6:

[1955] The server sends recommended educational content to the device. The device displays the recommended content in a user-friendly format. The user can review the recommended content and continue learning.

[1956] Step 7:

[1957] The server collects learning progress data from the user's device, and this data is analyzed by an educational data analysis AI. The collected data includes the number of completed assignments and the total number of assignments. This data is used as input to calculate the progress rate. For example, if 7 out of 10 items have been completed, the progress rate is 70%.

[1958] Step 8:

[1959] The server notifies the terminal of the progress. The terminal visually displays the progress to the user and guides them to the next learning step. The user can check the progress report and understand the remaining learning tasks.

[1960] Step 9:

[1961] The server collects the user's learning needs and sends a prompt to the generative AI model. The specific prompt is, "If the user is struggling to solve word problems, generate an appropriate learning plan." Based on this data, the generative AI model generates the optimal individualized learning plan.

[1962] Step 10:

[1963] The server sends the generated individualized learning plan to the device. The device displays the plan in a user-friendly format, providing it as a learning guide. The user can then proceed with their learning based on this learning plan.

[1964] By following the steps described above, the educational support system of the present invention can function smoothly and provide an effective educational experience for teachers and students.

[1965] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1966] This invention is a system that combines educational support AI, educational data analysis AI, and an emotion engine to solve the teacher shortage and decline in the quality of education in educational settings. This system includes the following functions:

[1967] 1. Automated creation of educational materials

[1968] The server accesses the curriculum database to retrieve the latest curriculum information. Based on this information, the AI ​​automatically generates teaching materials. The generated materials are sent from the server to the teacher's terminal. The teacher reviews the materials on their terminal and distributes them to students.

[1969] Specific example:

[1970] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra" and sends it to the teacher's terminal. The teacher then distributes the materials to the students.

[1971] 2. Scoring Tool

[1972] The server collects the answer data submitted by students from their devices, compares it against the correct answer key, and scores the answers. The grade data is sent from the server to the teacher's device. The teacher reviews the grades and provides feedback to the students.

[1973] Specific example:

[1974] The server collects student A's math test answers, matches them against the correct answer key, assigns a score of 90, and notifies the teacher's terminal of the result. The teacher then checks the grade.

[1975] 3. Learning support

[1976] The server periodically collects learning progress data from students' devices, and AI analyzes this data to identify areas where students are particularly struggling. Supplementary materials and activities are generated and sent to both teachers' and students' devices.

[1977] Specific example:

[1978] The server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[1979] 4. Analysis of learning progress and recommendations

[1980] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, the AI ​​proposes the optimal learning approach, and this information is sent to the teacher's terminal. The teacher then adjusts the lesson content based on the proposal.

[1981] Specific example:

[1982] The server collects student C's math learning history and suggests that "lessons that heavily utilize visual aids" would be effective, notifying the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[1983] 5. Creating an Individualized Education Plan

[1984] The server collects data on students' learning needs, and AI generates and optimizes individualized learning plans based on that data. The optimized learning plans are sent to the teachers' and students' devices. Teachers review the plans and provide appropriate instruction to students.

[1985] Specific example:

[1986] The server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[1987] 6. Suggestions for improving the educational process

[1988] The server collects data on the entire school's educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and notifies teachers of these improvements on their terminals. Teachers then revise their educational processes and curriculum based on the suggestions they receive.

[1989] Specific example:

[1990] The server analyzes the school-wide lesson evaluation data and proposes to "increase reading and writing time," then notifies teachers of this proposal. Teachers then adjust their lesson content based on the proposal.

[1991] 7. Utilizing the Emotional Engine

[1992] The server includes an emotion engine that recognizes user emotions and collects and analyzes user emotion data. Based on this data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials and relaxation activities.

[1993] Specific example:

[1994] The server collects emotional data from student E, and the AI ​​detects when the student is experiencing stress. Based on the analysis, it suggests relaxation exercises and sends them to the teacher's and student's devices. The teacher reviews the suggestions and instructs the student on additional relaxation activities.

[1995] 8. Utilization of teacher sentiment data

[1996] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[1997] Specific example:

[1998] The server collects emotional data from teacher F, and the AI ​​detects when the teacher is experiencing stress. Based on this, it sends suggestions to the teacher's terminal to help distribute tasks. The teacher then uses these suggestions to distribute tasks and reduce stress.

[1999] In summary, the present invention is a system that alleviates the shortage of teachers in educational settings, improves the quality of education, and further utilizes emotional data of students and teachers to provide optimal learning and guidance.

[2000] The following describes the processing flow.

[2001] Automated creation of educational materials

[2002] Step 1:

[2003] The server accesses the school's curriculum database to retrieve the latest curriculum information.

[2004] Step 2:

[2005] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[2006] Step 3:

[2007] The server sends the generated teaching material data to the teacher's terminal.

[2008] Step 4:

[2009] The teacher receives the teaching materials on a device and checks their contents.

[2010] Step 5:

[2011] The teacher will distribute the materials they have reviewed to the students, and the students will use the materials to study.

[2012] Scoring tool

[2013] Step 1:

[2014] The server collects the response data submitted from the students' devices.

[2015] Step 2:

[2016] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[2017] Step 3:

[2018] The server calculates each student's score and generates grade data.

[2019] Step 4:

[2020] The server sends the grade data to the teacher's terminal.

[2021] Step 5:

[2022] Teachers check grades on their devices and provide feedback to students.

[2023] Learning support

[2024] Step 1:

[2025] The server periodically collects learning progress data from students' devices.

[2026] Step 2:

[2027] The server collects progress data, which is then input into an AI model for analysis.

[2028] Step 3:

[2029] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[2030] Step 4:

[2031] The server automatically generates supplementary materials and activities.

