System

Abstract

A system is provided.SOLUTION: Means for notifying, by the student terminal, the server of the end of the test and transmitting answer data to the server, means for receiving, by the server, the answer data, checking the answer data against a standard answer database to automatically score the answer data, and storing a score result in the database, and means for identifying, by the server, an unanswered question from the answer data of the student; A system comprising: means for generating an explanation for each unanswered question using an AI system and transmitting the explanation to student terminals; means for analyzing test results of all students and optimizing a next test or a learning program by a server; and means for displaying the optimized learning program received from the server and providing feedback to the students by a teacher terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's educational environment, teachers and staff are overwhelmed with a variety of tasks and overtime work, and are expected to perform their work efficiently. However, grading tests and assessing each student's level of understanding takes time and effort, placing a significant burden on teachers and staff. Furthermore, students need prompt and accurate feedback to deepen their understanding of questions they were unable to answer on tests. A system that solves these issues, reduces the workload of teachers and staff, and improves students' learning outcomes is needed. [Means for solving the problem]

[0005] The present invention provides the following means to solve these problems for teachers and students.

[0006] The student terminal is provided with a means for notifying the server of the completion of the test and sending the answer data to the server. The server is provided with a means for receiving the answer data, automatically scoring it by comparing it with a standard answer database, and storing the scoring results in the database. The server also has a means for identifying unanswered questions from the student answer data, generating explanations for each unanswered question using an AI system, and sending the explanation data to the student terminal. The server is provided with a means for analyzing the test result data of all students and optimizing the next test and learning program. The system also includes a means for the teacher terminal to display the optimized learning program data received from the server and provide feedback to students. This reduces the burden on teachers and improves student learning effectiveness.

[0007] "Student Device" means an electronic device used by a student to take a test or receive clarification.

[0008] The "server" is a central processing unit that receives and analyzes test response data, provides scoring and explanations, and optimizes students' learning programs.

[0009] "Response data" is digital data that includes information about answers given by students during a test and questions left unanswered.

[0010] A "standard answer database" is a database that stores the correct answers to test questions and related information.

[0011] "Automatic scoring" is the process by which the server compares the received answer data with a database of standard answers and automatically calculates the score for each question.

[0012] "Scoring results" refers to information about the score for each question and the total score obtained by the server through the automatic scoring process.

[0013] An "unanswered question" is a question that a student did not answer on the test.

[0014] An "AI system" is a computer system that uses artificial intelligence to perform specific tasks.

[0015] "Explanatory data" refers to data that includes explanatory text and explanations generated by the AI ​​system for unanswered questions.

[0016] A "program of study" is a curriculum or set of materials designed for student study.

[0017] "Optimization" is the process by which the server analyzes each student's strengths and weaknesses and adjusts their individual learning program.

[0018] "Teacher Terminal" means an electronic device used by a teacher to display the optimized learning program and provide feedback to students.

[0019] "Feedback" is advice or instruction that a teacher provides to a student regarding their learning results or progress. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[0042] System configuration

[0043] 1. Student device: A device (tablet, PC, smartphone, etc.) used by students to take the test. This device has an interface for starting and ending the test, and for entering and submitting answers.

[0044] 2. Server: The central processing unit that forms the core of the educational support system. This server has the following functions:

[0045] Receives, decodes, and analyzes test response data.

[0046] The answers are compared with a database of standard answers and automatically graded.

[0047] Stores the marks in a database and identifies unanswered questions.

[0048] An AI system is used to generate explanations for unanswered questions.

[0049] Analyze test results for all students and generate optimized learning programs.

[0050] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[0051] System Operation

[0052] 1. Testing and Completion

[0053] Student device: The user (student) starts the test and enters the answers. When the test is finished, the student device sends the answer data to the server along with a notification that the test has finished.

[0054] Examples:

[0055] A student takes a math test on a tablet. When the student presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[0056] 2. Automatic scoring and analysis

[0057] Server: The server decodes the received answer data, compares it with the standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[0058] Examples:

[0059] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", it compares this with the standard answer and marks it as incorrect, giving the student 0 points.

[0060] 3. Explanation generation for unanswered questions

[0061] Server: After identifying unanswered questions, the server generates explanations using an AI system and sends the generated explanation data back to the student's device.

[0062] Examples:

[0063] If a student finishes the test without answering the "addition of fractions" question, the server will identify the question, generate an explanation for "addition of fractions" using AI, and send it to the student's device.

[0064] 4. Optimizing learning programs

[0065] Server: Collects and analyzes test result data from all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on that data and stores it in a database.

[0066] Examples:

[0067] If it turns out that a student has difficulty with adding fractions, adjust the next test or learning program to include more questions and materials related to adding fractions.

[0068] 5. Display of learning materials and learning feedback

[0069] Teacher terminal: The teacher terminal has an interface for displaying optimized learning program data and providing feedback to students, allowing teachers to provide effective instruction tailored to each student's level of understanding.

[0070] Examples:

[0071] A teacher opens the dashboard and sees that a student's weakness is "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[0072] In this way, the system of the present invention can effectively support students' learning and reduce the burden on teachers. This system is excellent in that it enhances students' understanding and provides learning programs optimized to meet individual learning needs.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user (student) starts the test on the student terminal, which displays the test questions on the screen and provides an interface for the user to enter their answers.

[0076] Step 2:

[0077] The user (student) enters answers to the test questions, and after completing all questions, presses the end test button. The student device encodes the user's answer data into JSON format data.

[0078] Step 3:

[0079] The student terminal sends the encoded answer data to the server using an HTTP POST request, and the server receives the request and analyzes the answer data.

[0080] Step 4:

[0081] The server decodes the received JSON data, extracts each question ID and answer data, and checks the correctness of each question against a standard answer database.

[0082] Step 5:

[0083] The server calculates the score for each question based on the results of matching with the standard answer database, and the calculation results are saved in the database as the scoring results for each student.

[0084] Step 6:

[0085] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[0086] Step 7:

[0087] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[0088] Step 8:

[0089] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the student.

[0090] Step 9:

[0091] The server periodically collects and analyzes test result data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[0092] Step 10:

[0093] The server uses the analyzed data to optimize the next test and learning program, and stores the optimized learning program in a database.

[0094] Step 11:

[0095] The teacher terminal periodically receives optimized learning program data from the server, and uses this data to display a dashboard for providing individual feedback to each student.

[0096] Step 12:

[0097] Teachers can provide appropriate guidance to students by looking at the dashboard and provide feedback based on their progress. This feedback data is also sent to the server and used to continuously optimize the learning program.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] Conventional educational support systems have had issues with the difficulty of grasping each student's learning status and providing appropriate feedback, and they place a heavy burden on teachers. Furthermore, generating explanations for unanswered questions and optimizing learning programs for each student manually takes time and effort, so automation was needed.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit the answer data to the server; means for the server to receive the answer data, automatically score the answer data by comparing it with a standard answer database, and store the scoring results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using an AI system, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the server to store the optimized study program in a database and transmit the generated study program data to the teacher terminal; and means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students. This allows for individual understanding of students' learning progress, providing quick and effective feedback, and reducing the burden on teachers. Furthermore, automating the generation of explanations for unanswered questions and the optimization of study programs improves the quality of education.

[0103] The "server" is the central processing unit of the educational support system, and is a device that analyzes received answer data, automatically grades answers, generates explanations, and optimizes the learning program.

[0104] "Student terminal" means a device used by a student to take a test, and is equipped with an interface for starting and ending the test and for inputting and submitting answers.

[0105] A "teacher terminal" is a device that allows teachers to check students' learning status and provide feedback based on an optimized learning program.

[0106] "Answer data" is data that includes information about test answers, and is sent from the student terminal to the server at the end of the test.

[0107] The "standard answer database" is a database that records correct answer information for tests, and is used by the server when automatically scoring tests.

[0108] "Automatic scoring" is the process by which the server compares the received answer data with a database of standard answers to calculate a score.

[0109] An "unanswered question" is a question to which a student did not enter an answer on the test.

[0110] "Explanation" is an explanatory text generated by the AI ​​system for unanswered questions, containing information to help students deepen their understanding.

[0111] An "optimized learning program" is a program generated by the server by analyzing the test result data of students and providing optimal learning content for each student.

[0112] A "database" is a data storage device for efficiently storing, managing, and searching information, and in the present invention, mainly stores grading results and learning programs.

[0113] An "HTTP POST request" is a standard communication protocol for sending data over the Internet, and is used in the present invention to send answer data and explanation data.

[0114] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[0115] System configuration

[0116] 1. Student device: This is the device used by students to take the test. This device can be a tablet, PC, smartphone, or other type of hardware. The student device has an interface for starting and ending the test, as well as entering and submitting answers.

[0117] 2. Server: This is the central processing unit that forms the core of the educational support system. This server has the following main functions:

[0118] Receiving and decoding response data: The system is equipped with a software module for receiving, decoding, and analyzing response data sent from student terminals.

[0119] Automatic scoring: Scores are calculated by comparing with a standard answer database. Scores are saved in a database for each student.

[0120] Explanation generation: An AI system is used to generate explanations for unanswered questions. The generated explanation data is then sent back to the student's device.

[0121] Optimizing learning programs: Collect and analyze the test results of all students to identify their strengths and weaknesses. Based on this, an optimized learning program for each student is generated and stored in the database.

[0122] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[0123] Hardware and software used

[0124] Hardware: Student devices (tablets, PCs, smartphones), teacher devices, servers

[0125] Software: Dedicated application for the educational support system, response data receiving module, automatic scoring module, AI explanation generation module, learning program optimization module, HTTP communication module

[0126] Specific examples

[0127] Example 1:

[0128] Students take a math test on a tablet. After completing the test, they tap the End Test button, encode their answers into JSON format, and then send it to the server as an HTTP POST request.

[0129] Example 2:

[0130] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", the server checks it against a database of standard answers and marks it as incorrect, giving the student zero points.

[0131] Example 3:

[0132] If a student leaves the "addition of fractions" problem unanswered and quits, the server will identify the problem, and the AI ​​system will generate an explanation for "addition of fractions" and send it to the student's device.

[0133] Example 4:

[0134] If a student is found to have difficulty with "adding fractions," the server will optimize the next test or learning program to include more questions and materials related to "adding fractions."

[0135] Example 5:

[0136] The teacher opens the dashboard on the teacher's computer and sees that a student has a weakness in "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[0137] Prompt Sentence Examples

[0138] Example prompt sentence:

[0139] "Please generate an explanation of how to add fractions. It is preferable that the explanation includes specific steps and examples."

[0140] The above is a concrete example of the educational support system. This system grasps each student's learning situation individually and provides quick and accurate feedback. It also reduces the burden on teachers and improves the quality of education.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1:

[0143] The student device starts the test, and the user (student) enters the answers. After the test is completed, the student device taps the "End Test" button and sends the answer data to the server.

[0144] Input: Test answers entered by the user (student)

[0145] Output: JSON-encoded response data

[0146] Specific operation: When the user has finished answering all the questions, they tap the "Submit" button on the student's device, which encodes the answer data into JSON format and sends it to the server as an HTTP POST request.

[0147] Step 2:

[0148] The server decodes and analyzes the answer data received from the student's device, then automatically scores it by comparing it with a standard answer database, and calculates the score.The calculated score data is then saved in the database.

[0149] Input: JSON formatted response data

[0150] Output:Scoring result data

[0151] Specific operation: The server receives and analyzes the answer data sent from the student's device. For example, if the answer is "4" to the question "2 + 3 =", the server checks it against the standard answer database and marks it as incorrect, giving it a score of 0. This is then stored in the database.

[0152] Step 3:

[0153] The server identifies unanswered questions from the students' answer data and uses an AI system to generate explanations for each unanswered question. The generated explanation data is then sent back to the student's device.

[0154] Input: Student response data

[0155] Output: Commentary data

[0156] Specific operation: The server analyzes the response data and lists any unanswered questions. An AI system is used to generate detailed explanations for the unanswered questions and send the explanation data to the student's device. For example, if "adding fractions" is left unanswered, an explanation for that subject is generated and sent to the student's device.

[0157] Step 4:

[0158] The server collects and analyzes the test results of all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on this information and stores it in a database.

[0159] Input: Test result data for all students

[0160] Output: Optimized learning program

[0161] Specific operation: The server aggregates and analyzes the test result data of all students. For example, if a student has a low score on "fraction addition," it identifies "fraction addition" as the student's weak point. It generates a learning program optimized for that student and stores it in the database.

[0162] Step 5:

[0163] The server sends optimized learning program data to the teacher's terminal, which displays it, and the teacher uses the data to provide appropriate feedback to each student.

[0164] Input: Optimized learning program data

[0165] Output: Teacher feedback

[0166] Specific operation: The teacher opens the dashboard on the teacher's device and checks the learning status of each student. For example, the teacher may determine that a student has a weakness in "adding fractions." In the next lesson, the teacher will focus on that area. The teacher will also provide individual feedback using the interface on the teacher's device.

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Conventional educational support systems did not adequately provide optimal learning programs tailored to individual needs or provide feedback based on students' level of understanding when they progressed through online learning. Furthermore, even when students could not attend a physical classroom, there was no environment in place for them to learn while interacting with other students. Furthermore, there was a lack of systems that integrated advanced functions such as AI-based explanation generation and learning support in virtual classrooms, making it difficult to provide effective online education.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit answer data to the server; means for the server to receive the answer data, compare it with a standard answer database, automatically grade it, and store the graded results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using a generative AI model, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students; and means for providing virtual classroom access in a virtual space so that students can participate in classes with other students in the virtual space. This allows students to study with an optimal program that meets their individual learning needs, even in an online environment, and to learn effectively while interacting with other students.

[0172] A "student device" is a device (smartphone, tablet, PC, smart glasses, head-mounted display, etc.) used by a student to take a test or participate in a learning program.

[0173] The "server" is a central processing unit that receives and processes answer data, and is a computer system that performs automatic scoring, analysis, explanation generation, and optimization of the learning program.

[0174] A "standard answer database" is a database that stores standard correct answers, allowing the server to automatically grade student answers.

[0175] A "generative AI model" is an artificial intelligence model used to automatically generate explanations for unanswered questions. Examples include natural language processing models.

[0176] A "virtual space" is a virtual reality or augmented reality environment that provides a virtual classroom where students can participate in online classes with other students.

[0177] "Virtual classroom access" is a feature that allows students to log in to a virtual space and participate in classes with other students.

[0178] "Optimized learning program data" refers to data on an educational program that is tailored to each student based on their test results and strengths and weaknesses.

[0179] "Feedback" refers to evaluations and advice provided to students by teachers or systems, which helps students improve their understanding.

[0180] "Test result data" refers to data that includes the answers given by students on tests and the results of their grading.

[0181] An "HTTP POST request" is one of the HTTP protocol methods used to send data from a client (student terminal) to a server.

[0182] "Statistical Analysis Module" means an analytical software module used to identify areas of strength and weakness for each Student.

[0183] "Explanation data" is data that is used to generate explanations for students' unanswered questions using a generative AI model and send them to the student's device.

[0184] "Optimizing the learning program" involves analyzing the test result data collected by the server and adjusting the content of the next test or learning program based on each student's strengths and weaknesses.

[0185] System Overview

[0186] This invention is an educational support system that uses student terminals, a server, and a teacher terminal. This system allows students to take tests online, the server automatically scores and analyzes the results, and teachers to provide individual learning support.

[0187] System configuration

[0188] 1. Student devices:

[0189] A device used by students to take tests. Devices include smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[0190] The student terminals are equipped with an interface for starting and ending the test, and for inputting and submitting answers.

[0191] 2. Server:

[0192] The server is a central processing unit that forms the core of the educational support system.

[0193] The server receives the answer data and automatically scores it by comparing it with a standard answer database.

[0194] The results of the scoring are stored in a database.

[0195] The server identifies unanswered questions from the student's response data and generates explanations using a generative AI model (such as the T5 Transformers model).

[0196] The explanation data is sent to the student's device, and appropriate explanations are provided based on prompts using an AI model.

[0197] The server analyzes the test result data of all students and uses a statistical analysis module to identify the strengths and weaknesses of each student and optimize the next test or learning program.

[0198] 3. Teacher's terminal:

[0199] This is a device that teachers can use to check students' learning status and provide feedback. Devices include PCs and tablets.

[0200] The teacher's terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate to each student.

[0201] Example of operation

[0202] 1. Testing and Completion

[0203] On the student's device, the user starts the test and enters the answers. When the user presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[0204] 2. Automatic scoring and analysis

[0205] The server decodes the received answer data, compares it with a standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[0206] For example, if a student answers "4" to the question "2+3=", the server compares it with the standard answer and marks it as incorrect, giving it a score of 0.

[0207] 3. Explanation generation for unanswered questions

[0208] The server identifies unanswered questions and generates explanations using a generative AI model.

[0209] As a specific example, if a student finishes a test without answering a question about "adding fractions," the server will identify the question, generate an explanation for "adding fractions" using a generative AI model, and send it to the student's device.

[0210] 4. Optimizing learning programs

[0211] The server collects and analyzes test result data for all students and identifies each student's strengths and weaknesses based on the generated prompts.

[0212] For example, if it turns out that a student has difficulty with "adding fractions," the next test or learning program will be adjusted to include more questions and materials related to "adding fractions."

[0213] 5. Virtual classroom access in virtual space

[0214] Students can log in to a virtual space and participate in classes with other students, allowing them to learn while interacting with other students just as they would in a physical classroom.

[0215] Through these measures, it is possible to provide online programs that are optimally tailored to individual learning needs and to create an environment where students can learn effectively while interacting with other students.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1: Conducting and Finishing the Test

[0218] The user (student) starts the test using the student terminal and enters the answers. Specifically, the student operates the terminal interface to answer the questions and presses the end button.

[0219] Input: Student answer data

[0220] Output: Test completion notification and answer data encoded in JSON format

[0221] Data processing: Encode answer data into JSON format

[0222] The student terminal sends the encoded answer data to the server via an HTTP POST request along with a test completion notification.

[0223] Step 2: Automated scoring and analysis

[0224] The server decodes the received answer data and checks it against a database of standard answers. Specifically, the server analyzes the answer data and compares each answer with the standard answers.

[0225] Input: Answer data (JSON format)

[0226] Output: Grade results for each student

[0227] Data processing: Matching the decoded answer data with the standard answer data

[0228] The server calculates the scores and stores the results in a database as the grades for each student.

[0229] Step 3: Generate explanations for unanswered questions

[0230] The server identifies unanswered questions from the student's answer data. Specifically, the server checks the answer data and checks for blank spaces.

[0231] Input: Answer data and standard answer data

[0232] Output: List of unanswered questions

[0233] Data processing: Identifying missing responses

[0234] The server uses a generative AI model to generate an explanation for each unanswered question. Specifically, the AI ​​model generates an explanation based on the prompt sentence.

[0235] Input: List of unanswered questions, prompt text

[0236] Output: Commentary data

[0237] Data Computation: Generating Explanations with Generative AI Models

[0238] The server transmits the generated commentary data to the student terminal.

[0239] Step 4: Optimize your learning program

[0240] The server collects and analyzes test result data for all students and uses a statistical analysis module to identify each student's strengths and weaknesses.

[0241] Input: Test result data for all students

[0242] Output: Identification of strengths and weaknesses for each student

[0243] Data Computation: Statistical Analysis

[0244] The server uses this information to optimize the next test or study program, specifically adjusting the layout of questions and study materials to strengthen strengths and compensate for weaknesses.

[0245] Input: Strengths and weaknesses of each student

[0246] Output: Optimized learning program data

[0247] Data Computing: Learning Program Generation and Optimization

[0248] Step 5: Virtual classroom access in a virtual space

[0249] Users (students) log in to the virtual space and participate in classes with other students. Specifically, students wear smart glasses or a head-mounted display and access the virtual classroom.

[0250] Input: User login information

[0251] Output: Virtual classroom access permission

[0252] Data calculation: Login authentication and access right confirmation

[0253] Students can take live lessons with other students in a virtual classroom and interact in real time.

[0254] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0255] The present invention is an educational support system that is configured by combining student terminals, a server, a teacher terminal, and an emotion engine. The specific configuration and operation of this system will be described below.

[0256] System configuration

[0257] 1. Student Device: A device (tablet, PC, smartphone, etc.) used by students to take tests and receive feedback. This device is equipped with an interface for starting and ending tests and inputting and submitting answers. It also has an integrated emotion engine that can analyze students' facial expressions and reactions to generate emotion data.

[0258] 2. Server: This is the central part of the educational support system. This server has the following functions:

[0259] Test response data is received, compared with a standard answer database, and automatically scored.

[0260] Stores the marks in a database and identifies unanswered questions.

[0261] An AI system is used to generate an explanation for each unanswered question, and the explanation data is sent to the student's device.

[0262] Analyze test result data and emotional data for all students to optimize the next test and learning program.

[0263] 3. Teacher terminal: A device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotional data, supporting effective instruction.

[0264] 4. Emotion Engine: A system that analyzes students' facial expressions and reactions to generate emotional data. The emotional data is sent from the student's device to a server and used to optimize the learning program.

[0265] System Operation

[0266] 1. Testing and Completion

[0267] Student device: The user (student) starts the test and enters answers to the questions. When the test is finished, the student device sends a notification of the test completion and the answer data to the server. In addition, the device monitors the student's facial expressions and reactions during the test and generates emotion data in real time.

[0268] Examples:

[0269] While students are taking the Japanese language test, the device's camera monitors their facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the emotional data is sent to the server along with the students' answers.

[0270] 2. Automatic scoring and analysis

[0271] Server: The server decodes the received answer data, compares it with a standard answer database, and automatically scores each question. The scoring results are stored in a database.

[0272] Examples:

[0273] The server receives the students' answers, compares them with standard answers, and calculates a score for each question, including the reading of kanji. The results are recorded in the individual student's database.

[0274] 3. Explanation generation for unanswered questions

[0275] Server: The server identifies unanswered questions from the students' answer data, generates explanations using the AI ​​system, and sends the generated explanation data to the students' devices.

[0276] Examples:

[0277] If a student leaves a kanji writing question unanswered, the server will recognize this and the AI ​​system will generate an explanation on how to write the kanji and send it to the student's device.

[0278] 4. Optimizing learning programs

[0279] Server: The server collects and analyzes test results and emotional data from all students to individually optimize the next test and study program. For example, if a student feels stressed about a particular problem, the server generates a study program that includes additional learning materials or a different approach to that problem.

[0280] Examples:

[0281] If a student feels highly stressed by a "reading comprehension" question and this is reflected in the emotional data, the server will optimize the next learning program to include more practice questions and supplementary materials in that area.

[0282] 5. Display of learning materials and learning feedback

[0283] Teacher's terminal: The teacher's terminal displays the optimized learning program data and student's emotional data received from the server. Based on this, the teacher can provide appropriate feedback and guidance to the student.

[0284] Examples:

[0285] A teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations and practice of the geometry problem during class.

[0286] As described above, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[0287] The processing flow will be explained below.

[0288] Step 1:

[0289] The user (student) starts the test on the student's device. The student's device displays the test questions on the screen and provides an interface for entering answers. Meanwhile, the emotion engine installed on the device monitors the student's facial expressions and reactions in real time and generates emotion data.

[0290] Step 2:

[0291] The user (student) enters the answer to each question and presses the end test button after completing all questions. The student's device encodes the user's answer data and the emotion data collected during the test into JSON format.

[0292] Step 3:

[0293] The student device sends the encoded response data and emotion data to the server using an HTTP POST request. The server receives the request and begins analyzing the data.

[0294] Step 4:

[0295] The server decodes the received JSON data and extracts each question ID and answer data. The server checks the correctness of each question against a standard answer database and calculates the score. The calculated score is saved in a database.

[0296] Step 5:

[0297] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[0298] Step 6:

[0299] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[0300] Step 7:

[0301] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the user (student).

[0302] Step 8:

[0303] The server periodically collects and analyzes test result data and emotional data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[0304] Step 9:

[0305] The server then uses the analyzed data to individually optimize the next test or study program. For example, if a student feels particularly stressed about a particular problem, it will generate a study program that includes additional material or a different approach to that problem.

[0306] Step 10:

[0307] The server sends the optimized learning program data to the teacher's terminal via an HTTP POST request, which then displays a dashboard to provide optimal feedback to each student.

[0308] Step 11:

[0309] The teacher's terminal checks each student's progress based on the optimized learning program data and student emotion data sent from the server. The teacher uses this data to provide appropriate feedback to each student.

[0310] Step 12:

[0311] The teacher inputs the feedback he or she wants to provide to the student into the teacher's terminal and sends it to the server, which then collects this feedback data and uses it to optimize the learning program.

[0312] Example 2

[0313] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] Conventional educational support systems make it difficult to maximize the learning effect of individual students. Furthermore, they do not provide feedback that takes into account students' emotions, which can lead to a decrease in motivation to learn and stress. This increases the burden on teachers and often leads to a lack of individual instruction. Therefore, it is necessary to solve these issues.

[0315] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0316] In this invention, the server includes means for the student terminal to instruct the user to start the test, means for notifying the server of the end of the test and transmitting answer data and emotion data to the server, means for automatically scoring the received answer data and emotion data by comparing it with a standard answer database and saving the scoring results in the database, means for identifying unanswered questions from the student answer data and transmitting generated explanation data to the student terminal, means for analyzing the test result data and emotion data of all students and optimizing the next test or learning program, means for displaying the optimized learning program data and emotion data and providing feedback, and an emotion engine for the student terminal to generate emotion data in real time. This enables optimal feedback that takes into account each student's individual learning situation and emotions, resulting in effective learning support.

[0317] A "student device" is a device (e.g., tablet, PC, smartphone) used by a student to take a test or receive feedback.

[0318] The "server" is the central part of the educational support system, and is a device that receives, stores, analyzes, and optimizes various types of data.

[0319] The "emotion engine" is a system that analyzes students' facial expressions and reactions to generate emotional data, and is a device that collects emotional data from student devices in real time and transmits it to a server.

[0320] A "teacher terminal" is a device that allows a teacher to give feedback to students based on data received from the server.

[0321] "Standard answer database" refers to a database that stores correct answer data and is used by the server to automatically score tests.

[0322] "Scoring results" refers to score information generated after the server automatically scores the answer data it receives by comparing it with a standard answer database.

[0323] An "unanswered question" is a question that a student did not answer during the test.

[0324] "Explanation data" refers to information about explanations and commentaries generated by the server for unanswered questions, and is provided to help students deepen their understanding.

[0325] "Optimizing the next test or learning program" is the process in which the server analyzes the test result data and emotional data of all students and generates individually optimized test and learning program content.

[0326] "Feedback" is information that teachers use to provide guidance and areas for improvement to students' learning.

[0327] An "HTTP POST request" is one of the communication protocols used when a server sends data, and is a method of sending data from a client to a server.

[0328] "Statistical Analysis Module" means a software module that has the functionality to analyze data to identify areas of strength and weakness of a student.

[0329] The present invention is an educational support system that combines student terminals, a server, a teacher terminal, and an emotion engine. This system provides individually optimized education by cooperating with each hardware and software component.

[0330] Student Devices

[0331] The student device is a device (tablet, PC, smartphone, etc.) that students use to take tests and receive feedback. This device has an interface for starting and ending tests, and for entering and submitting answers. Furthermore, it is integrated with an emotion engine, which can analyze students' facial expressions and reactions to generate emotional data.

[0332] For example, while a student is taking a Japanese language test, the device's camera monitors the student's facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the student's emotional data is sent to the server along with their answer data.

[0333] server

[0334] The server is the central part of the educational support system. It has the following main functions:

[0335] 1. Automatic scoring: The server decodes the received answer data and automatically scores each question by comparing it with a standard answer database. The scoring results are stored in a database. For example, the server receives the student's answer data, compares questions including "how to read kanji" with the standard answers, and calculates the score for each.

[0336] 2. Generating explanations for unanswered questions: The server identifies unanswered questions from the student's answer data and generates explanations using the AI ​​system. The generated explanation data is sent to the student's device. For example, if a student leaves a "kanji dictation" question unanswered, the server recognizes this and the AI ​​system generates an explanation on "how to write that kanji" and sends it to the student's device.

[0337] 3. Optimizing learning programs: The server collects and analyzes test results and emotional data from all students, and then individually optimizes the next test and learning program. For students who feel particularly stressed by a particular problem, the server provides additional learning materials or different approaches to that problem.

[0338] Teacher's terminal

[0339] The teacher terminal is a device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotion data to support effective instruction.

[0340] For example, a teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations or practice of the geometry problem during class.

[0341] Emotion Engine

[0342] The emotion engine is a system that analyzes students' facial expressions and reactions to generate emotion data. The emotion data is sent from the student's device to a server and used to optimize the learning program.

[0343] For example, if a student feels anxious or worried during a test, that emotional data is sent to the server in real time and reflected in the next learning program.

[0344] Using generative AI models

[0345] A generative AI model is used to optimize the entire system and generate explanations. Specific examples of prompts include "How to train an AI model to automatically generate explanations for unanswered questions" and "How to optimize learning programs by analyzing student sentiment data."

[0346] In this way, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] Starting the test

[0350] User (Student): When the user presses the "Start Test" button on the student's device, the system displays the test interface and activates the device's camera to record the student's facial expression in real time.

[0351] Input: User clicks the "Start Test" button.

[0352] Output: Display of test interface and start of camera.

[0353] How it works: When a student clicks the "Start Test" button on the tablet, the first question appears on the screen, and the camera begins monitoring the student's facial expressions.

[0354] Step 2:

[0355] Enter your answer

[0356] User (student): The user answers the questions by tapping the correct answer for multiple choice questions and typing the answer on the keyboard for written questions.

[0357] Input: User answer input.

[0358] Output: Temporarily save answer data.

[0359] Specific operation: The student enters the answer to the "Kanji reading" question using the keyboard. If it is a multiple choice question, they tap on the option. Once the answer is entered, the next question will be displayed.

[0360] Step 3:

[0361] End of test and data transmission

[0362] User (student): When the user has answered all questions or the time is up, a notification is displayed that the test is over. When the user presses the end button, the answer data and emotion data are sent to the server.

[0363] Input: Test end operation.

[0364] Output: Sending response data and sentiment data.

[0365] Specific operation: At the end of the test, a message saying "Test completed" is displayed. When the student clicks the "Exit" button, the answer data and real-time collected emotion data are sent to the server.

[0366] Step 4:

[0367] Receiving data

[0368] Server: The server receives the response data and emotion data sent from the device, decodes them, and stores them.

[0369] Input: Receives response data and emotion data.

[0370] Output: Save to database.

[0371] Specific operation: The server captures the data stream, decodes the response data and emotion data, and stores them in a database.

[0372] Step 5:

[0373] Automatic scoring

[0374] Server: The server compares the answer data with a standard answer database and automatically scores the answers. The scores are stored in a database.

[0375] Input: Response data.

[0376] Output: Scoring results.

[0377] Specific operation: The received answer data "Kanji reading" is compared with the standard answer, and if the answer is correct, points are awarded, and if the answer is incorrect, no points are awarded. The results are recorded in the database.

[0378] Step 6:

[0379] Identifying unanswered questions

[0380] Server: The server analyzes the response data to identify unanswered questions and, if any, generates a list of unanswered questions.

[0381] Input: Response data.

[0382] Output: A list of unanswered questions.

[0383] What happens: The server loops through the answer data and identifies any entries that are blank. If the "Kanji dictation" question has not been answered, that information is listed.

[0384] Step 7:

[0385] Generate explanations

[0386] Server: The server uses an AI system to generate explanations for unanswered questions. The generated explanation data is sent to the student's device.