[2032] Step 5:

[2033] The server sends the generated supplementary materials to the teachers' and students' devices.

[2034] Step 6:

[2035] Teachers use their devices to review supplementary materials and provide instruction to students.

[2036] Learning progress analysis and suggestions

[2037] Step 1:

[2038] The server collects students' learning history and performance data.

[2039] Step 2:

[2040] The server inputs the collected data into an AI model for detailed analysis.

[2041] Step 3:

[2042] The AI ​​proposes the optimal learning approach based on the analysis results.

[2043] Step 4:

[2044] The server notifies the teacher's terminal of the proposed content.

[2045] Step 5:

[2046] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[2047] Creating an individualized education plan

[2048] Step 1:

[2049] The server collects data related to students' learning needs.

[2050] Step 2:

[2051] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[2052] Step 3:

[2053] The AI ​​optimizes the educational plans it generates.

[2054] Step 4:

[2055] The server sends optimized lesson plans to teachers' and students' devices.

[2056] Step 5:

[2057] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[2058] Suggestions for improving the education process

[2059] Step 1:

[2060] The server collects data about the entire school's educational process.

[2061] Step 2:

[2062] The server collects data, which is then input into an AI model for analysis.

[2063] Step 3:

[2064] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[2065] Step 4:

[2066] The server will notify teachers' terminals of the identified areas for improvement.

[2067] Step 5:

[2068] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[2069] Utilizing the Emotion Engine

[2070] Step 1:

[2071] The server activates the emotion engine to collect user emotion data.

[2072] Step 2:

[2073] The emotion engine analyzes the user's facial expressions and behavioral data to generate emotion data.

[2074] Step 3:

[2075] The server inputs the generated emotion data into the AI ​​model, which then adjusts the learning materials and activities.

[2076] Step 4:

[2077] The server sends the prepared teaching materials and activities to the teachers' and students' devices.

[2078] Step 5:

[2079] Teachers check the adjustments on their devices and provide guidance to students.

[2080] Stress management using emotional data

[2081] Step 1:

[2082] The server collects emotional data from students and teachers.

[2083] Step 2:

[2084] AI analyzes emotional data to detect signs of stress.

[2085] Step 3:

[2086] The server generates supplementary materials and relaxation activities to help with stress management.

[2087] Step 4:

[2088] The server sends the generated supplementary materials and activities to the teachers' and students' devices.

[2089] Step 5:

[2090] Teachers use their devices to check supplementary materials and activities and provide instruction.

[2091] (Example 2)

[2092] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[2093] In the education sector, teacher shortages and a decline in the quality of education are serious problems. In particular, creating teaching materials tailored to the individual learning needs of students and providing appropriate feedback is difficult, which further contributes to the decline in quality. Furthermore, understanding the emotional states of students and teachers and responding appropriately based on that understanding is also challenging. A system is needed to solve these problems and improve the quality of education.

[2094] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[2095] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, and means for transmitting the generated teaching materials to teachers' terminals. This enables the automatic generation and distribution of teaching materials based on the latest curriculum. It also includes means for generating teaching materials using an AI model and means for sending instructions to the generation AI model using prompt statements, thereby enabling the efficient creation of high-quality teaching materials and improving the quality of education. Furthermore, it includes means for collecting and analyzing student and teacher emotional data using an emotion engine, allowing for the adjustment of teaching materials and activities to maximize learning effectiveness based on the analysis results, thus contributing to the improvement of educational quality from an emotional perspective as well.

[2096] "Curriculum information" refers to information that includes teaching objectives, content, and evaluation criteria within the educational curriculum.

[2097] "Learning materials" refer to materials and tools that learners use for their studies, and include textbooks, workbooks, reference books, and digital learning materials.

[2098] A "terminal" refers to a device used by a user to interact with a system, and includes personal computers, tablets, smartphones, and other similar devices.

[2099] An "AI model" is a model that uses artificial intelligence algorithms to perform a specific task, and includes, for example, generative AI models and analytical AI models.

[2100] A "prompt message" is text data used to provide specific instructions or input information to a generative AI model.

[2101] "Response data" refers to the answers that learners submit to tests and assignments.

[2102] A "correct answer key" is a reference data that indicates the correct answer to a test or assignment, and is used for grading and performance evaluation.

[2103] "Learning progress data" refers to data that shows how far a learner has progressed in their studies, and includes study time, progress rate, and level of understanding.

[2104] An "emotion engine" is an artificial intelligence system designed to recognize and analyze a user's emotional state, and includes features such as facial recognition, voice analysis, and text analysis.

[2105] "Feedback" refers to evaluation results and suggestions for improvement provided to learners and teachers, with the aim of improving learning methods and comprehension.

[2106] An "activity" refers to a specific activity or exercise performed while progressing through learning, and includes problem-solving games and experiments.

[2107] This invention is a system designed to address teacher shortages and declining quality of education in educational settings, and operates primarily through servers, terminals, and users. Specifically, it operates by combining the following functions.

[2108] 1. Acquisition of curriculum information and automatic generation of teaching materials

[2109] The server accesses the curriculum database to retrieve the latest curriculum information. Based on this information, the server automatically generates teaching materials using a generative AI model (e.g., "GPT-4"). The generated teaching materials are sent from the server to the teacher's terminal. The teacher then uses that terminal to review the materials and distribute them to students.

[2110] Specific example:

[2111] The server retrieves the curriculum for "Junior High School 2nd Year Mathematics" and sends the following prompt to the generating AI model to generate a set of problems on "Basic Algebra."

[2112] "Please create a workbook of basic algebra problems based on the curriculum for second-year junior high school mathematics."