[0387] Input: List of unanswered questions.

[0388] Output: The generated narrative data.

[0389] Specific operation: The AI ​​system generates correct writing methods and example sentences for "kanji dictation" problems. Explanation data is compiled and sent to the student's device.

[0390] Step 8:

[0391] Optimizing your learning program

[0392] Server: The server analyzes test results and emotional data for all students and individually optimizes the next test and learning program, providing additional learning materials and different approaches to high-stress problems.

[0393] Input: Test result data and emotion data of all students.

[0394] Output: An optimized learning program.

[0395] Specific operation: Based on data on students who felt highly stressed by the "reading comprehension" questions, the server configures the next learning program to include additional practice questions and supplementary materials.

[0396] Step 9:

[0397] Data Display and Feedback

[0398] Teacher terminal: The teacher terminal displays the optimized learning program data and emotion data received from the server. The teacher provides feedback based on the displayed data.

[0399] Input: Optimized learning program data and emotion data.

[0400] Output: Feedback.

[0401] Specific behavior: The test results and emotional data of specific students are displayed on the dashboard of the teacher's device, and the teacher can provide feedback to the students, such as "Add more focus on specific questions in the next learning program."

[0402] (Application example 2)

[0403] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0404] Conventional educational support systems have limited data collection and analysis to maximize students' learning outcomes, and are unable to provide optimal feedback or guidance that takes into account students' emotional data. Furthermore, in the maintenance of factory robots, appropriate maintenance suggestions that take into account the emotional state of the technicians were not provided, which can increase technician stress and reduce efficiency. It is necessary to provide a sustainable system that solves these issues.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0406] In this invention, the server includes means for receiving students' answer data, comparing it with a standard answer database to automatically score the answers, and storing the scoring results in a database; means for identifying unanswered questions from the students' answer data, generating explanations for each unanswered question using an AI system, and transmitting the explanation data to the student terminals; means for analyzing the test result data and emotion data of all students and optimizing the next test or study program; means for receiving and analyzing the robot's sensor data to generate robot maintenance suggestions and transmit the necessary actions to the engineer terminal; and means for the engineer terminal to generate emotion data using camera footage and transmit it to the server. This enables effective feedback, guidance, and maintenance suggestions that take emotion data into account in both educational settings and factories.

[0407] A "student device" is a device used by students to take tests and receive feedback.

[0408] The "server" is a central processing unit that receives students' answer data, compares it with a standard answer database, automatically scores it, and analyzes the test result data and emotional data of all students.

[0409] A "standard answer database" is a database that stores standard answers for tests.

[0410] "Automatic scoring" is the process by which the server compares student response data with a database of standard answers and calculates scores without human intervention.

[0411] An "AI system" is a system that uses artificial intelligence and has the ability to automatically generate explanations for students' unanswered questions.

[0412] "Explanation data" refers to the explanations generated by the AI ​​system for unanswered questions.

[0413] "Emotional data" refers to data on the emotional state of students and engineers obtained by analyzing their facial expressions and reactions.

[0414] "Robot sensor data" is data that includes status information such as temperature and vibration collected from robots operating in factories.

[0415] A "maintenance proposal" is a maintenance method proposal generated by the server based on the robot's sensor data and the technician's emotional data.

[0416] An "engineer terminal" is a device used by engineers to perform maintenance and operation of the robot.

[0417] "Camera video" refers to video data acquired by a camera mounted on the engineer's terminal.

[0418] This invention is a system that is configured by combining student terminals, a server, a teacher terminal, an engineer terminal, and an emotion engine. The detailed configuration and operation of this system will be explained below.

[0419] System configuration

[0420] 1. Student devices

[0421] The student terminal is a device used by students taking courses, and is equipped with an interface for students to take tests and receive feedback. The student terminal is equipped with a camera to monitor the students' facial expressions and reactions during tests, and the emotion engine analyzes this to generate emotion data.

[0422] 2. Server

[0423] The server is the central part of the system and has the following functions:

[0424] The system receives answer data sent from student devices and automatically scores them by comparing them with a standard answer database.

[0425] The scoring results and emotion data are stored in a database and analyzed together with the test result data of all students.

[0426] Unanswered questions are identified and explanations are generated using an AI system and sent to student devices.

[0427] Analyze student response data and sentiment data to optimize the next test or learning program.

[0428] It receives and analyzes the robot's sensor data to generate maintenance suggestions and send them to the technician's terminal.

[0429] 3. Teacher's terminal

[0430] The teacher terminal is a device that allows teachers to monitor students' learning progress and provide feedback. It displays optimized learning program data and student emotional data, supporting effective instruction.

[0431] 4. Technician terminal

[0432] The engineer terminal is a device used to perform maintenance and operation of factory robots. The engineer terminal is equipped with a camera that monitors the face of the engineer and generates emotional data. The generated emotional data is sent to the server and used to generate maintenance suggestions.

[0433] 5. Emotion Engine

[0434] The emotion engine is a system that analyzes camera footage and generates emotion data from the facial expressions and reactions of students and engineers. The emotion data is sent from the student and engineer devices to a server and is used to optimize learning programs and generate maintenance suggestions.

[0435] System Operation

[0436] Operation as an educational support system

[0437] 1. Testing and Completion

[0438] The start and end of the test are notified from the student's device, and the answer data is sent to the server. At the same time, the camera on the student's device monitors the student's facial expressions and generates emotional data in real time.

[0439] 2. Automatic scoring and analysis

[0440] The server automatically scores the received answer data by comparing it with a standard answer database, and the results are stored in the database.

[0441] 3. Explanation generation for unanswered questions

[0442] The server identifies unanswered questions and generates explanations using an AI system, which are then sent to the student's device.

[0443] 4. Optimizing learning programs

[0444] The server analyzes the test results and emotional data of all students and individually optimizes their next test and learning program.

[0445] Operation as a maintenance system for factory robots

[0446] 1. Robot status monitoring

[0447] The server receives sensor data from the factory robots and monitors their status in real time.

[0448] 2. Collecting engineer emotion data

[0449] The engineer's terminal monitors the engineer's facial expression using camera images, and an emotion engine generates emotion data.

[0450] 3. Generate maintenance proposals

[0451] The server analyzes the received sensor data and emotion data and sends appropriate maintenance suggestions to the technician's terminal.

[0452] Specific examples

[0453] If a robot running in a factory is experiencing high temperatures and an engineer is feeling stressed about the situation, the system will:

[0454] The server recognizes from the robot's sensor data that Robot A's temperature has reached 90°C and generates a cooling suggestion.

[0455] At the same time, the technician terminal detects from the camera footage that technician B's stress level is high and generates a break suggestion.

[0456] The server sends these suggestions to the technician's terminal, and the technician takes appropriate action accordingly.

[0457] Example prompts to input to the generative AI model

[0458] "Robot A's temperature is over 90°C. Also, Technician B's stress level is detected to be high. Please make appropriate maintenance suggestions."

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] Student device starts testing

[0462] The student device is operated by the user (student) and the test begins. The student device collects camera footage in real time, analyzes facial expressions, and generates emotion data.

[0463] Input: Start test by student operation, camera image

[0464] Output: Test start notification, real-time emotion data

[0465] Specific operation: The camera on the student's device captures the student's facial expression, which is then analyzed by the emotion engine to generate emotion data.

[0466] Step 2:

[0467] Student devices will receive a notification of test completion and send answer data.

[0468] The student's device notifies the server that the test has ended and sends the answer data. The emotion data collected during the test is also sent to the server.

[0469] Input: Test completion notification, answer data, emotion data

[0470] Output: Sending answer data and emotion data

[0471] Specific operation: After the student device finishes the test, it sends an HTTP request to the server and transmits the answer data and emotion data.

[0472] Step 3:

[0473] The server receives the answer data and scores it.

[0474] The server receives the answer data sent from the student's device, compares it with a standard answer database, and automatically scores it. The results are saved in the database.

[0475] Input: Answer data

[0476] Output: Scoring results, updated database

[0477] Specific operation: The server compares the answer data with the standard answer database, calculates the score, and stores it in the database.

[0478] Step 4:

[0479] The server identifies unanswered questions and generates explanations

[0480] The server analyzes the response data, identifies unanswered questions, uses an AI system to generate explanations for these questions, and sends the explanation data to the student's device.

[0481] Input: Answer data, standard answer database

[0482] Output: List of unanswered questions, explanation data

[0483] Specific operation: The server extracts unanswered questions from the response data, generates explanatory text using a generative AI model, and sends it to the student's device.

[0484] Step 5:

[0485] The server analyzes test results and emotional data to optimize the learning program.

[0486] The server analyzes the test result data and emotional data of all students and individually optimizes the next test and learning program.

[0487] Input: Test result data, emotion data

[0488] Output: Optimized learning program

[0489] How it works: The server analyzes the data using statistical analysis and machine learning models to generate an optimized learning program for each student.

[0490] Step 6:

[0491] The server receives and analyzes the robot's sensor data.

[0492] The server receives sensor data from the factory robots and analyzes the data in real time.

[0493] Input: Robot sensor data (temperature, vibration, etc.)

[0494] Output: Analysis results

[0495] Specific operation: The server analyzes temperature and vibration data and performs threshold judgments to detect abnormal conditions.

[0496] Step 7:

[0497] The engineer's terminal generates emotion data using camera footage.

[0498] The engineer's terminal monitors the engineer's facial expressions in real time, and the emotion engine generates emotion data and sends it to the server.

[0499] Input: Technician's camera feed

[0500] Output: Generated emotion data

[0501] Specific operation: The camera on the technician's terminal captures the technician's face, and the emotion engine analyzes the facial expressions to generate emotion data, which is then sent to the server.

[0502] Step 8:

[0503] Server generates and sends maintenance proposals

[0504] The server analyzes the received sensor data and emotion data, generates maintenance suggestions for the robot, and sends the suggestions to the technician's terminal.

[0505] Input: Sensor data, emotion data

[0506] Output: Maintenance suggestions

[0507] Specific operation: The server analyzes sensor data and emotion data using the generated AI model and recommends appropriate maintenance actions to the technician's terminal.

[0508] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0509] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0510] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0511] [Second embodiment]

[0512] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0513] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0514] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0515] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0516] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0517] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0518] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0519] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0520] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0521] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0522] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0523] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0524] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[0525] System configuration

[0526] 1. Student device: A device (tablet, PC, smartphone, etc.) used by students to take the test. This device has an interface for starting and ending the test, and for entering and submitting answers.

[0527] 2. Server: The central processing unit that forms the core of the educational support system. This server has the following functions:

[0528] Receives, decodes, and analyzes test response data.

[0529] The answers are compared with a database of standard answers and automatically graded.

[0530] Stores the marks in a database and identifies unanswered questions.

[0531] An AI system is used to generate explanations for unanswered questions.

[0532] Analyze test results for all students and generate optimized learning programs.

[0533] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[0534] System Operation

[0535] 1. Testing and Completion

[0536] Student device: The user (student) starts the test and enters the answers. When the test is finished, the student device sends the answer data to the server along with a notification that the test has finished.

[0537] Examples:

[0538] A student takes a math test on a tablet. When the student presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[0539] 2. Automatic scoring and analysis

[0540] Server: The server decodes the received answer data, compares it with the standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[0541] Examples:

[0542] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", it compares this with the standard answer and marks it as incorrect, giving the student 0 points.

[0543] 3. Explanation generation for unanswered questions

[0544] Server: After identifying unanswered questions, the server generates explanations using an AI system and sends the generated explanation data back to the student's device.

[0545] Examples:

[0546] If a student finishes the test without answering the "addition of fractions" question, the server will identify the question, generate an explanation for "addition of fractions" using AI, and send it to the student's device.

[0547] 4. Optimizing learning programs

[0548] Server: Collects and analyzes test result data from all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on that data and stores it in a database.

[0549] Examples:

[0550] If it turns out that a student has difficulty with adding fractions, adjust the next test or learning program to include more questions and materials related to adding fractions.

[0551] 5. Display of learning materials and learning feedback

[0552] Teacher terminal: The teacher terminal has an interface for displaying optimized learning program data and providing feedback to students, allowing teachers to provide effective instruction tailored to each student's level of understanding.

[0553] Examples:

[0554] A teacher opens the dashboard and sees that a student's weakness is "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[0555] In this way, the system of the present invention can effectively support students' learning and reduce the burden on teachers. This system is excellent in that it enhances students' understanding and provides learning programs optimized to meet individual learning needs.

[0556] The processing flow will be explained below.

[0557] Step 1:

[0558] The user (student) starts the test on the student terminal, which displays the test questions on the screen and provides an interface for the user to enter their answers.

[0559] Step 2:

[0560] The user (student) enters answers to the test questions, and after completing all questions, presses the end test button. The student device encodes the user's answer data into JSON format data.

[0561] Step 3:

[0562] The student terminal sends the encoded answer data to the server using an HTTP POST request, and the server receives the request and analyzes the answer data.

[0563] Step 4:

[0564] The server decodes the received JSON data, extracts each question ID and answer data, and checks the correctness of each question against a standard answer database.

[0565] Step 5:

[0566] The server calculates the score for each question based on the results of matching with the standard answer database, and the calculation results are saved in the database as the scoring results for each student.

[0567] Step 6:

[0568] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[0569] Step 7:

[0570] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[0571] Step 8:

[0572] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the student.

[0573] Step 9:

[0574] The server periodically collects and analyzes test result data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[0575] Step 10:

[0576] The server uses the analyzed data to optimize the next test and learning program, and stores the optimized learning program in a database.

[0577] Step 11:

[0578] The teacher terminal periodically receives optimized learning program data from the server, and uses this data to display a dashboard for providing individual feedback to each student.

[0579] Step 12:

[0580] Teachers can provide appropriate guidance to students by looking at the dashboard and provide feedback based on their progress. This feedback data is also sent to the server and used to continuously optimize the learning program.

[0581] Example 1

[0582] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0583] Conventional educational support systems have had issues with the difficulty of grasping each student's learning status and providing appropriate feedback, and they place a heavy burden on teachers. Furthermore, generating explanations for unanswered questions and optimizing learning programs for each student manually takes time and effort, so automation was needed.

[0584] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0585] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit the answer data to the server; means for the server to receive the answer data, automatically score the answer data by comparing it with a standard answer database, and store the scoring results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using an AI system, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the server to store the optimized study program in a database and transmit the generated study program data to the teacher terminal; and means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students. This allows for individual understanding of students' learning progress, providing quick and effective feedback, and reducing the burden on teachers. Furthermore, automating the generation of explanations for unanswered questions and the optimization of study programs improves the quality of education.

[0586] The "server" is the central processing unit of the educational support system, and is a device that analyzes received answer data, automatically grades answers, generates explanations, and optimizes the learning program.

[0587] "Student terminal" means a device used by a student to take a test, and is equipped with an interface for starting and ending the test and for inputting and submitting answers.

[0588] A "teacher terminal" is a device that allows teachers to check students' learning status and provide feedback based on an optimized learning program.

[0589] "Answer data" is data that includes information about test answers, and is sent from the student terminal to the server at the end of the test.

[0590] The "standard answer database" is a database that records correct answer information for tests, and is used by the server when automatically scoring tests.

[0591] "Automatic scoring" is the process by which the server compares the received answer data with a database of standard answers to calculate a score.

[0592] An "unanswered question" is a question to which a student did not enter an answer on the test.

[0593] "Explanation" is an explanatory text generated by the AI ​​system for unanswered questions, containing information to help students deepen their understanding.

[0594] An "optimized learning program" is a program generated by the server by analyzing the test result data of students and providing optimal learning content for each student.

[0595] A "database" is a data storage device for efficiently storing, managing, and searching information, and in the present invention, mainly stores grading results and learning programs.

[0596] An "HTTP POST request" is a standard communication protocol for sending data over the Internet, and is used in the present invention to send answer data and explanation data.

[0597] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[0598] System configuration

[0599] 1. Student device: This is the device used by students to take the test. This device can be a tablet, PC, smartphone, or other type of hardware. The student device has an interface for starting and ending the test, as well as entering and submitting answers.

[0600] 2. Server: This is the central processing unit that forms the core of the educational support system. This server has the following main functions:

[0601] Receiving and decoding response data: The system is equipped with a software module for receiving, decoding, and analyzing response data sent from student terminals.

[0602] Automatic scoring: Scores are calculated by comparing with a standard answer database. Scores are saved in a database for each student.

[0603] Explanation generation: An AI system is used to generate explanations for unanswered questions. The generated explanation data is then sent back to the student's device.

[0604] Optimizing learning programs: Collect and analyze the test results of all students to identify their strengths and weaknesses. Based on this, an optimized learning program for each student is generated and stored in the database.

[0605] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[0606] Hardware and software used

[0607] Hardware: Student devices (tablets, PCs, smartphones), teacher devices, servers

[0608] Software: Dedicated application for the educational support system, response data receiving module, automatic scoring module, AI explanation generation module, learning program optimization module, HTTP communication module

[0609] Specific examples

[0610] Example 1:

[0611] Students take a math test on a tablet. After completing the test, they tap the End Test button, encode their answers into JSON format, and then send it to the server as an HTTP POST request.

[0612] Example 2:

[0613] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", the server checks it against a database of standard answers and marks it as incorrect, giving the student zero points.

[0614] Example 3:

[0615] If a student leaves the "addition of fractions" problem unanswered and quits, the server will identify the problem, and the AI ​​system will generate an explanation for "addition of fractions" and send it to the student's device.

[0616] Example 4:

[0617] If a student is found to have difficulty with "adding fractions," the server will optimize the next test or learning program to include more questions and materials related to "adding fractions."

[0618] Example 5:

[0619] The teacher opens the dashboard on the teacher's computer and sees that a student has a weakness in "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[0620] Prompt Sentence Examples

[0621] Example prompt sentence:

[0622] "Please generate an explanation of how to add fractions. It is preferable that the explanation includes specific steps and examples."

[0623] The above is a concrete example of the educational support system. This system grasps each student's learning situation individually and provides quick and accurate feedback. It also reduces the burden on teachers and improves the quality of education.

[0624] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] The student device starts the test, and the user (student) enters the answers. After the test is completed, the student device taps the "End Test" button and sends the answer data to the server.

[0627] Input: Test answers entered by the user (student)

[0628] Output: JSON-encoded response data

[0629] Specific operation: When the user has finished answering all the questions, they tap the "Submit" button on the student's device, which encodes the answer data into JSON format and sends it to the server as an HTTP POST request.

[0630] Step 2:

[0631] The server decodes and analyzes the answer data received from the student's device, then automatically scores it by comparing it with a standard answer database, and calculates the score.The calculated score data is then saved in the database.

[0632] Input: JSON formatted response data

[0633] Output:Scoring result data

[0634] Specific operation: The server receives and analyzes the answer data sent from the student's device. For example, if the answer is "4" to the question "2 + 3 =", the server checks it against the standard answer database and marks it as incorrect, giving it a score of 0. This is then stored in the database.

[0635] Step 3:

[0636] The server identifies unanswered questions from the students' answer data and uses an AI system to generate explanations for each unanswered question. The generated explanation data is then sent back to the student's device.

[0637] Input: Student response data

[0638] Output: Commentary data

[0639] Specific operation: The server analyzes the response data and lists any unanswered questions. An AI system is used to generate detailed explanations for the unanswered questions and send the explanation data to the student's device. For example, if "adding fractions" is left unanswered, an explanation for that subject is generated and sent to the student's device.

[0640] Step 4:

[0641] The server collects and analyzes the test results of all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on this information and stores it in a database.

[0642] Input: Test result data for all students

[0643] Output: Optimized learning program

[0644] Specific operation: The server aggregates and analyzes the test result data of all students. For example, if a student has a low score on "fraction addition," it identifies "fraction addition" as the student's weak point. It generates a learning program optimized for that student and stores it in the database.

[0645] Step 5:

[0646] The server sends optimized learning program data to the teacher's terminal, which displays it, and the teacher uses the data to provide appropriate feedback to each student.

[0647] Input: Optimized learning program data

[0648] Output: Teacher feedback

[0649] Specific operation: The teacher opens the dashboard on the teacher's device and checks the learning status of each student. For example, the teacher may determine that a student has a weakness in "adding fractions." In the next lesson, the teacher will focus on that area. The teacher will also provide individual feedback using the interface on the teacher's device.

[0650] (Application example 1)

[0651] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0652] Conventional educational support systems did not adequately provide optimal learning programs tailored to individual needs or provide feedback based on students' level of understanding when they progressed through online learning. Furthermore, even when students could not attend a physical classroom, there was no environment in place for them to learn while interacting with other students. Furthermore, there was a lack of systems that integrated advanced functions such as AI-based explanation generation and learning support in virtual classrooms, making it difficult to provide effective online education.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0654] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit answer data to the server; means for the server to receive the answer data, compare it with a standard answer database, automatically grade it, and store the graded results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using a generative AI model, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students; and means for providing virtual classroom access in a virtual space so that students can participate in classes with other students in the virtual space. This allows students to study with an optimal program that meets their individual learning needs, even in an online environment, and to learn effectively while interacting with other students.

[0655] A "student device" is a device (smartphone, tablet, PC, smart glasses, head-mounted display, etc.) used by a student to take a test or participate in a learning program.

[0656] The "server" is a central processing unit that receives and processes answer data, and is a computer system that performs automatic scoring, analysis, explanation generation, and optimization of the learning program.

[0657] A "standard answer database" is a database that stores standard correct answers, allowing the server to automatically grade student answers.

[0658] A "generative AI model" is an artificial intelligence model used to automatically generate explanations for unanswered questions. Examples include natural language processing models.

[0659] A "virtual space" is a virtual reality or augmented reality environment that provides a virtual classroom where students can participate in online classes with other students.

[0660] "Virtual classroom access" is a feature that allows students to log in to a virtual space and participate in classes with other students.

[0661] "Optimized learning program data" refers to data on an educational program that is tailored to each student based on their test results and strengths and weaknesses.

[0662] "Feedback" refers to evaluations and advice provided to students by teachers or systems, which helps students improve their understanding.

[0663] "Test result data" refers to data that includes the answers given by students on tests and the results of their grading.

[0664] An "HTTP POST request" is one of the HTTP protocol methods used to send data from a client (student terminal) to a server.

[0665] "Statistical Analysis Module" means an analytical software module used to identify areas of strength and weakness for each Student.

[0666] "Explanation data" is data that is used to generate explanations for students' unanswered questions using a generative AI model and send them to the student's device.

[0667] "Optimizing the learning program" involves analyzing the test result data collected by the server and adjusting the content of the next test or learning program based on each student's strengths and weaknesses.

[0668] System Overview

[0669] This invention is an educational support system that uses student terminals, a server, and a teacher terminal. This system allows students to take tests online, the server automatically scores and analyzes the results, and teachers to provide individual learning support.

[0670] System configuration

[0671] 1. Student devices:

[0672] A device used by students to take tests. Devices include smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[0673] The student terminals are equipped with an interface for starting and ending the test, and for inputting and submitting answers.

[0674] 2. Server:

[0675] The server is a central processing unit that forms the core of the educational support system.

[0676] The server receives the answer data and automatically scores it by comparing it with a standard answer database.

[0677] The results of the scoring are stored in a database.

[0678] The server identifies unanswered questions from the student's response data and generates explanations using a generative AI model (such as the T5 Transformers model).

[0679] The explanation data is sent to the student's device, and appropriate explanations are provided based on prompts using an AI model.

[0680] The server analyzes the test result data of all students and uses a statistical analysis module to identify the strengths and weaknesses of each student and optimize the next test or learning program.

[0681] 3. Teacher's terminal:

[0682] This is a device that teachers can use to check students' learning status and provide feedback. Devices include PCs and tablets.

[0683] The teacher's terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate to each student.

[0684] Example of operation

[0685] 1. Testing and Completion

[0686] On the student's device, the user starts the test and enters the answers. When the user presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[0687] 2. Automatic scoring and analysis

[0688] The server decodes the received answer data, compares it with a standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[0689] For example, if a student answers "4" to the question "2+3=", the server compares it with the standard answer and marks it as incorrect, giving it a score of 0.

[0690] 3. Explanation generation for unanswered questions

[0691] The server identifies unanswered questions and generates explanations using a generative AI model.

[0692] As a specific example, if a student finishes a test without answering a question about "adding fractions," the server will identify the question, generate an explanation for "adding fractions" using a generative AI model, and send it to the student's device.

[0693] 4. Optimizing learning programs

[0694] The server collects and analyzes test result data for all students and identifies each student's strengths and weaknesses based on the generated prompts.

[0695] For example, if it turns out that a student has difficulty with "adding fractions," the next test or learning program will be adjusted to include more questions and materials related to "adding fractions."

[0696] 5. Virtual classroom access in virtual space

[0697] Students can log in to a virtual space and participate in classes with other students, allowing them to learn while interacting with other students just as they would in a physical classroom.

[0698] Through these measures, it is possible to provide online programs that are optimally tailored to individual learning needs and to create an environment where students can learn effectively while interacting with other students.

[0699] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0700] Step 1: Conducting and Finishing the Test

[0701] The user (student) starts the test using the student terminal and enters the answers. Specifically, the student operates the terminal interface to answer the questions and presses the end button.

[0702] Input: Student answer data

[0703] Output: Test completion notification and answer data encoded in JSON format

[0704] Data processing: Encode answer data into JSON format

[0705] The student terminal sends the encoded answer data to the server via an HTTP POST request along with a test completion notification.

[0706] Step 2: Automated scoring and analysis

[0707] The server decodes the received answer data and checks it against a database of standard answers. Specifically, the server analyzes the answer data and compares each answer with the standard answers.

[0708] Input: Answer data (JSON format)

[0709] Output: Grade results for each student

[0710] Data processing: Matching the decoded answer data with the standard answer data

[0711] The server calculates the scores and stores the results in a database as the grades for each student.

[0712] Step 3: Generate explanations for unanswered questions

[0713] The server identifies unanswered questions from the student's answer data. Specifically, the server checks the answer data and checks for blank spaces.

[0714] Input: Answer data and standard answer data

[0715] Output: List of unanswered questions

[0716] Data processing: Identifying missing responses

[0717] The server uses a generative AI model to generate an explanation for each unanswered question. Specifically, the AI ​​model generates an explanation based on the prompt sentence.

[0718] Input: List of unanswered questions, prompt text

[0719] Output: Commentary data

[0720] Data Computation: Generating Explanations with Generative AI Models

[0721] The server transmits the generated commentary data to the student terminal.

[0722] Step 4: Optimize your learning program

[0723] The server collects and analyzes test result data for all students and uses a statistical analysis module to identify each student's strengths and weaknesses.

[0724] Input: Test result data for all students

[0725] Output: Identification of strengths and weaknesses for each student

[0726] Data Computation: Statistical Analysis

[0727] The server uses this information to optimize the next test or study program, specifically adjusting the layout of questions and study materials to strengthen strengths and compensate for weaknesses.

[0728] Input: Strengths and weaknesses of each student

[0729] Output: Optimized learning program data

[0730] Data Computing: Learning Program Generation and Optimization

[0731] Step 5: Virtual classroom access in a virtual space

[0732] Users (students) log in to the virtual space and participate in classes with other students. Specifically, students wear smart glasses or a head-mounted display and access the virtual classroom.

[0733] Input: User login information

[0734] Output: Virtual classroom access permission

[0735] Data calculation: Login authentication and access right confirmation

[0736] Students can take live lessons with other students in a virtual classroom and interact in real time.

[0737] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0738] The present invention is an educational support system that is configured by combining student terminals, a server, a teacher terminal, and an emotion engine. The specific configuration and operation of this system will be described below.

[0739] System configuration

[0740] 1. Student Device: A device (tablet, PC, smartphone, etc.) used by students to take tests and receive feedback. This device is equipped with an interface for starting and ending tests and inputting and submitting answers. It also has an integrated emotion engine that can analyze students' facial expressions and reactions to generate emotion data.

[0741] 2. Server: This is the central part of the educational support system. This server has the following functions:

[0742] Test response data is received, compared with a standard answer database, and automatically scored.

[0743] Stores the marks in a database and identifies unanswered questions.

[0744] An AI system is used to generate an explanation for each unanswered question, and the explanation data is sent to the student's device.

[0745] Analyze test result data and emotional data for all students to optimize the next test and learning program.

[0746] 3. Teacher terminal: A device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotional data, supporting effective instruction.

[0747] 4. Emotion Engine: A system that analyzes students' facial expressions and reactions to generate emotional data. The emotional data is sent from the student's device to a server and used to optimize the learning program.

[0748] System Operation

[0749] 1. Testing and Completion

[0750] Student device: The user (student) starts the test and enters answers to the questions. When the test is finished, the student device sends a notification of the test completion and the answer data to the server. In addition, the device monitors the student's facial expressions and reactions during the test and generates emotion data in real time.

[0751] Examples:

[0752] While students are taking the Japanese language test, the device's camera monitors their facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the emotional data is sent to the server along with the students' answers.

[0753] 2. Automatic scoring and analysis

[0754] Server: The server decodes the received answer data, compares it with a standard answer database, and automatically scores each question. The scoring results are stored in a database.

[0755] Examples:

[0756] The server receives the students' answers, compares them with standard answers, and calculates a score for each question, including the reading of kanji. The results are recorded in the individual student's database.

[0757] 3. Explanation generation for unanswered questions

[0758] Server: The server identifies unanswered questions from the students' answer data, generates explanations using the AI ​​system, and sends the generated explanation data to the students' devices.

[0759] Examples:

[0760] If a student leaves a kanji writing question unanswered, the server will recognize this and the AI ​​system will generate an explanation on how to write the kanji and send it to the student's device.

[0761] 4. Optimizing learning programs

[0762] Server: The server collects and analyzes test results and emotional data from all students to individually optimize the next test and study program. For example, if a student feels stressed about a particular problem, the server generates a study program that includes additional learning materials or a different approach to that problem.

[0763] Examples:

[0764] If a student feels highly stressed by a "reading comprehension" question and this is reflected in the emotional data, the server will optimize the next learning program to include more practice questions and supplementary materials in that area.

[0765] 5. Display of learning materials and learning feedback

[0766] Teacher's terminal: The teacher's terminal displays the optimized learning program data and student's emotional data received from the server. Based on this, the teacher can provide appropriate feedback and guidance to the student.

[0767] Examples:

[0768] A teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations and practice of the geometry problem during class.

[0769] As described above, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[0770] The processing flow will be explained below.

[0771] Step 1:

[0772] The user (student) starts the test on the student's device. The student's device displays the test questions on the screen and provides an interface for entering answers. Meanwhile, the emotion engine installed on the device monitors the student's facial expressions and reactions in real time and generates emotion data.

[0773] Step 2:

[0774] The user (student) enters the answer to each question and presses the end test button after completing all questions. The student's device encodes the user's answer data and the emotion data collected during the test into JSON format.

[0775] Step 3:

[0776] The student device sends the encoded response data and emotion data to the server using an HTTP POST request. The server receives the request and begins analyzing the data.

[0777] Step 4:

[0778] The server decodes the received JSON data and extracts each question ID and answer data. The server checks the correctness of each question against a standard answer database and calculates the score. The calculated score is saved in a database.

[0779] Step 5:

[0780] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[0781] Step 6:

[0782] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[0783] Step 7:

[0784] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the user (student).

[0785] Step 8:

[0786] The server periodically collects and analyzes test result data and emotional data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[0787] Step 9:

[0788] The server then uses the analyzed data to individually optimize the next test or study program. For example, if a student feels particularly stressed about a particular problem, it will generate a study program that includes additional material or a different approach to that problem.