[2113] 2. Scoring Tool

[2114] The server collects the answer data submitted by students from their devices and scores it by comparing it with the correct answer key. The correct answer key is stored in a database on the server. The scoring results are sent from the server to the teacher's device, where the teacher can check the grades and provide feedback to the students.

[2115] Specific example:

[2116] The server collects the answers to student A's math test and uses a generative AI model to grade them with the following prompt messages.

[2117] "Please compare Student A's answer with the correct answer key, grade it, and notify the teacher of the score." The result is a score of 90 points, which is then notified to the teacher.

[2118] 3. Learning support

[2119] The server periodically collects learning progress data from students' devices and analyzes it using a generative AI model. This identifies areas where students are particularly struggling and generates supplementary materials and activities. These are then sent to both teachers' and students' devices.

[2120] Specific example:

[2121] The server analyzes student B's progress data and uses a generating AI model to send the following prompt message, thereby generating "additional problems for solving word problems."

[2122] "Analyze student B's progress data and generate supplementary materials to address their weak areas." The teacher checks this on their device and provides instruction to the student.

[2123] 4. Analysis of learning progress and recommendations

[2124] The server collects students' learning history and performance data and analyzes it in detail using a generative AI model. Based on the analysis results, the optimal learning approach is proposed and notified to the teacher's terminal. The teacher adjusts the lesson content based on this proposal.

[2125] Specific example:

[2126] The server analyzes student C's math learning history and suggests that "lessons that heavily utilize visual aids" would be effective. This suggestion is sent to the teacher's terminal with the following prompt message.

[2127] "Analyze student C's learning history and propose the optimal learning approach."

[2128] 5. Creating an Individualized Education Plan

[2129] The server collects student learning needs data and uses a generative AI model to generate and optimize individualized learning plans. The optimized plans are sent to the teacher's and student's devices. Teachers review the plans and provide appropriate instruction to students.

[2130] Specific example:

[2131] The server analyzes student D's learning needs and generates a "reading and writing support program" by sending the following prompt message using a generative AI model.

[2132] "Generate and optimize an individualized learning plan based on student D's learning needs." The teacher will then provide appropriate instruction based on this plan.

[2133] 6. Suggestions for improving the educational process

[2134] The server collects data on the school's overall educational process and analyzes it using a generative AI model. Based on the data, it identifies areas for improvement in the educational process and curriculum, and notifies teachers of these improvements on their terminals. Teachers then revise their educational processes and curriculum based on the suggestions they receive.

[2135] Specific example:

[2136] The server analyzes the school-wide lesson evaluation data and sends the following prompt message using a generative AI model.

[2137] "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum." As a result, "increasing reading and writing time" is suggested and communicated to the teachers.

[2138] 7. Utilizing the Emotional Engine

[2139] The server includes an emotion engine that recognizes user emotions. User emotion data is collected on the server and analyzed by the emotion engine. Based on the user's emotion data, the emotion engine adjusts learning materials and activities to maximize learning effectiveness. It also detects signs of student stress and suggests appropriate supplementary materials or relaxation activities.

[2140] Specific example:

[2141] The server collects student E's emotional data and uses the emotional engine to send the following prompt message.

[2142] "Analyze student E's emotional data and suggest relaxation exercises to reduce stress." The teacher will then use this suggestion to instruct the student on additional relaxation activities.

[2143] 8. Utilization of teacher sentiment data

[2144] The Emotion Engine collects and analyzes teachers' emotional data and provides suggestions to help manage their stress. Based on this emotional data, it offers approaches to reduce their workload.

[2145] Specific example:

[2146] The server collects teacher F's emotional data and uses the emotion engine to send the following prompt message.

[2147] "Analyze teacher F's emotional data and propose approaches to reduce their workload." Based on these proposals, the teacher will distribute tasks and reduce stress.

[2148] As described above, the system of the present invention not only alleviates the shortage of teachers in educational settings and improves the quality of education, but also makes it possible to provide optimal learning and guidance by utilizing emotional data of students and teachers.

[2149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2150] Automated creation of educational materials

[2151] Step 1:

[2152] The server accesses the curriculum database.

[2153] input:

[2154] Request to access the curriculum database

[2155] Data processing:

[2156] Execute a query to extract curriculum information.

[2157] output:

[2158] Latest curriculum information

[2159] Specific actions:

[2160] The server sends a query to the curriculum database with the condition "Junior High School 2nd Year Mathematics" and retrieves the corresponding curriculum information.

[2161] Step 2:

[2162] The server inputs the acquired curriculum information into a generating AI model.

[2163] input:

[2164] Latest curriculum information

[2165] Data processing:

[2166] Convert curriculum information into prompt messages

[2167] output:

[2168] Instruction prompts for the AI ​​model

[2169] Specific actions:

[2170] The server generates a prompt message, "Generate a set of problems on the basics of algebra based on the curriculum for second-year junior high school mathematics," and sends it to the AI ​​model.

[2171] Step 3:

[2172] The AI ​​model automatically generates educational materials.

[2173] input:

[2174] Instruction prompt message

[2175] Data processing:

[2176] Creating educational materials using generative AI models

[2177] output:

[2178] Automatically generated teaching materials

[2179] Specific actions:

[2180] A generative AI model (e.g., GPT-4) generates a set of problems on fundamental algebraic concepts based on a prompt.

[2181] Step 4:

[2182] The server sends the generated teaching materials to the teacher's terminal.

[2183] input:

[2184] Automatically generated teaching materials

[2185] Data processing:

[2186] Preparing to send teaching material data

[2187] output:

[2188] Sending teaching materials data to teachers' devices

[2189] Specific actions:

[2190] The server converts the generated teaching materials into PDF format and sends them to the teacher's terminal.