[0789] Step 10:

[0790] The server sends the optimized learning program data to the teacher's terminal via an HTTP POST request, which then displays a dashboard to provide optimal feedback to each student.

[0791] Step 11:

[0792] The teacher's terminal checks each student's progress based on the optimized learning program data and student emotion data sent from the server. The teacher uses this data to provide appropriate feedback to each student.

[0793] Step 12:

[0794] The teacher inputs the feedback he or she wants to provide to the student into the teacher's terminal and sends it to the server, which then collects this feedback data and uses it to optimize the learning program.

[0795] Example 2

[0796] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0797] Conventional educational support systems make it difficult to maximize the learning effect of individual students. Furthermore, they do not provide feedback that takes into account students' emotions, which can lead to a decrease in motivation to learn and stress. This increases the burden on teachers and often leads to a lack of individual instruction. Therefore, it is necessary to solve these issues.

[0798] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0799] In this invention, the server includes means for the student terminal to instruct the user to start the test, means for notifying the server of the end of the test and transmitting answer data and emotion data to the server, means for automatically scoring the received answer data and emotion data by comparing it with a standard answer database and saving the scoring results in the database, means for identifying unanswered questions from the student answer data and transmitting generated explanation data to the student terminal, means for analyzing the test result data and emotion data of all students and optimizing the next test or learning program, means for displaying the optimized learning program data and emotion data and providing feedback, and an emotion engine for the student terminal to generate emotion data in real time. This enables optimal feedback that takes into account each student's individual learning situation and emotions, resulting in effective learning support.

[0800] A "student device" is a device (e.g., tablet, PC, smartphone) used by a student to take a test or receive feedback.

[0801] The "server" is the central part of the educational support system, and is a device that receives, stores, analyzes, and optimizes various types of data.

[0802] The "emotion engine" is a system that analyzes students' facial expressions and reactions to generate emotional data, and is a device that collects emotional data from student devices in real time and transmits it to a server.

[0803] A "teacher terminal" is a device that allows a teacher to give feedback to students based on data received from the server.

[0804] "Standard answer database" refers to a database that stores correct answer data and is used by the server to automatically score tests.

[0805] "Scoring results" refers to score information generated after the server automatically scores the answer data it receives by comparing it with a standard answer database.

[0806] An "unanswered question" is a question that a student did not answer during the test.

[0807] "Explanation data" refers to information about explanations and commentaries generated by the server for unanswered questions, and is provided to help students deepen their understanding.

[0808] "Optimizing the next test or learning program" is the process in which the server analyzes the test result data and emotional data of all students and generates individually optimized test and learning program content.

[0809] "Feedback" is information that teachers use to provide guidance and areas for improvement to students' learning.

[0810] An "HTTP POST request" is one of the communication protocols used when a server sends data, and is a method of sending data from a client to a server.

[0811] "Statistical Analysis Module" means a software module that has the functionality to analyze data to identify areas of strength and weakness of a student.

[0812] The present invention is an educational support system that combines student terminals, a server, a teacher terminal, and an emotion engine. This system provides individually optimized education by cooperating with each hardware and software component.

[0813] Student Devices

[0814] The student device is a device (tablet, PC, smartphone, etc.) that students use to take tests and receive feedback. This device has an interface for starting and ending tests, and for entering and submitting answers. Furthermore, it is integrated with an emotion engine, which can analyze students' facial expressions and reactions to generate emotional data.

[0815] For example, while a student is taking a Japanese language test, the device's camera monitors the student's facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the student's emotional data is sent to the server along with their answer data.

[0816] server

[0817] The server is the central part of the educational support system. It has the following main functions:

[0818] 1. Automatic scoring: The server decodes the received answer data and automatically scores each question by comparing it with a standard answer database. The scoring results are stored in a database. For example, the server receives the student's answer data, compares questions including "how to read kanji" with the standard answers, and calculates the score for each.

[0819] 2. Generating explanations for unanswered questions: The server identifies unanswered questions from the student's answer data and generates explanations using the AI ​​system. The generated explanation data is sent to the student's device. For example, if a student leaves a "kanji dictation" question unanswered, the server recognizes this and the AI ​​system generates an explanation on "how to write that kanji" and sends it to the student's device.

[0820] 3. Optimizing learning programs: The server collects and analyzes test results and emotional data from all students, and then individually optimizes the next test and learning program. For students who feel particularly stressed by a particular problem, the server provides additional learning materials or different approaches to that problem.

[0821] Teacher's terminal

[0822] The teacher terminal is a device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotion data to support effective instruction.

[0823] For example, a teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations or practice of the geometry problem during class.

[0824] Emotion Engine

[0825] The emotion engine is a system that analyzes students' facial expressions and reactions to generate emotion data. The emotion data is sent from the student's device to a server and used to optimize the learning program.

[0826] For example, if a student feels anxious or worried during a test, that emotional data is sent to the server in real time and reflected in the next learning program.

[0827] Using generative AI models

[0828] A generative AI model is used to optimize the entire system and generate explanations. Specific examples of prompts include "How to train an AI model to automatically generate explanations for unanswered questions" and "How to optimize learning programs by analyzing student sentiment data."

[0829] In this way, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[0830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] Starting the test

[0833] User (Student): When the user presses the "Start Test" button on the student's device, the system displays the test interface and activates the device's camera to record the student's facial expression in real time.

[0834] Input: User clicks the "Start Test" button.

[0835] Output: Display of test interface and start of camera.

[0836] How it works: When a student clicks the "Start Test" button on the tablet, the first question appears on the screen, and the camera begins monitoring the student's facial expressions.

[0837] Step 2:

[0838] Enter your answer

[0839] User (student): The user answers the questions by tapping the correct answer for multiple choice questions and typing the answer on the keyboard for written questions.

[0840] Input: User answer input.

[0841] Output: Temporarily save answer data.

[0842] Specific operation: The student enters the answer to the "Kanji reading" question using the keyboard. If it is a multiple choice question, they tap on the option. Once the answer is entered, the next question will be displayed.

[0843] Step 3:

[0844] End of test and data transmission

[0845] User (student): When the user has answered all questions or the time is up, a notification is displayed that the test is over. When the user presses the end button, the answer data and emotion data are sent to the server.

[0846] Input: Test end operation.

[0847] Output: Sending response data and sentiment data.

[0848] Specific operation: At the end of the test, a message saying "Test completed" is displayed. When the student clicks the "Exit" button, the answer data and real-time collected emotion data are sent to the server.

[0849] Step 4:

[0850] Receiving data

[0851] Server: The server receives the response data and emotion data sent from the device, decodes them, and stores them.

[0852] Input: Receives response data and emotion data.

[0853] Output: Save to database.

[0854] Specific operation: The server captures the data stream, decodes the response data and emotion data, and stores them in a database.

[0855] Step 5:

[0856] Automatic scoring

[0857] Server: The server compares the answer data with a standard answer database and automatically scores the answers. The scores are stored in a database.

[0858] Input: Response data.

[0859] Output: Scoring results.

[0860] Specific operation: The received answer data "Kanji reading" is compared with the standard answer, and if the answer is correct, points are awarded, and if the answer is incorrect, no points are awarded. The results are recorded in the database.

[0861] Step 6:

[0862] Identifying unanswered questions

[0863] Server: The server analyzes the response data to identify unanswered questions and, if any, generates a list of unanswered questions.

[0864] Input: Response data.

[0865] Output: A list of unanswered questions.

[0866] What happens: The server loops through the answer data and identifies any entries that are blank. If the "Kanji dictation" question has not been answered, that information is listed.

[0867] Step 7:

[0868] Generate explanations

[0869] Server: The server uses an AI system to generate explanations for unanswered questions. The generated explanation data is sent to the student's device.

[0870] Input: List of unanswered questions.

[0871] Output: The generated narrative data.

[0872] Specific operation: The AI ​​system generates correct writing methods and example sentences for "kanji dictation" problems. Explanation data is compiled and sent to the student's device.

[0873] Step 8:

[0874] Optimizing your learning program

[0875] Server: The server analyzes test results and emotional data for all students and individually optimizes the next test and learning program, providing additional learning materials and different approaches to high-stress problems.

[0876] Input: Test result data and emotion data of all students.

[0877] Output: An optimized learning program.

[0878] Specific operation: Based on data on students who felt highly stressed by the "reading comprehension" questions, the server configures the next learning program to include additional practice questions and supplementary materials.

[0879] Step 9:

[0880] Data Display and Feedback

[0881] Teacher terminal: The teacher terminal displays the optimized learning program data and emotion data received from the server. The teacher provides feedback based on the displayed data.

[0882] Input: Optimized learning program data and emotion data.

[0883] Output: Feedback.

[0884] Specific behavior: The test results and emotional data of specific students are displayed on the dashboard of the teacher's device, and the teacher can provide feedback to the students, such as "Add more focus on specific questions in the next learning program."

[0885] (Application example 2)

[0886] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0887] Conventional educational support systems have limited data collection and analysis to maximize students' learning outcomes, and are unable to provide optimal feedback or guidance that takes into account students' emotional data. Furthermore, in the maintenance of factory robots, appropriate maintenance suggestions that take into account the emotional state of the technicians were not provided, which can increase technician stress and reduce efficiency. It is necessary to provide a sustainable system that solves these issues.

[0888] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0889] In this invention, the server includes means for receiving students' answer data, comparing it with a standard answer database to automatically score the answers, and storing the scoring results in a database; means for identifying unanswered questions from the students' answer data, generating explanations for each unanswered question using an AI system, and transmitting the explanation data to the student terminals; means for analyzing the test result data and emotion data of all students and optimizing the next test or study program; means for receiving and analyzing the robot's sensor data to generate robot maintenance suggestions and transmit the necessary actions to the engineer terminal; and means for the engineer terminal to generate emotion data using camera footage and transmit it to the server. This enables effective feedback, guidance, and maintenance suggestions that take emotion data into account in both educational settings and factories.

[0890] A "student device" is a device used by students to take tests and receive feedback.

[0891] The "server" is a central processing unit that receives students' answer data, compares it with a standard answer database, automatically scores it, and analyzes the test result data and emotional data of all students.

[0892] A "standard answer database" is a database that stores standard answers for tests.

[0893] "Automatic scoring" is the process by which the server compares student response data with a database of standard answers and calculates scores without human intervention.

[0894] An "AI system" is a system that uses artificial intelligence and has the ability to automatically generate explanations for students' unanswered questions.

[0895] "Explanation data" refers to the explanations generated by the AI ​​system for unanswered questions.

[0896] "Emotional data" refers to data on the emotional state of students and engineers obtained by analyzing their facial expressions and reactions.

[0897] "Robot sensor data" is data that includes status information such as temperature and vibration collected from robots operating in factories.

[0898] A "maintenance proposal" is a maintenance method proposal generated by the server based on the robot's sensor data and the technician's emotional data.

[0899] An "engineer terminal" is a device used by engineers to perform maintenance and operation of the robot.

[0900] "Camera video" refers to video data acquired by a camera mounted on the engineer's terminal.

[0901] This invention is a system that is configured by combining student terminals, a server, a teacher terminal, an engineer terminal, and an emotion engine. The detailed configuration and operation of this system will be explained below.

[0902] System configuration

[0903] 1. Student devices

[0904] The student terminal is a device used by students taking courses, and is equipped with an interface for students to take tests and receive feedback. The student terminal is equipped with a camera to monitor the students' facial expressions and reactions during tests, and the emotion engine analyzes this to generate emotion data.

[0905] 2. Server

[0906] The server is the central part of the system and has the following functions:

[0907] The system receives answer data sent from student devices and automatically scores them by comparing them with a standard answer database.

[0908] The scoring results and emotion data are stored in a database and analyzed together with the test result data of all students.

[0909] Unanswered questions are identified and explanations are generated using an AI system and sent to student devices.

[0910] Analyze student response data and sentiment data to optimize the next test or learning program.

[0911] It receives and analyzes the robot's sensor data to generate maintenance suggestions and send them to the technician's terminal.

[0912] 3. Teacher's terminal

[0913] The teacher terminal is a device that allows teachers to monitor students' learning progress and provide feedback. It displays optimized learning program data and student emotional data, supporting effective instruction.

[0914] 4. Technician terminal

[0915] The engineer terminal is a device used to perform maintenance and operation of factory robots. The engineer terminal is equipped with a camera that monitors the face of the engineer and generates emotional data. The generated emotional data is sent to the server and used to generate maintenance suggestions.

[0916] 5. Emotion Engine

[0917] The emotion engine is a system that analyzes camera footage and generates emotion data from the facial expressions and reactions of students and engineers. The emotion data is sent from the student and engineer devices to a server and is used to optimize learning programs and generate maintenance suggestions.

[0918] System Operation

[0919] Operation as an educational support system

[0920] 1. Testing and Completion

[0921] The start and end of the test are notified from the student's device, and the answer data is sent to the server. At the same time, the camera on the student's device monitors the student's facial expressions and generates emotional data in real time.

[0922] 2. Automatic scoring and analysis

[0923] The server automatically scores the received answer data by comparing it with a standard answer database, and the results are stored in the database.

[0924] 3. Explanation generation for unanswered questions

[0925] The server identifies unanswered questions and generates explanations using an AI system, which are then sent to the student's device.

[0926] 4. Optimizing learning programs

[0927] The server analyzes the test results and emotional data of all students and individually optimizes their next test and learning program.

[0928] Operation as a maintenance system for factory robots

[0929] 1. Robot status monitoring

[0930] The server receives sensor data from the factory robots and monitors their status in real time.

[0931] 2. Collecting engineer emotion data

[0932] The engineer's terminal monitors the engineer's facial expression using camera images, and an emotion engine generates emotion data.

[0933] 3. Generate maintenance proposals

[0934] The server analyzes the received sensor data and emotion data and sends appropriate maintenance suggestions to the technician's terminal.

[0935] Specific examples

[0936] If a robot running in a factory is experiencing high temperatures and an engineer is feeling stressed about the situation, the system will:

[0937] The server recognizes from the robot's sensor data that Robot A's temperature has reached 90°C and generates a cooling suggestion.

[0938] At the same time, the technician terminal detects from the camera footage that technician B's stress level is high and generates a break suggestion.

[0939] The server sends these suggestions to the technician's terminal, and the technician takes appropriate action accordingly.

[0940] Example prompts to input to the generative AI model

[0941] "Robot A's temperature is over 90°C. Also, Technician B's stress level is detected to be high. Please make appropriate maintenance suggestions."

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] Student device starts testing

[0945] The student device is operated by the user (student) and the test begins. The student device collects camera footage in real time, analyzes facial expressions, and generates emotion data.

[0946] Input: Start test by student operation, camera image

[0947] Output: Test start notification, real-time emotion data

[0948] Specific operation: The camera on the student's device captures the student's facial expression, which is then analyzed by the emotion engine to generate emotion data.

[0949] Step 2:

[0950] Student devices will receive a notification of test completion and send answer data.

[0951] The student's device notifies the server that the test has ended and sends the answer data. The emotion data collected during the test is also sent to the server.

[0952] Input: Test completion notification, answer data, emotion data

[0953] Output: Sending answer data and emotion data

[0954] Specific operation: After the student device finishes the test, it sends an HTTP request to the server and transmits the answer data and emotion data.

[0955] Step 3:

[0956] The server receives the answer data and scores it.

[0957] The server receives the answer data sent from the student's device, compares it with a standard answer database, and automatically scores it. The results are saved in the database.

[0958] Input: Answer data

[0959] Output: Scoring results, updated database

[0960] Specific operation: The server compares the answer data with the standard answer database, calculates the score, and stores it in the database.

[0961] Step 4:

[0962] The server identifies unanswered questions and generates explanations

[0963] The server analyzes the response data, identifies unanswered questions, uses an AI system to generate explanations for these questions, and sends the explanation data to the student's device.

[0964] Input: Answer data, standard answer database

[0965] Output: List of unanswered questions, explanation data

[0966] Specific operation: The server extracts unanswered questions from the response data, generates explanatory text using a generative AI model, and sends it to the student's device.

[0967] Step 5:

[0968] The server analyzes test results and emotional data to optimize the learning program.

[0969] The server analyzes the test result data and emotional data of all students and individually optimizes the next test and learning program.

[0970] Input: Test result data, emotion data

[0971] Output: Optimized learning program

[0972] How it works: The server analyzes the data using statistical analysis and machine learning models to generate an optimized learning program for each student.

[0973] Step 6:

[0974] The server receives and analyzes the robot's sensor data.

[0975] The server receives sensor data from the factory robots and analyzes the data in real time.

[0976] Input: Robot sensor data (temperature, vibration, etc.)

[0977] Output: Analysis results

[0978] Specific operation: The server analyzes temperature and vibration data and performs threshold judgments to detect abnormal conditions.

[0979] Step 7:

[0980] The engineer's terminal generates emotion data using camera footage.

[0981] The engineer's terminal monitors the engineer's facial expressions in real time, and the emotion engine generates emotion data and sends it to the server.

[0982] Input: Technician's camera feed

[0983] Output: Generated emotion data

[0984] Specific operation: The camera on the technician's terminal captures the technician's face, and the emotion engine analyzes the facial expressions to generate emotion data, which is then sent to the server.

[0985] Step 8:

[0986] Server generates and sends maintenance proposals

[0987] The server analyzes the received sensor data and emotion data, generates maintenance suggestions for the robot, and sends the suggestions to the technician's terminal.

[0988] Input: Sensor data, emotion data

[0989] Output: Maintenance suggestions

[0990] Specific operation: The server analyzes sensor data and emotion data using the generated AI model and recommends appropriate maintenance actions to the technician's terminal.

[0991] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0992] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0993] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0994] [Third embodiment]

[0995] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0996] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0997] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0998] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0999] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1000] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1001] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1002] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1003] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1004] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1005] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1006] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1007] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[1008] System configuration

[1009] 1. Student device: A device (tablet, PC, smartphone, etc.) used by students to take the test. This device has an interface for starting and ending the test, and for entering and submitting answers.

[1010] 2. Server: The central processing unit that forms the core of the educational support system. This server has the following functions:

[1011] Receives, decodes, and analyzes test response data.

[1012] The answers are compared with a database of standard answers and automatically graded.

[1013] Stores the marks in a database and identifies unanswered questions.

[1014] An AI system is used to generate explanations for unanswered questions.

[1015] Analyze test results for all students and generate optimized learning programs.

[1016] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[1017] System Operation

[1018] 1. Testing and Completion

[1019] Student device: The user (student) starts the test and enters the answers. When the test is finished, the student device sends the answer data to the server along with a notification that the test has finished.

[1020] Examples:

[1021] A student takes a math test on a tablet. When the student presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[1022] 2. Automatic scoring and analysis

[1023] Server: The server decodes the received answer data, compares it with the standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[1024] Examples:

[1025] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", it compares this with the standard answer and marks it as incorrect, giving the student 0 points.

[1026] 3. Explanation generation for unanswered questions

[1027] Server: After identifying unanswered questions, the server generates explanations using an AI system and sends the generated explanation data back to the student's device.

[1028] Examples:

[1029] If a student finishes the test without answering the "addition of fractions" question, the server will identify the question, generate an explanation for "addition of fractions" using AI, and send it to the student's device.

[1030] 4. Optimizing learning programs

[1031] Server: Collects and analyzes test result data from all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on that data and stores it in a database.

[1032] Examples:

[1033] If it turns out that a student has difficulty with adding fractions, adjust the next test or learning program to include more questions and materials related to adding fractions.

[1034] 5. Display of learning materials and learning feedback

[1035] Teacher terminal: The teacher terminal has an interface for displaying optimized learning program data and providing feedback to students, allowing teachers to provide effective instruction tailored to each student's level of understanding.

[1036] Examples:

[1037] A teacher opens the dashboard and sees that a student's weakness is "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[1038] In this way, the system of the present invention can effectively support students' learning and reduce the burden on teachers. This system is excellent in that it enhances students' understanding and provides learning programs optimized to meet individual learning needs.

[1039] The processing flow will be explained below.

[1040] Step 1:

[1041] The user (student) starts the test on the student terminal, which displays the test questions on the screen and provides an interface for the user to enter their answers.

[1042] Step 2:

[1043] The user (student) enters answers to the test questions, and after completing all questions, presses the end test button. The student device encodes the user's answer data into JSON format data.

[1044] Step 3:

[1045] The student terminal sends the encoded answer data to the server using an HTTP POST request, and the server receives the request and analyzes the answer data.

[1046] Step 4:

[1047] The server decodes the received JSON data, extracts each question ID and answer data, and checks the correctness of each question against a standard answer database.

[1048] Step 5:

[1049] The server calculates the score for each question based on the results of matching with the standard answer database, and the calculation results are saved in the database as the scoring results for each student.

[1050] Step 6:

[1051] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[1052] Step 7:

[1053] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[1054] Step 8:

[1055] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the student.

[1056] Step 9:

[1057] The server periodically collects and analyzes test result data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[1058] Step 10:

[1059] The server uses the analyzed data to optimize the next test and learning program, and stores the optimized learning program in a database.

[1060] Step 11:

[1061] The teacher terminal periodically receives optimized learning program data from the server, and uses this data to display a dashboard for providing individual feedback to each student.

[1062] Step 12:

[1063] Teachers can provide appropriate guidance to students by looking at the dashboard and provide feedback based on their progress. This feedback data is also sent to the server and used to continuously optimize the learning program.

[1064] Example 1

[1065] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1066] Conventional educational support systems have had issues with the difficulty of grasping each student's learning status and providing appropriate feedback, and they place a heavy burden on teachers. Furthermore, generating explanations for unanswered questions and optimizing learning programs for each student manually takes time and effort, so automation was needed.

[1067] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1068] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit the answer data to the server; means for the server to receive the answer data, automatically score the answer data by comparing it with a standard answer database, and store the scoring results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using an AI system, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the server to store the optimized study program in a database and transmit the generated study program data to the teacher terminal; and means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students. This allows for individual understanding of students' learning progress, providing quick and effective feedback, and reducing the burden on teachers. Furthermore, automating the generation of explanations for unanswered questions and the optimization of study programs improves the quality of education.

[1069] The "server" is the central processing unit of the educational support system, and is a device that analyzes received answer data, automatically grades answers, generates explanations, and optimizes the learning program.

[1070] "Student terminal" means a device used by a student to take a test, and is equipped with an interface for starting and ending the test and for inputting and submitting answers.

[1071] A "teacher terminal" is a device that allows teachers to check students' learning status and provide feedback based on an optimized learning program.

[1072] "Answer data" is data that includes information about test answers, and is sent from the student terminal to the server at the end of the test.

[1073] The "standard answer database" is a database that records correct answer information for tests, and is used by the server when automatically scoring tests.

[1074] "Automatic scoring" is the process by which the server compares the received answer data with a database of standard answers to calculate a score.

[1075] An "unanswered question" is a question to which a student did not enter an answer on the test.

[1076] "Explanation" is an explanatory text generated by the AI ​​system for unanswered questions, containing information to help students deepen their understanding.

[1077] An "optimized learning program" is a program generated by the server by analyzing the test result data of students and providing optimal learning content for each student.

[1078] A "database" is a data storage device for efficiently storing, managing, and searching information, and in the present invention, mainly stores grading results and learning programs.

[1079] An "HTTP POST request" is a standard communication protocol for sending data over the Internet, and is used in the present invention to send answer data and explanation data.

[1080] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[1081] System configuration

[1082] 1. Student device: This is the device used by students to take the test. This device can be a tablet, PC, smartphone, or other type of hardware. The student device has an interface for starting and ending the test, as well as entering and submitting answers.

[1083] 2. Server: This is the central processing unit that forms the core of the educational support system. This server has the following main functions:

[1084] Receiving and decoding response data: The system is equipped with a software module for receiving, decoding, and analyzing response data sent from student terminals.

[1085] Automatic scoring: Scores are calculated by comparing with a standard answer database. Scores are saved in a database for each student.

[1086] Explanation generation: An AI system is used to generate explanations for unanswered questions. The generated explanation data is then sent back to the student's device.

[1087] Optimizing learning programs: Collect and analyze the test results of all students to identify their strengths and weaknesses. Based on this, an optimized learning program for each student is generated and stored in the database.

[1088] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[1089] Hardware and software used

[1090] Hardware: Student devices (tablets, PCs, smartphones), teacher devices, servers

[1091] Software: Dedicated application for the educational support system, response data receiving module, automatic scoring module, AI explanation generation module, learning program optimization module, HTTP communication module

[1092] Specific examples

[1093] Example 1:

[1094] Students take a math test on a tablet. After completing the test, they tap the End Test button, encode their answers into JSON format, and then send it to the server as an HTTP POST request.

[1095] Example 2:

[1096] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", the server checks it against a database of standard answers and marks it as incorrect, giving the student zero points.

[1097] Example 3:

[1098] If a student leaves the "addition of fractions" problem unanswered and quits, the server will identify the problem, and the AI ​​system will generate an explanation for "addition of fractions" and send it to the student's device.

[1099] Example 4:

[1100] If a student is found to have difficulty with "adding fractions," the server will optimize the next test or learning program to include more questions and materials related to "adding fractions."

[1101] Example 5:

[1102] The teacher opens the dashboard on the teacher's computer and sees that a student has a weakness in "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[1103] Prompt Sentence Examples

[1104] Example prompt sentence:

[1105] "Please generate an explanation of how to add fractions. It is preferable that the explanation includes specific steps and examples."

[1106] The above is a concrete example of the educational support system. This system grasps each student's learning situation individually and provides quick and accurate feedback. It also reduces the burden on teachers and improves the quality of education.

[1107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1108] Step 1:

[1109] The student device starts the test, and the user (student) enters the answers. After the test is completed, the student device taps the "End Test" button and sends the answer data to the server.

[1110] Input: Test answers entered by the user (student)

[1111] Output: JSON-encoded response data

[1112] Specific operation: When the user has finished answering all the questions, they tap the "Submit" button on the student's device, which encodes the answer data into JSON format and sends it to the server as an HTTP POST request.

[1113] Step 2:

[1114] The server decodes and analyzes the answer data received from the student's device, then automatically scores it by comparing it with a standard answer database, and calculates the score.The calculated score data is then saved in the database.

[1115] Input: JSON formatted response data

[1116] Output:Scoring result data

[1117] Specific operation: The server receives and analyzes the answer data sent from the student's device. For example, if the answer is "4" to the question "2 + 3 =", the server checks it against the standard answer database and marks it as incorrect, giving it a score of 0. This is then stored in the database.

[1118] Step 3:

[1119] The server identifies unanswered questions from the students' answer data and uses an AI system to generate explanations for each unanswered question. The generated explanation data is then sent back to the student's device.

[1120] Input: Student response data

[1121] Output: Commentary data

[1122] Specific operation: The server analyzes the response data and lists any unanswered questions. An AI system is used to generate detailed explanations for the unanswered questions and send the explanation data to the student's device. For example, if "adding fractions" is left unanswered, an explanation for that subject is generated and sent to the student's device.

[1123] Step 4:

[1124] The server collects and analyzes the test results of all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on this information and stores it in a database.

[1125] Input: Test result data for all students

[1126] Output: Optimized learning program

[1127] Specific operation: The server aggregates and analyzes the test result data of all students. For example, if a student has a low score on "fraction addition," it identifies "fraction addition" as the student's weak point. It generates a learning program optimized for that student and stores it in the database.

[1128] Step 5:

[1129] The server sends optimized learning program data to the teacher's terminal, which displays it, and the teacher uses the data to provide appropriate feedback to each student.

[1130] Input: Optimized learning program data

[1131] Output: Teacher feedback

[1132] Specific operation: The teacher opens the dashboard on the teacher's device and checks the learning status of each student. For example, the teacher may determine that a student has a weakness in "adding fractions." In the next lesson, the teacher will focus on that area. The teacher will also provide individual feedback using the interface on the teacher's device.

[1133] (Application example 1)

[1134] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1135] Conventional educational support systems did not adequately provide optimal learning programs tailored to individual needs or provide feedback based on students' level of understanding when they progressed through online learning. Furthermore, even when students could not attend a physical classroom, there was no environment in place for them to learn while interacting with other students. Furthermore, there was a lack of systems that integrated advanced functions such as AI-based explanation generation and learning support in virtual classrooms, making it difficult to provide effective online education.

[1136] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1137] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit answer data to the server; means for the server to receive the answer data, compare it with a standard answer database, automatically grade it, and store the graded results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using a generative AI model, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students; and means for providing virtual classroom access in a virtual space so that students can participate in classes with other students in the virtual space. This allows students to study with an optimal program that meets their individual learning needs, even in an online environment, and to learn effectively while interacting with other students.

[1138] A "student device" is a device (smartphone, tablet, PC, smart glasses, head-mounted display, etc.) used by a student to take a test or participate in a learning program.

[1139] The "server" is a central processing unit that receives and processes answer data, and is a computer system that performs automatic scoring, analysis, explanation generation, and optimization of the learning program.

[1140] A "standard answer database" is a database that stores standard correct answers, allowing the server to automatically grade student answers.

[1141] A "generative AI model" is an artificial intelligence model used to automatically generate explanations for unanswered questions. Examples include natural language processing models.

[1142] A "virtual space" is a virtual reality or augmented reality environment that provides a virtual classroom where students can participate in online classes with other students.

[1143] "Virtual classroom access" is a feature that allows students to log in to a virtual space and participate in classes with other students.

[1144] "Optimized learning program data" refers to data on an educational program that is tailored to each student based on their test results and strengths and weaknesses.

[1145] "Feedback" refers to evaluations and advice provided to students by teachers or systems, which helps students improve their understanding.

[1146] "Test result data" refers to data that includes the answers given by students on tests and the results of their grading.

[1147] An "HTTP POST request" is one of the HTTP protocol methods used to send data from a client (student terminal) to a server.

[1148] "Statistical Analysis Module" means an analytical software module used to identify areas of strength and weakness for each Student.

[1149] "Explanation data" is data that is used to generate explanations for students' unanswered questions using a generative AI model and send them to the student's device.

[1150] "Optimizing the learning program" involves analyzing the test result data collected by the server and adjusting the content of the next test or learning program based on each student's strengths and weaknesses.

[1151] System Overview

[1152] This invention is an educational support system that uses student terminals, a server, and a teacher terminal. This system allows students to take tests online, the server automatically scores and analyzes the results, and teachers to provide individual learning support.

[1153] System configuration

[1154] 1. Student devices:

[1155] A device used by students to take tests. Devices include smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[1156] The student terminals are equipped with an interface for starting and ending the test, and for inputting and submitting answers.

[1157] 2. Server:

[1158] The server is a central processing unit that forms the core of the educational support system.

[1159] The server receives the answer data and automatically scores it by comparing it with a standard answer database.

[1160] The results of the scoring are stored in a database.

[1161] The server identifies unanswered questions from the student's response data and generates explanations using a generative AI model (such as the T5 Transformers model).

[1162] The explanation data is sent to the student's device, and appropriate explanations are provided based on prompts using an AI model.

[1163] The server analyzes the test result data of all students and uses a statistical analysis module to identify the strengths and weaknesses of each student and optimize the next test or learning program.

[1164] 3. Teacher's terminal:

[1165] This is a device that teachers can use to check students' learning status and provide feedback. Devices include PCs and tablets.

[1166] The teacher's terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate to each student.

[1167] Example of operation

[1168] 1. Testing and Completion

[1169] On the student's device, the user starts the test and enters the answers. When the user presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[1170] 2. Automatic scoring and analysis

[1171] The server decodes the received answer data, compares it with a standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[1172] For example, if a student answers "4" to the question "2+3=", the server compares it with the standard answer and marks it as incorrect, giving it a score of 0.