[2191] Scoring tool

[2192] Step 1:

[2193] Students submit their answers to the server from their devices.

[2194] input:

[2195] Student response data

[2196] Data processing:

[2197] Collection of response data

[2198] output:

[2199] Response data sent to the server

[2200] Specific actions:

[2201] The student clicks the "end" button on the online test, and the answer data is uploaded to the server.

[2202] Step 2:

[2203] The server compares the response data with the correct key.

[2204] input:

[2205] Student response data, correct answer key

[2206] Data processing:

[2207] Scoring by comparison

[2208] output:

[2209] Scoring results

[2210] Specific actions:

[2211] The server compares student A's answer data with the correct answer key previously stored in the database and calculates the score.

[2212] Step 3:

[2213] The server notifies the teacher's terminal of the grading results as grades.

[2214] input:

[2215] Scoring results

[2216] Data processing:

[2217] Preparing to send result data

[2218] output:

[2219] Grade notification to the teacher's device

[2220] Specific actions:

[2221] The server notifies teachers of the grading results in real time on their terminals, allowing teachers to review them and provide feedback to students.

[2222] Learning support

[2223] Step 1:

[2224] Students' devices send learning progress data to the server.

[2225] input:

[2226] Student learning progress data

[2227] Data processing:

[2228] Collection of progress data

[2229] output:

[2230] Progress data sent to the server

[2231] Specific actions:

[2232] Students record their daily learning progress using a learning app, and this information is automatically sent to a server.

[2233] Step 2:

[2234] The server inputs progress data into the AI ​​model.

[2235] input:

[2236] Student learning progress data

[2237] Data processing:

[2238] Generating prompts for analyzing progress data

[2239] output:

[2240] Analysis prompts for AI models

[2241] Specific actions:

[2242] The server generates a prompt message saying, "Analyze student B's progress data and generate supplementary materials to address their weak areas," and sends it to the AI ​​model.

[2243] Step 3:

[2244] The generative AI model generates supplementary materials and activities.

[2245] input:

[2246] Analysis prompt message

[2247] Data processing:

[2248] Generating supplementary materials and activities

[2249] output:

[2250] Supplementary materials and activities that are generated

[2251] Specific actions:

[2252] The generative AI model generates "additional problems for solving word problems" based on the prompt text.

[2253] Step 4:

[2254] The server sends the generated supplementary materials to the teachers' and students' devices.

[2255] input:

[2256] Supplementary materials and activities that are generated

[2257] Data processing:

[2258] Preparing to send teaching material data

[2259] output:

[2260] Sending teaching materials data to teachers' and students' devices

[2261] Specific actions:

[2262] The server converts supplementary materials into PDF format and sends them to the teacher's and students' devices. The teacher reviews them and provides instruction to the students.

[2263] Learning progress analysis and suggestions

[2264] Step 1:

[2265] The server collects students' learning history and performance data.

[2266] input:

[2267] Student learning history and performance data

[2268] Data processing:

[2269] Data collection

[2270] output:

[2271] Learning history and performance data collected on the server

[2272] Specific actions:

[2273] The server periodically collects student C's math learning data for the past six months.

[2274] Step 2:

[2275] The server inputs the learning history and performance data into the generated AI model.

[2276] input:

[2277] Student learning history and performance data

[2278] Data processing:

[2279] Generating prompts for analysis

[2280] output:

[2281] Analysis prompts for AI models

[2282] Specific actions:

[2283] The server generates a prompt message saying, "Analyze student C's learning history and suggest the optimal learning approach," and sends it to the AI ​​model.

[2284] Step 3:

[2285] Generative AI models analyze data in detail and propose the optimal learning approach.

[2286] input:

[2287] Analysis prompt message

[2288] Data processing:

[2289] Generating learning approach proposals

[2290] output:

[2291] Proposal details

[2292] Specific actions:

[2293] The generative AI model analyzes student C's data and generates a suggestion that "lessons that heavily utilize visual aids" are effective.

[2294] Step 4:

[2295] The server sends the proposal to the teacher's terminal.

[2296] input:

[2297] Proposal details

[2298] Data processing:

[2299] Preparing to send proposal data

[2300] output:

[2301] Sending proposal content to the teacher's terminal

[2302] Specific actions:

[2303] The server sends the proposed content to the teacher's terminal, and the teacher adjusts the lesson content to make extensive use of visual aids.

[2304] Creating an individualized education plan

[2305] Step 1:

[2306] Student devices send learning needs data to the server.

[2307] input:

[2308] Student learning needs data

[2309] Data processing:

[2310] Collection of needs data

[2311] output:

[2312] Needs data sent to the server

[2313] Specific actions:

[2314] Students record their special learning needs, and this information is sent to a server.

[2315] Step 2:

[2316] The server generates learning needs data and inputs it into the AI ​​model.

[2317] input:

[2318] Student learning needs data

[2319] Data processing:

[2320] Prompt message generation for plan generation

[2321] output:

[2322] Prompt for generating a plan for the AI ​​model

[2323] Specific actions:

[2324] The server generates a prompt message, "Generate and optimize an individualized learning plan based on student D's learning needs," and sends it to the AI ​​model.

[2325] Step 3:

[2326] The generative AI model generates and optimizes individualized educational plans.

[2327] input:

[2328] Plan generation prompt message

[2329] Data processing:

[2330] Generating and optimizing individualized education plans

[2331] output:

[2332] Generated Individual Education Plan

[2333] Specific actions:

[2334] The generative AI model generates and optimizes a "reading and writing support program" based on student D's data.

[2335] Step 4:

[2336] The server sends the generated individualized education plans to the teachers' and students' devices.

[2337] input:

[2338] Generated Individual Education Plan

[2339] Data processing:

[2340] Preparing to send plan data

[2341] output:

[2342] Sending plan data to teachers' and students' devices

[2343] Specific actions:

[2344] The server converts the generated lesson plan into PDF format and sends it to the teacher's and student's devices. The teacher then provides appropriate instruction based on the plan.

[2345] Suggestions for improving the education process

[2346] Step 1:

[2347] The server collects data about the entire school's educational process.

[2348] input:

[2349] Educational process data

[2350] Data processing:

[2351] Data collection

[2352] output:

[2353] Educational process data collected on the server

[2354] Specific actions:

[2355] The server collects school-wide lesson evaluation survey data.

[2356] Step 2:

[2357] The server inputs educational process data into the AI ​​model.

[2358] input:

[2359] Educational process data

[2360] Data processing:

[2361] Generating prompt messages for improvement suggestions

[2362] output:

[2363] Prompt for suggesting improvements to the AI ​​model

[2364] Specific actions:

[2365] The server generates a prompt message that reads, "Analyze the school-wide lesson evaluation data and suggest improvements to the teaching process and curriculum," and sends it to the AI ​​model.

[2366] Step 3:

[2367] The generative AI model analyzes data and suggests improvements to the educational process and curriculum.

[2368] input:

[2369] Improvement suggestion prompt message

[2370] Data processing:

[2371] Generating proposals for educational improvement

[2372] output:

[2373] Improvement proposal details

[2374] Specific actions:

[2375] The generative AI model analyzes the data and generates suggestions such as "increase reading and writing time."

[2376] Step 4:

[2377] The server sends the improvement suggestions to the teacher's terminal.

[2378] input:

[2379] Improvement proposal details

[2380] Data processing:

[2381] Preparing to send improvement suggestion data

[2382] output:

[2383] Sending proposal content to the teacher's terminal

[2384] Specific actions:

[2385] The server sends the proposal to the teacher's terminal, and the teacher adjusts the curriculum timetable to increase reading and writing time.

[2386] Utilizing the Emotion Engine

[2387] Step 1:

[2388] The user's device sends emotional data to the server.

[2389] input:

[2390] User sentiment data

[2391] Data processing:

[2392] Collection of emotional data

[2393] output:

[2394] Emotional data sent to the server

[2395] Specific actions:

[2396] The user records their emotional state on their device, and that information is sent to the server.

[2397] Step 2:

[2398] The server inputs emotional data into the emotion engine.

[2399] input:

[2400] Emotional data

[2401] Data processing:

[2402] Analysis of emotional data

[2403] output:

[2404] Analysis results regarding emotional state

[2405] Specific actions:

[2406] The server inputs emotional data into the emotion engine, which then performs analysis.

[2407] Step 3:

[2408] The emotion engine analyzes emotional data and adjusts supplementary materials and activities accordingly.

[2409] input:

[2410] Analysis results regarding emotional state

[2411] Data processing:

[2412] Adjusting teaching materials and activities

[2413] output:

[2414] Customized teaching materials and activities

[2415] Specific actions:

[2416] The emotion engine analyzes student E's data and suggests "relaxation exercises" if it detects a high stress level.

[2417] Step 4:

[2418] The server sends the adjusted learning materials and activities to the user.

[2419] input:

[2420] Customized teaching materials and activities

[2421] Data processing:

[2422] Preparing to send teaching material data

[2423] output:

[2424] Sending educational material data to the user's device

[2425] Specific actions:

[2426] The server sends the suggested content to the teacher's and student's devices, and the teacher then instructs them on relaxation activities.

[2427] Utilizing teacher sentiment data

[2428] Step 1:

[2429] Teachers send emotional data from their devices to the server.

[2430] input:

[2431] Teacher sentiment data

[2432] Data processing:

[2433] Collection of emotional data

[2434] output:

[2435] Emotional data sent to the server

[2436] Specific actions:

[2437] Teachers record their emotional state, and this information is sent to a server.

[2438] Step 2:

[2439] The server inputs emotional data into the emotion engine.

[2440] input:

[2441] Teacher sentiment data

[2442] Data processing:

[2443] Analysis of emotional data

[2444] output:

[2445] Analysis results regarding emotional state

[2446] Specific actions:

[2447] The server inputs emotional data into the emotion engine, which then performs analysis.

[2448] Step 3:

[2449] The emotion engine analyzes emotional data and generates stress management suggestions.

[2450] input:

[2451] Analysis results regarding emotional state

[2452] Data processing:

[2453] Generating stress management proposals

[2454] output:

[2455] Generated stress management proposals

[2456] Specific actions:

[2457] The emotion engine analyzes teacher F's data and generates suggestions for "dividing the workload."

[2458] Step 4:

[2459] The server sends the proposal to the teacher's terminal.

[2460] input:

[2461] Generated stress management proposals

[2462] Data processing:

[2463] Preparing to send proposal data

[2464] output:

[2465] Sending proposal content to the teacher's terminal

[2466] Specific actions:

[2467] The server sends the proposed content to the teachers' terminals, and based on the proposals, tasks are divided and stress is reduced.

[2468] Through the above processing steps, the system of the present invention alleviates the shortage of teachers in educational settings, improves the quality of education, and provides optimal learning and guidance by utilizing emotional data.

[2469] (Application Example 2)

[2470] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[2471] Teacher shortages and declining quality of education are significant challenges in the modern educational environment. Efficient training and education of new operators in factories are also crucial. Traditional methods place an excessive burden on teachers and trainers, risking a decline in the quality of education. Furthermore, inadequate stress management among operators makes effective training difficult. This invention provides a system to solve these problems.