[1173] 3. Explanation generation for unanswered questions

[1174] The server identifies unanswered questions and generates explanations using a generative AI model.

[1175] As a specific example, if a student finishes a test without answering a question about "adding fractions," the server will identify the question, generate an explanation for "adding fractions" using a generative AI model, and send it to the student's device.

[1176] 4. Optimizing learning programs

[1177] The server collects and analyzes test result data for all students and identifies each student's strengths and weaknesses based on the generated prompts.

[1178] For example, if it turns out that a student has difficulty with "adding fractions," the next test or learning program will be adjusted to include more questions and materials related to "adding fractions."

[1179] 5. Virtual classroom access in virtual space

[1180] Students can log in to a virtual space and participate in classes with other students, allowing them to learn while interacting with other students just as they would in a physical classroom.

[1181] Through these measures, it is possible to provide online programs that are optimally tailored to individual learning needs and to create an environment where students can learn effectively while interacting with other students.

[1182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1183] Step 1: Conducting and Finishing the Test

[1184] The user (student) starts the test using the student terminal and enters the answers. Specifically, the student operates the terminal interface to answer the questions and presses the end button.

[1185] Input: Student answer data

[1186] Output: Test completion notification and answer data encoded in JSON format

[1187] Data processing: Encode answer data into JSON format

[1188] The student terminal sends the encoded answer data to the server via an HTTP POST request along with a test completion notification.

[1189] Step 2: Automated scoring and analysis

[1190] The server decodes the received answer data and checks it against a database of standard answers. Specifically, the server analyzes the answer data and compares each answer with the standard answers.

[1191] Input: Answer data (JSON format)

[1192] Output: Grade results for each student

[1193] Data processing: Matching the decoded answer data with the standard answer data

[1194] The server calculates the scores and stores the results in a database as the grades for each student.

[1195] Step 3: Generate explanations for unanswered questions

[1196] The server identifies unanswered questions from the student's answer data. Specifically, the server checks the answer data and checks for blank spaces.

[1197] Input: Answer data and standard answer data

[1198] Output: List of unanswered questions

[1199] Data processing: Identifying missing responses

[1200] The server uses a generative AI model to generate an explanation for each unanswered question. Specifically, the AI ​​model generates an explanation based on the prompt sentence.

[1201] Input: List of unanswered questions, prompt text

[1202] Output: Commentary data

[1203] Data Computation: Generating Explanations with Generative AI Models

[1204] The server transmits the generated commentary data to the student terminal.

[1205] Step 4: Optimize your learning program

[1206] The server collects and analyzes test result data for all students and uses a statistical analysis module to identify each student's strengths and weaknesses.

[1207] Input: Test result data for all students

[1208] Output: Identification of strengths and weaknesses for each student

[1209] Data Computation: Statistical Analysis

[1210] The server uses this information to optimize the next test or study program, specifically adjusting the layout of questions and study materials to strengthen strengths and compensate for weaknesses.

[1211] Input: Strengths and weaknesses of each student

[1212] Output: Optimized learning program data

[1213] Data Computing: Learning Program Generation and Optimization

[1214] Step 5: Virtual classroom access in a virtual space

[1215] Users (students) log in to the virtual space and participate in classes with other students. Specifically, students wear smart glasses or a head-mounted display and access the virtual classroom.

[1216] Input: User login information

[1217] Output: Virtual classroom access permission

[1218] Data calculation: Login authentication and access right confirmation

[1219] Students can take live lessons with other students in a virtual classroom and interact in real time.

[1220] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1221] The present invention is an educational support system that is configured by combining student terminals, a server, a teacher terminal, and an emotion engine. The specific configuration and operation of this system will be described below.

[1222] System configuration

[1223] 1. Student Device: A device (tablet, PC, smartphone, etc.) used by students to take tests and receive feedback. This device is equipped with an interface for starting and ending tests and inputting and submitting answers. It also has an integrated emotion engine that can analyze students' facial expressions and reactions to generate emotion data.

[1224] 2. Server: This is the central part of the educational support system. This server has the following functions:

[1225] Test response data is received, compared with a standard answer database, and automatically scored.

[1226] Stores the marks in a database and identifies unanswered questions.

[1227] An AI system is used to generate an explanation for each unanswered question, and the explanation data is sent to the student's device.

[1228] Analyze test result data and emotional data for all students to optimize the next test and learning program.

[1229] 3. Teacher terminal: A device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotional data, supporting effective instruction.

[1230] 4. Emotion Engine: A system that analyzes students' facial expressions and reactions to generate emotional data. The emotional data is sent from the student's device to a server and used to optimize the learning program.

[1231] System Operation

[1232] 1. Testing and Completion

[1233] Student device: The user (student) starts the test and enters answers to the questions. When the test is finished, the student device sends a notification of the test completion and the answer data to the server. In addition, the device monitors the student's facial expressions and reactions during the test and generates emotion data in real time.

[1234] Examples:

[1235] While students are taking the Japanese language test, the device's camera monitors their facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the emotional data is sent to the server along with the students' answers.

[1236] 2. Automatic scoring and analysis

[1237] Server: The server decodes the received answer data, compares it with a standard answer database, and automatically scores each question. The scoring results are stored in a database.

[1238] Examples:

[1239] The server receives the students' answers, compares them with standard answers, and calculates a score for each question, including the reading of kanji. The results are recorded in the individual student's database.

[1240] 3. Explanation generation for unanswered questions

[1241] Server: The server identifies unanswered questions from the students' answer data, generates explanations using the AI ​​system, and sends the generated explanation data to the students' devices.

[1242] Examples:

[1243] If a student leaves a kanji writing question unanswered, the server will recognize this and the AI ​​system will generate an explanation on how to write the kanji and send it to the student's device.

[1244] 4. Optimizing learning programs

[1245] Server: The server collects and analyzes test results and emotional data from all students to individually optimize the next test and study program. For example, if a student feels stressed about a particular problem, the server generates a study program that includes additional learning materials or a different approach to that problem.

[1246] Examples:

[1247] If a student feels highly stressed by a "reading comprehension" question and this is reflected in the emotional data, the server will optimize the next learning program to include more practice questions and supplementary materials in that area.

[1248] 5. Display of learning materials and learning feedback

[1249] Teacher's terminal: The teacher's terminal displays the optimized learning program data and student's emotional data received from the server. Based on this, the teacher can provide appropriate feedback and guidance to the student.

[1250] Examples:

[1251] A teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations and practice of the geometry problem during class.

[1252] As described above, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] The user (student) starts the test on the student's device. The student's device displays the test questions on the screen and provides an interface for entering answers. Meanwhile, the emotion engine installed on the device monitors the student's facial expressions and reactions in real time and generates emotion data.

[1256] Step 2:

[1257] The user (student) enters the answer to each question and presses the end test button after completing all questions. The student's device encodes the user's answer data and the emotion data collected during the test into JSON format.

[1258] Step 3:

[1259] The student device sends the encoded response data and emotion data to the server using an HTTP POST request. The server receives the request and begins analyzing the data.

[1260] Step 4:

[1261] The server decodes the received JSON data and extracts each question ID and answer data. The server checks the correctness of each question against a standard answer database and calculates the score. The calculated score is saved in a database.

[1262] Step 5:

[1263] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[1264] Step 6:

[1265] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[1266] Step 7:

[1267] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the user (student).

[1268] Step 8:

[1269] The server periodically collects and analyzes test result data and emotional data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[1270] Step 9:

[1271] The server then uses the analyzed data to individually optimize the next test or study program. For example, if a student feels particularly stressed about a particular problem, it will generate a study program that includes additional material or a different approach to that problem.

[1272] Step 10:

[1273] The server sends the optimized learning program data to the teacher's terminal via an HTTP POST request, which then displays a dashboard to provide optimal feedback to each student.

[1274] Step 11:

[1275] The teacher's terminal checks each student's progress based on the optimized learning program data and student emotion data sent from the server. The teacher uses this data to provide appropriate feedback to each student.

[1276] Step 12:

[1277] The teacher inputs the feedback he or she wants to provide to the student into the teacher's terminal and sends it to the server, which then collects this feedback data and uses it to optimize the learning program.

[1278] Example 2

[1279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1280] Conventional educational support systems make it difficult to maximize the learning effect of individual students. Furthermore, they do not provide feedback that takes into account students' emotions, which can lead to a decrease in motivation to learn and stress. This increases the burden on teachers and often leads to a lack of individual instruction. Therefore, it is necessary to solve these issues.

[1281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1282] In this invention, the server includes means for the student terminal to instruct the user to start the test, means for notifying the server of the end of the test and transmitting answer data and emotion data to the server, means for automatically scoring the received answer data and emotion data by comparing it with a standard answer database and saving the scoring results in the database, means for identifying unanswered questions from the student answer data and transmitting generated explanation data to the student terminal, means for analyzing the test result data and emotion data of all students and optimizing the next test or learning program, means for displaying the optimized learning program data and emotion data and providing feedback, and an emotion engine for the student terminal to generate emotion data in real time. This enables optimal feedback that takes into account each student's individual learning situation and emotions, resulting in effective learning support.

[1283] A "student device" is a device (e.g., tablet, PC, smartphone) used by a student to take a test or receive feedback.

[1284] The "server" is the central part of the educational support system, and is a device that receives, stores, analyzes, and optimizes various types of data.

[1285] The "emotion engine" is a system that analyzes students' facial expressions and reactions to generate emotional data, and is a device that collects emotional data from student devices in real time and transmits it to a server.

[1286] A "teacher terminal" is a device that allows a teacher to give feedback to students based on data received from the server.

[1287] "Standard answer database" refers to a database that stores correct answer data and is used by the server to automatically score tests.

[1288] "Scoring results" refers to score information generated after the server automatically scores the answer data it receives by comparing it with a standard answer database.

[1289] An "unanswered question" is a question that a student did not answer during the test.

[1290] "Explanation data" refers to information about explanations and commentaries generated by the server for unanswered questions, and is provided to help students deepen their understanding.

[1291] "Optimizing the next test or learning program" is the process in which the server analyzes the test result data and emotional data of all students and generates individually optimized test and learning program content.

[1292] "Feedback" is information that teachers use to provide guidance and areas for improvement to students' learning.

[1293] An "HTTP POST request" is one of the communication protocols used when a server sends data, and is a method of sending data from a client to a server.

[1294] "Statistical Analysis Module" means a software module that has the functionality to analyze data to identify areas of strength and weakness of a student.

[1295] The present invention is an educational support system that combines student terminals, a server, a teacher terminal, and an emotion engine. This system provides individually optimized education by cooperating with each hardware and software component.

[1296] Student Devices

[1297] The student device is a device (tablet, PC, smartphone, etc.) that students use to take tests and receive feedback. This device has an interface for starting and ending tests, and for entering and submitting answers. Furthermore, it is integrated with an emotion engine, which can analyze students' facial expressions and reactions to generate emotional data.

[1298] For example, while a student is taking a Japanese language test, the device's camera monitors the student's facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the student's emotional data is sent to the server along with their answer data.

[1299] server

[1300] The server is the central part of the educational support system. It has the following main functions:

[1301] 1. Automatic scoring: The server decodes the received answer data and automatically scores each question by comparing it with a standard answer database. The scoring results are stored in a database. For example, the server receives the student's answer data, compares questions including "how to read kanji" with the standard answers, and calculates the score for each.

[1302] 2. Generating explanations for unanswered questions: The server identifies unanswered questions from the student's answer data and generates explanations using the AI ​​system. The generated explanation data is sent to the student's device. For example, if a student leaves a "kanji dictation" question unanswered, the server recognizes this and the AI ​​system generates an explanation on "how to write that kanji" and sends it to the student's device.

[1303] 3. Optimizing learning programs: The server collects and analyzes test results and emotional data from all students, and then individually optimizes the next test and learning program. For students who feel particularly stressed by a particular problem, the server provides additional learning materials or different approaches to that problem.

[1304] Teacher's terminal

[1305] The teacher terminal is a device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotion data to support effective instruction.

[1306] For example, a teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations or practice of the geometry problem during class.

[1307] Emotion Engine

[1308] The emotion engine is a system that analyzes students' facial expressions and reactions to generate emotion data. The emotion data is sent from the student's device to a server and used to optimize the learning program.

[1309] For example, if a student feels anxious or worried during a test, that emotional data is sent to the server in real time and reflected in the next learning program.

[1310] Using generative AI models

[1311] A generative AI model is used to optimize the entire system and generate explanations. Specific examples of prompts include "How to train an AI model to automatically generate explanations for unanswered questions" and "How to optimize learning programs by analyzing student sentiment data."

[1312] In this way, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[1313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1314] Step 1:

[1315] Starting the test

[1316] User (Student): When the user presses the "Start Test" button on the student's device, the system displays the test interface and activates the device's camera to record the student's facial expression in real time.

[1317] Input: User clicks the "Start Test" button.

[1318] Output: Display of test interface and start of camera.

[1319] How it works: When a student clicks the "Start Test" button on the tablet, the first question appears on the screen, and the camera begins monitoring the student's facial expressions.

[1320] Step 2:

[1321] Enter your answer

[1322] User (student): The user answers the questions by tapping the correct answer for multiple choice questions and typing the answer on the keyboard for written questions.

[1323] Input: User answer input.

[1324] Output: Temporarily save answer data.

[1325] Specific operation: The student enters the answer to the "Kanji reading" question using the keyboard. If it is a multiple choice question, they tap on the option. Once the answer is entered, the next question will be displayed.

[1326] Step 3:

[1327] End of test and data transmission

[1328] User (student): When the user has answered all questions or the time is up, a notification is displayed that the test is over. When the user presses the end button, the answer data and emotion data are sent to the server.

[1329] Input: Test end operation.

[1330] Output: Sending response data and sentiment data.

[1331] Specific operation: At the end of the test, a message saying "Test completed" is displayed. When the student clicks the "Exit" button, the answer data and real-time collected emotion data are sent to the server.

[1332] Step 4:

[1333] Receiving data

[1334] Server: The server receives the response data and emotion data sent from the device, decodes them, and stores them.

[1335] Input: Receives response data and emotion data.

[1336] Output: Save to database.

[1337] Specific operation: The server captures the data stream, decodes the response data and emotion data, and stores them in a database.

[1338] Step 5:

[1339] Automatic scoring

[1340] Server: The server compares the answer data with a standard answer database and automatically scores the answers. The scores are stored in a database.

[1341] Input: Response data.

[1342] Output: Scoring results.

[1343] Specific operation: The received answer data "Kanji reading" is compared with the standard answer, and if the answer is correct, points are awarded, and if the answer is incorrect, no points are awarded. The results are recorded in the database.

[1344] Step 6:

[1345] Identifying unanswered questions

[1346] Server: The server analyzes the response data to identify unanswered questions and, if any, generates a list of unanswered questions.

[1347] Input: Response data.

[1348] Output: A list of unanswered questions.

[1349] What happens: The server loops through the answer data and identifies any entries that are blank. If the "Kanji dictation" question has not been answered, that information is listed.

[1350] Step 7:

[1351] Generate explanations

[1352] Server: The server uses an AI system to generate explanations for unanswered questions. The generated explanation data is sent to the student's device.

[1353] Input: List of unanswered questions.

[1354] Output: The generated narrative data.

[1355] Specific operation: The AI ​​system generates correct writing methods and example sentences for "kanji dictation" problems. Explanation data is compiled and sent to the student's device.

[1356] Step 8:

[1357] Optimizing your learning program

[1358] Server: The server analyzes test results and emotional data for all students and individually optimizes the next test and learning program, providing additional learning materials and different approaches to high-stress problems.

[1359] Input: Test result data and emotion data of all students.

[1360] Output: An optimized learning program.

[1361] Specific operation: Based on data on students who felt highly stressed by the "reading comprehension" questions, the server configures the next learning program to include additional practice questions and supplementary materials.