[2472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[2473] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials based on the curriculum information, means for transmitting the generated teaching materials to a teacher's terminal, means for automatically generating training materials based on factory operating procedures and safety guidelines, means for providing the generated training materials to an operator's terminal, means for collecting operator progress data and emotional data, and means for analyzing the progress data and emotional data and suggesting relaxation exercises if stress is detected. This makes it possible to alleviate teacher shortages and the decline in the quality of education, as well as manage operator stress.

[2474] "Curriculum information" refers to information about learning content and teaching policies established for educational purposes.

[2475] "Educational materials" refer to materials and content used to achieve specific educational objectives.

[2476] A "terminal" is a device used to communicate with a server and receive information.

[2477] "Operating procedures" refer to the steps and methods for correctly performing tasks and operations in a factory.

[2478] "Safety guidelines" are standards and guidelines for performing work safely within a factory.

[2479] "Training materials" are educational materials used to acquire specific skills or knowledge.

[2480] An "operator" is a worker who operates machinery and equipment in a factory or work site.

[2481] "Progress data" refers to information about the progress of learning or work.

[2482] "Emotional data" refers to information about an individual's emotional state.

[2483] "Relaxation exercise" refers to activities and movements designed to reduce stress and promote mental and physical relaxation.

[2484] "Outcome data" refers to information about grades and performance obtained as a result of education or training.

[2485] "Stress" refers to a reaction or state of tension to physical, psychological, or environmental factors.

[2486] "Feedback" refers to evaluations and advice given regarding the results of learning or work.

[2487] "Educational methods" refer to the methods and means used to effectively carry out educational activities.

[2488] This invention is a system that combines educational support AI, educational data analysis AI, and an emotion engine to address teacher shortages and declining quality of education in educational settings. It can also be applied to training and educational support for new operators in factories. The following provides a detailed description of the system that realizes this application.

[2489] Hardware configuration

[2490] server:

[2491] The server plays a central role in managing curriculum information, factory operating procedures, and safety guidelines, and in automatically generating educational materials. It also includes a database for collecting and analyzing student and operator progress and sentiment data.

[2492] Terminal:

[2493] The devices include tablets and personal computers for teachers and operators. These devices are used to receive generated teaching materials and feedback.

[2494] Emotion sensor:

[2495] The emotion sensor is a sensor used to collect emotional data from operators and students. This allows for appropriate responses if stress is detected.

[2496] Software Configuration

[2497] Educational support AI:

[2498] The educational support AI automatically generates teaching materials and training materials based on curriculum information and factory operating procedures. The generated materials are then sent to the terminals of teachers and operators.

[2499] AI for educational data analysis:

[2500] The educational data analysis AI analyzes progress and performance data from students and operators. This allows it to identify learning trends and areas of weakness, and then suggest optimal teaching methods and supplementary materials.

[2501] Emotional engine:

[2502] The emotion engine collects and analyzes emotional data from students and operators. Based on this, if stress is detected, it suggests relaxation exercises or other responses.

[2503] Processing flow

[2504] 1. Automated creation of educational materials:

[2505] The server retrieves curriculum information, factory operating procedures, and safety guidelines, and uses educational support AI to automatically generate teaching materials and training materials.

[2506] 2. Provision of generated teaching materials:

[2507] The generated teaching materials and training materials are sent to terminals for instructors and operators and provided to users.

[2508] 3. Collection and analysis of progress data and sentiment data:

[2509] The server collects progress and emotional data from students and operators, and analyzes it using educational data analysis AI and an emotional engine.

[2510] 4. Feedback and suggestions for additional materials:

[2511] Based on the analysis results, optimal teaching methods and supplementary materials are suggested and sent to terminals for teachers and operators. If stress is detected, relaxation exercises are suggested.

[2512] Specific example

[2513] For example, if a factory robot is training a new operator on "wiring a power distribution panel," the robot automatically generates training materials based on operating procedures and safety guidelines and provides them to the operator's tablet. Once the operator completes the training, the robot collects progress data and emotional data and sends it to a server. An AI for analyzing educational data evaluates the progress, and an emotional engine determines whether or not stress is present. Additional supplementary materials or relaxation exercises are suggested as needed.

[2514] Example of a prompt

[2515] "Automatically generate training materials for new operators to learn how to wire distribution panels. Also, analyze training progress and operator emotional data, and suggest necessary additional materials and relaxation exercises."

[2516] This system will help address teacher shortages and the decline in the quality of education, as well as enable efficient training and stress management for operators.

[2517] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2518] Step 1:

[2519] The server retrieves curriculum information, factory operating procedures, and safety guidelines. This information is collected as input data and used in the following steps.

[2520] Input: Curriculum information, operating procedures, safety guidelines

[2521] Output: Acquired curriculum information and guideline data

[2522] Step 2:

[2523] The educational support AI automatically generates teaching materials and training materials based on the curriculum information and operating procedures acquired in the previous step. The generated materials are diverse and include text, video, and interactive content.

[2524] Input: Curriculum information, operating procedures, safety guidelines

[2525] Data processing: Generating educational materials using AI models.

[2526] Output: Generated teaching materials, training materials

[2527] Step 3:

[2528] The generated teaching materials and training materials are sent to terminals for instructors and operators. Users can then view these materials on their terminals and conduct their learning or training.

[2529] Input: Generated teaching materials, training materials

[2530] Output: Provided teaching materials and training materials (on the device)

[2531] Specific operation: Sending data from the server to the terminal.

[2532] Step 4:

[2533] Users perform training and learning using their devices, and progress data and emotional data are collected. Data is collected from emotional sensors, usage logs, test results, etc.

[2534] Input: User's action progress, sentiment data

[2535] Output: Progress data, sentiment data (sent to the server)

[2536] Specific actions: Real-time collection of progress and sentiment data.

[2537] Step 5:

[2538] The server passes the collected progress and emotional data to the educational data analysis AI and emotion engine for analysis. This analysis includes identifying areas of difficulty and stress levels.

[2539] Input: Progress data, sentiment data

[2540] Data processing: AI-based progress analysis and sentiment analysis.

[2541] Output: Analysis results (issue areas, stress levels, etc.)

[2542] Step 6:

[2543] The educational data analysis AI generates supplementary materials and activities based on the progress analysis results, and the server sends the generated supplementary materials and relaxation exercises to terminals for teachers and operators.

[2544] Input: Progress analysis results, city situation analysis results

[2545] Data processing: Generation of supplementary materials and relaxation exercises.

[2546] Output: Generated supplementary materials, relaxation exercises (sent to the device)

[2547] Specific operation: Sending additional learning materials from the server to the terminal.

[2548] Step 7:

[2549] Teachers and operators can access and apply supplementary materials and relaxation exercises on their devices. This helps improve comprehension and reduce stress.

[2550] Input: Supplementary materials, relaxation exercises

[2551] Output: Application results (user progress and emotional changes)

[2552] Specific actions: The user completes the instructed learning materials and exercises.

[2553] Through the steps described above, the system of this invention can achieve effective educational support, operator training, and stress management.

[2554] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2555] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2556] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[2557] [Fourth Embodiment]

[2558] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[2559] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2560] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2561] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[2562] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[2563] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[2564] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[2565] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[2566] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[2567] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[2568] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2569] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[2570] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2571] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the quality of education in schools. This system includes functions to automatically generate teaching materials based on curriculum information and send them to teachers' terminals, to collect and grade response data and notify teachers of their grades on their terminals, to analyze students' learning progress data and provide supplementary materials and activities, to analyze individual students' learning history and performance data and propose the optimal learning approach, to generate and optimize individual educational plans based on learning needs, and to propose improvements to the educational process.

[2572] 1. Automated creation of educational materials

[2573] The server retrieves the latest curriculum information from the curriculum database and automatically generates teaching materials based on that information. For example, the server retrieves the curriculum for "Junior High School 2nd Year Mathematics," and the AI ​​generates a workbook on "Basic Algebra." The server then sends the generated teaching materials to the teacher's terminal, and the teacher distributes the materials to the students.

[2574] 2. Scoring Tool

[2575] The server collects answer data submitted from students' devices and scores it by comparing it to the correct answer key. For example, the server collects answer data for a math test, and the AI ​​compares it to the correct answer key and scores it at 90 points. The result is then notified to the teacher's device as grade data, and the teacher can check the grade.

[2576] 3. Learning support

[2577] The server periodically collects student learning progress data, and AI analyzes this data. It identifies students' learning trends and areas where they are lacking, and generates supplementary materials and activities. For example, the server analyzes student B's progress data, generates "additional problems for solving word problems," and sends them to the teacher's and student's devices. The teacher reviews the supplementary materials and provides instruction to the student.

[2578] 4. Analysis of learning progress and recommendations

[2579] The server collects students' learning history and performance data, which are then analyzed in detail by AI. Based on the analysis, it proposes the optimal learning approach and notifies the teacher of the proposal on their terminal. For example, the server collects student C's math learning history and suggests that "lessons using a lot of visual aids" would be effective, and notifies the teacher of this suggestion on their terminal. The teacher then adjusts the lesson content based on the suggestion.

[2580] 5. Creating an Individualized Education Plan

[2581] The server collects data on students' learning needs, and AI generates individualized educational plans based on that data. The generated plans are then optimized and sent to the teacher's and student's devices. For example, the server analyzes student D's learning needs, generates and optimizes a "reading and writing support program," and sends it to the teacher's and student's devices. The teacher reviews the plan and provides appropriate instruction to the student.

[2582] 6. Suggestions for improving the educational process

[2583] The server collects data on the educational process, and AI analyzes that data. Based on the data, it identifies areas for improvement in the educational process and curriculum, and creates detailed improvement suggestions. These suggestions are then notified to teachers' terminals, and teachers consider them. For example, the server analyzes school-wide lesson evaluation data and suggests "increasing reading and writing time," and notifies teachers of this suggestion. Teachers then adjust their lesson content based on the suggestion.

[2584] This invention reduces the workload of teachers while simultaneously providing optimal educational support to each student, thereby improving the overall quality of the educational environment.

[2585] The following describes the processing flow.

[2586] Automated creation of educational materials

[2587] Step 1:

[2588] The server accesses the curriculum database to retrieve the latest curriculum information.

[2589] Step 2:

[2590] The server inputs curriculum information into an AI model, which then automatically generates teaching materials.

[2591] Step 3:

[2592] The server sends the generated teaching material data to the teacher's terminal.

[2593] Step 4:

[2594] The teacher receives the teaching materials on a device and checks their contents.

[2595] Step 5:

[2596] The teacher distributes teaching materials to the students, and the students use the materials to study.

[2597] Scoring tool

[2598] Step 1:

[2599] The server collects the response data submitted from the students' devices.

[2600] Step 2:

[2601] The server compares the answer data with the correct answer key to determine whether each question is correct or incorrect.

[2602] Step 3:

[2603] The server calculates each student's score and generates grade data.

[2604] Step 4:

[2605] The server sends the grade data to the teacher's terminal.

[2606] Step 5:

[2607] Teachers check grades on their devices and provide feedback to students.

[2608] Learning support

[2609] Step 1:

[2610] The server periodically collects learning progress data from students' devices.

[2611] Step 2:

[2612] The server collects progress data, which is then input into an AI model for analysis.

[2613] Step 3:

[2614] Based on the analysis results, the AI ​​identifies the areas in which students are particularly weak.

[2615] Step 4:

[2616] The server automatically generates supplementary materials and activities.

[2617] Step 5:

[2618] The server sends the generated supplementary materials to the teachers' and students' devices.

[2619] Step 6:

[2620] Teachers use their devices to review supplementary materials and provide instruction to students.

[2621] Learning progress analysis and suggestions

[2622] Step 1:

[2623] The server collects students' learning history and performance data.

[2624] Step 2:

[2625] The server inputs the collected data into an AI model for detailed analysis.

[2626] Step 3:

[2627] The AI ​​identifies the optimal learning approach based on the analysis results.

[2628] Step 4:

[2629] The server notifies the teacher's terminal of the proposed content.

[2630] Step 5:

[2631] Teachers review the proposed changes and adjust the lesson content and learning methods accordingly.

[2632] Creating an individualized education plan

[2633] Step 1:

[2634] The server collects data related to students' learning needs.

[2635] Step 2:

[2636] The server inputs the collected data into an AI model, which then automatically generates individualized educational plans.

[2637] Step 3:

[2638] The AI ​​optimizes the educational plans it generates.

[2639] Step 4:

[2640] The server sends optimized lesson plans to teachers' and students' devices.

[2641] Step 5:

[2642] Teachers can check lesson plans on their devices and provide appropriate guidance to students.

[2643] Suggestions for improving the education process

[2644] Step 1:

[2645] The server collects data about the entire school's educational process.

[2646] Step 2:

[2647] The server collects data, which is then input into an AI model for analysis.

[2648] Step 3:

[2649] Based on the analysis results, AI identifies areas for improvement in educational processes and curricula.

[2650] Step 4:

[2651] The server will notify teachers' terminals of the identified areas for improvement.

[2652] Step 5:

[2653] Teachers will review the improvement suggestions they receive and revise their teaching processes and curriculum.

[2654] (Example 1)

[2655] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2656] In today's education system, teacher shortages and a decline in the quality of education are serious problems. In addition, providing individualized instruction to each student and preparing diverse teaching materials is often difficult. As a result, education is becoming more homogenized, and the individual learning needs of students cannot be met. To solve these problems, effective and efficient creation and distribution of teaching materials, automated grading, and individualized instruction based on students' progress are required.

[2657] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[2658] In this invention, the server includes means for acquiring curriculum information, means for automatically generating teaching materials using a generation AI model based on the curriculum information, means for sending prompt messages to the generation AI model to generate teaching materials, and means for transmitting the generated teaching materials to the teacher's information terminal. This reduces the workload of teachers and enables optimal educational support tailored to the learning needs of each student.

[2659] "Curriculum information" refers to educational data that includes detailed information such as the content of lessons, learning objectives, teaching materials, and progress schedules set by educational institutions.

[2660] A "generative AI model" is an artificial intelligence technique that learns from large amounts of data and automatically generates educational materials and problem sets according to specific instructions.

[2661] A "prompt message" is text data used to give specific instructions to a generative AI model, and it plays a role in prompting the generation of educational materials and problem sets.

[2662] "Teaching materials" refer to educational materials used to support students' learning, and include textbooks, workbooks, supplementary materials, and other similar items.

[2663] "Teacher information terminals" refer to electronic devices such as computers, tablets, and smartphones used by teachers that are capable of sending and receiving data via email and applications.

[2664] "Student learning progress data" refers to data that shows the results, evaluations, level of understanding, and progress that students have achieved during the learning process, and is important information for understanding the progress of learning based on this data.

[2665] A "correct answer key" is a standard set of answers that indicates the correct answers in tests and workbooks, and serves as a standard for evaluating and grading learning.

[2666] "Grades" are numerical values ​​or evaluations that quantitatively show academic achievement, and are calculated based on factors such as test results and evaluations of submitted work.

[2667] "Supplementary materials" are educational resources added to deepen understanding of existing materials, and include additional problems, exercises, and activities.

[2668] An "activity" is a practical activity or exercise designed to support students' learning and to reinforce the learning content.

[2669] This invention is a system that utilizes educational support AI and educational data analysis AI to solve the teacher shortage and the decline in the qu...

Claims

1. Means of obtaining curriculum information, A means for automatically generating teaching materials based on the aforementioned curriculum information, A means of sending the generated teaching materials to the teacher's terminal, A system that includes this.

2. Means for collecting student response data, A means for comparing the aforementioned answer data with the correct answer key and scoring it, A means for notifying the teacher's terminal of the aforementioned scoring results as grades, The system according to claim 1, including the following:

3. A means of collecting student learning progress data, A means of analyzing the aforementioned learning progress data to identify students' learning trends and areas where they are lacking, A means for generating supplementary materials and activities based on the aforementioned analysis results, A means for transmitting the generated supplementary materials to the devices of teachers and students, The system according to claim 1, including the following:

4. A means of collecting students' learning history and performance data, A means for analyzing the aforementioned learning history and performance data, A means for proposing the optimal learning approach based on the aforementioned analysis results, A means of notifying the teacher's terminal of the aforementioned proposal, The system according to claim 1, including the following:

5. Means for collecting data related to students' learning needs, A means for generating individual education plans based on the aforementioned data, Means for optimizing the aforementioned education plan, A means of transmitting optimized educational plans to teachers' and students' devices, The system according to claim 1, including the following:

6. Means of collecting data on the educational process, A means of analyzing the aforementioned data to identify areas for improvement in the educational process and curriculum, A means of notifying the teacher of the aforementioned improvements via their terminal, The system according to claim 1, including the following:

Images