[1362] Step 9:

[1363] Data Display and Feedback

[1364] Teacher terminal: The teacher terminal displays the optimized learning program data and emotion data received from the server. The teacher provides feedback based on the displayed data.

[1365] Input: Optimized learning program data and emotion data.

[1366] Output: Feedback.

[1367] Specific behavior: The test results and emotional data of specific students are displayed on the dashboard of the teacher's device, and the teacher can provide feedback to the students, such as "Add more focus on specific questions in the next learning program."

[1368] (Application example 2)

[1369] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1370] Conventional educational support systems have limited data collection and analysis to maximize students' learning outcomes, and are unable to provide optimal feedback or guidance that takes into account students' emotional data. Furthermore, in the maintenance of factory robots, appropriate maintenance suggestions that take into account the emotional state of the technicians were not provided, which can increase technician stress and reduce efficiency. It is necessary to provide a sustainable system that solves these issues.

[1371] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1372] In this invention, the server includes means for receiving students' answer data, comparing it with a standard answer database to automatically score the answers, and storing the scoring results in a database; means for identifying unanswered questions from the students' answer data, generating explanations for each unanswered question using an AI system, and transmitting the explanation data to the student terminals; means for analyzing the test result data and emotion data of all students and optimizing the next test or study program; means for receiving and analyzing the robot's sensor data to generate robot maintenance suggestions and transmit the necessary actions to the engineer terminal; and means for the engineer terminal to generate emotion data using camera footage and transmit it to the server. This enables effective feedback, guidance, and maintenance suggestions that take emotion data into account in both educational settings and factories.

[1373] A "student device" is a device used by students to take tests and receive feedback.

[1374] The "server" is a central processing unit that receives students' answer data, compares it with a standard answer database, automatically scores it, and analyzes the test result data and emotional data of all students.

[1375] A "standard answer database" is a database that stores standard answers for tests.

[1376] "Automatic scoring" is the process by which the server compares student response data with a database of standard answers and calculates scores without human intervention.

[1377] An "AI system" is a system that uses artificial intelligence and has the ability to automatically generate explanations for students' unanswered questions.

[1378] "Explanation data" refers to the explanations generated by the AI ​​system for unanswered questions.

[1379] "Emotional data" refers to data on the emotional state of students and engineers obtained by analyzing their facial expressions and reactions.

[1380] "Robot sensor data" is data that includes status information such as temperature and vibration collected from robots operating in factories.

[1381] A "maintenance proposal" is a maintenance method proposal generated by the server based on the robot's sensor data and the technician's emotional data.

[1382] An "engineer terminal" is a device used by engineers to perform maintenance and operation of the robot.

[1383] "Camera video" refers to video data acquired by a camera mounted on the engineer's terminal.

[1384] This invention is a system that is configured by combining student terminals, a server, a teacher terminal, an engineer terminal, and an emotion engine. The detailed configuration and operation of this system will be explained below.

[1385] System configuration

[1386] 1. Student devices

[1387] The student terminal is a device used by students taking courses, and is equipped with an interface for students to take tests and receive feedback. The student terminal is equipped with a camera to monitor the students' facial expressions and reactions during tests, and the emotion engine analyzes this to generate emotion data.

[1388] 2. Server

[1389] The server is the central part of the system and has the following functions:

[1390] The system receives answer data sent from student devices and automatically scores them by comparing them with a standard answer database.

[1391] The scoring results and emotion data are stored in a database and analyzed together with the test result data of all students.

[1392] Unanswered questions are identified and explanations are generated using an AI system and sent to student devices.

[1393] Analyze student response data and sentiment data to optimize the next test or learning program.

[1394] It receives and analyzes the robot's sensor data to generate maintenance suggestions and send them to the technician's terminal.

[1395] 3. Teacher's terminal

[1396] The teacher terminal is a device that allows teachers to monitor students' learning progress and provide feedback. It displays optimized learning program data and student emotional data, supporting effective instruction.

[1397] 4. Technician terminal

[1398] The engineer terminal is a device used to perform maintenance and operation of factory robots. The engineer terminal is equipped with a camera that monitors the face of the engineer and generates emotional data. The generated emotional data is sent to the server and used to generate maintenance suggestions.

[1399] 5. Emotion Engine

[1400] The emotion engine is a system that analyzes camera footage and generates emotion data from the facial expressions and reactions of students and engineers. The emotion data is sent from the student and engineer devices to a server and is used to optimize learning programs and generate maintenance suggestions.

[1401] System Operation

[1402] Operation as an educational support system

[1403] 1. Testing and Completion

[1404] The start and end of the test are notified from the student's device, and the answer data is sent to the server. At the same time, the camera on the student's device monitors the student's facial expressions and generates emotional data in real time.

[1405] 2. Automatic scoring and analysis

[1406] The server automatically scores the received answer data by comparing it with a standard answer database, and the results are stored in the database.

[1407] 3. Explanation generation for unanswered questions

[1408] The server identifies unanswered questions and generates explanations using an AI system, which are then sent to the student's device.

[1409] 4. Optimizing learning programs

[1410] The server analyzes the test results and emotional data of all students and individually optimizes their next test and learning program.

[1411] Operation as a maintenance system for factory robots

[1412] 1. Robot status monitoring

[1413] The server receives sensor data from the factory robots and monitors their status in real time.

[1414] 2. Collecting engineer emotion data

[1415] The engineer's terminal monitors the engineer's facial expression using camera images, and an emotion engine generates emotion data.

[1416] 3. Generate maintenance proposals

[1417] The server analyzes the received sensor data and emotion data and sends appropriate maintenance suggestions to the technician's terminal.

[1418] Specific examples

[1419] If a robot running in a factory is experiencing high temperatures and an engineer is feeling stressed about the situation, the system will:

[1420] The server recognizes from the robot's sensor data that Robot A's temperature has reached 90°C and generates a cooling suggestion.

[1421] At the same time, the technician terminal detects from the camera footage that technician B's stress level is high and generates a break suggestion.

[1422] The server sends these suggestions to the technician's terminal, and the technician takes appropriate action accordingly.

[1423] Example prompts to input to the generative AI model

[1424] "Robot A's temperature is over 90°C. Also, Technician B's stress level is detected to be high. Please make appropriate maintenance suggestions."

[1425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1426] Step 1:

[1427] Student device starts testing

[1428] The student device is operated by the user (student) and the test begins. The student device collects camera footage in real time, analyzes facial expressions, and generates emotion data.

[1429] Input: Start test by student operation, camera image

[1430] Output: Test start notification, real-time emotion data

[1431] Specific operation: The camera on the student's device captures the student's facial expression, which is then analyzed by the emotion engine to generate emotion data.

[1432] Step 2:

[1433] Student devices will receive a notification of test completion and send answer data.

[1434] The student's device notifies the server that the test has ended and sends the answer data. The emotion data collected during the test is also sent to the server.

[1435] Input: Test completion notification, answer data, emotion data

[1436] Output: Sending answer data and emotion data

[1437] Specific operation: After the student device finishes the test, it sends an HTTP request to the server and transmits the answer data and emotion data.

[1438] Step 3:

[1439] The server receives the answer data and scores it.

[1440] The server receives the answer data sent from the student's device, compares it with a standard answer database, and automatically scores it. The results are saved in the database.

[1441] Input: Answer data

[1442] Output: Scoring results, updated database

[1443] Specific operation: The server compares the answer data with the standard answer database, calculates the score, and stores it in the database.

[1444] Step 4:

[1445] The server identifies unanswered questions and generates explanations

[1446] The server analyzes the response data, identifies unanswered questions, uses an AI system to generate explanations for these questions, and sends the explanation data to the student's device.

[1447] Input: Answer data, standard answer database

[1448] Output: List of unanswered questions, explanation data

[1449] Specific operation: The server extracts unanswered questions from the response data, generates explanatory text using a generative AI model, and sends it to the student's device.

[1450] Step 5:

[1451] The server analyzes test results and emotional data to optimize the learning program.

[1452] The server analyzes the test result data and emotional data of all students and individually optimizes the next test and learning program.

[1453] Input: Test result data, emotion data

[1454] Output: Optimized learning program

[1455] How it works: The server analyzes the data using statistical analysis and machine learning models to generate an optimized learning program for each student.

[1456] Step 6:

[1457] The server receives and analyzes the robot's sensor data.

[1458] The server receives sensor data from the factory robots and analyzes the data in real time.

[1459] Input: Robot sensor data (temperature, vibration, etc.)

[1460] Output: Analysis results

[1461] Specific operation: The server analyzes temperature and vibration data and performs threshold judgments to detect abnormal conditions.

[1462] Step 7:

[1463] The engineer's terminal generates emotion data using camera footage.

[1464] The engineer's terminal monitors the engineer's facial expressions in real time, and the emotion engine generates emotion data and sends it to the server.

[1465] Input: Technician's camera feed

[1466] Output: Generated emotion data

[1467] Specific operation: The camera on the technician's terminal captures the technician's face, and the emotion engine analyzes the facial expressions to generate emotion data, which is then sent to the server.

[1468] Step 8:

[1469] Server generates and sends maintenance proposals

[1470] The server analyzes the received sensor data and emotion data, generates maintenance suggestions for the robot, and sends the suggestions to the technician's terminal.

[1471] Input: Sensor data, emotion data

[1472] Output: Maintenance suggestions

[1473] Specific operation: The server analyzes sensor data and emotion data using the generated AI model and recommends appropriate maintenance actions to the technician's terminal.

[1474] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1476] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1477] [Fourth embodiment]

[1478] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1479] 7, a 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.

[1480] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1481] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1482] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1483] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1484] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1485] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1486] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1489] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1490] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1491] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[1492] System configuration

[1493] 1. Student device: A device (tablet, PC, smartphone, etc.) used by students to take the test. This device has an interface for starting and ending the test, and for entering and submitting answers.

[1494] 2. Server: The central processing unit that forms the core of the educational support system. This server has the following functions:

[1495] Receives, decodes, and analyzes test response data.

[1496] The answers are compared with a database of standard answers and automatically graded.

[1497] Stores the marks in a database and identifies unanswered questions.

[1498] An AI system is used to generate explanations for unanswered questions.

[1499] Analyze test results for all students and generate optimized learning programs.

[1500] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[1501] System Operation

[1502] 1. Testing and Completion

[1503] Student device: The user (student) starts the test and enters the answers. When the test is finished, the student device sends the answer data to the server along with a notification that the test has finished.

[1504] Examples:

[1505] A student takes a math test on a tablet. When the student presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[1506] 2. Automatic scoring and analysis

[1507] Server: The server decodes the received answer data, compares it with the standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[1508] Examples:

[1509] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", it compares this with the standard answer and marks it as incorrect, giving the student 0 points.

[1510] 3. Explanation generation for unanswered questions

[1511] Server: After identifying unanswered questions, the server generates explanations using an AI system and sends the generated explanation data back to the student's device.

[1512] Examples:

[1513] If a student finishes the test without answering the "addition of fractions" question, the server will identify the question, generate an explanation for "addition of fractions" using AI, and send it to the student's device.

[1514] 4. Optimizing learning programs

[1515] Server: Collects and analyzes test result data from all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on that data and stores it in a database.

[1516] Examples:

[1517] If it turns out that a student has difficulty with adding fractions, adjust the next test or learning program to include more questions and materials related to adding fractions.

[1518] 5. Display of learning materials and learning feedback

[1519] Teacher terminal: The teacher terminal has an interface for displaying optimized learning program data and providing feedback to students, allowing teachers to provide effective instruction tailored to each student's level of understanding.

[1520] Examples:

[1521] A teacher opens the dashboard and sees that a student's weakness is "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[1522] In this way, the system of the present invention can effectively support students' learning and reduce the burden on teachers. This system is excellent in that it enhances students' understanding and provides learning programs optimized to meet individual learning needs.

[1523] The processing flow will be explained below.

[1524] Step 1:

[1525] The user (student) starts the test on the student terminal, which displays the test questions on the screen and provides an interface for the user to enter their answers.

[1526] Step 2:

[1527] The user (student) enters answers to the test questions, and after completing all questions, presses the end test button. The student device encodes the user's answer data into JSON format data.

[1528] Step 3:

[1529] The student terminal sends the encoded answer data to the server using an HTTP POST request, and the server receives the request and analyzes the answer data.

[1530] Step 4:

[1531] The server decodes the received JSON data, extracts each question ID and answer data, and checks the correctness of each question against a standard answer database.

[1532] Step 5:

[1533] The server calculates the score for each question based on the results of matching with the standard answer database, and the calculation results are saved in the database as the scoring results for each student.

[1534] Step 6:

[1535] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[1536] Step 7:

[1537] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[1538] Step 8:

[1539] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the student.

[1540] Step 9:

[1541] The server periodically collects and analyzes test result data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[1542] Step 10:

[1543] The server uses the analyzed data to optimize the next test and learning program, and stores the optimized learning program in a database.

[1544] Step 11:

[1545] The teacher terminal periodically receives optimized learning program data from the server, and uses this data to display a dashboard for providing individual feedback to each student.

[1546] Step 12:

[1547] Teachers can provide appropriate guidance to students by looking at the dashboard and provide feedback based on their progress. This feedback data is also sent to the server and used to continuously optimize the learning program.

[1548] Example 1

[1549] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1550] Conventional educational support systems have had issues with the difficulty of grasping each student's learning status and providing appropriate feedback, and they place a heavy burden on teachers. Furthermore, generating explanations for unanswered questions and optimizing learning programs for each student manually takes time and effort, so automation was needed.

[1551] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1552] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit the answer data to the server; means for the server to receive the answer data, automatically score the answer data by comparing it with a standard answer database, and store the scoring results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using an AI system, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the server to store the optimized study program in a database and transmit the generated study program data to the teacher terminal; and means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students. This allows for individual understanding of students' learning progress, providing quick and effective feedback, and reducing the burden on teachers. Furthermore, automating the generation of explanations for unanswered questions and the optimization of study programs improves the quality of education.

[1553] The "server" is the central processing unit of the educational support system, and is a device that analyzes received answer data, automatically grades answers, generates explanations, and optimizes the learning program.

[1554] "Student terminal" means a device used by a student to take a test, and is equipped with an interface for starting and ending the test and for inputting and submitting answers.

[1555] A "teacher terminal" is a device that allows teachers to check students' learning status and provide feedback based on an optimized learning program.

[1556] "Answer data" is data that includes information about test answers, and is sent from the student terminal to the server at the end of the test.

[1557] The "standard answer database" is a database that records correct answer information for tests, and is used by the server when automatically scoring tests.

[1558] "Automatic scoring" is the process by which the server compares the received answer data with a database of standard answers to calculate a score.

[1559] An "unanswered question" is a question to which a student did not enter an answer on the test.

[1560] "Explanation" is an explanatory text generated by the AI ​​system for unanswered questions, containing information to help students deepen their understanding.

[1561] An "optimized learning program" is a program generated by the server by analyzing the test result data of students and providing optimal learning content for each student.

[1562] A "database" is a data storage device for efficiently storing, managing, and searching information, and in the present invention, mainly stores grading results and learning programs.

[1563] An "HTTP POST request" is a standard communication protocol for sending data over the Internet, and is used in the present invention to send answer data and explanation data.

[1564] The present invention is an educational support system that utilizes student terminals, a server, and a teacher terminal. The specific configuration and operation of this system will be described below.

[1565] System configuration

[1566] 1. Student device: This is the device used by students to take the test. This device can be a tablet, PC, smartphone, or other type of hardware. The student device has an interface for starting and ending the test, as well as entering and submitting answers.

[1567] 2. Server: This is the central processing unit that forms the core of the educational support system. This server has the following main functions:

[1568] Receiving and decoding response data: The system is equipped with a software module for receiving, decoding, and analyzing response data sent from student terminals.

[1569] Automatic scoring: Scores are calculated by comparing with a standard answer database. Scores are saved in a database for each student.

[1570] Explanation generation: An AI system is used to generate explanations for unanswered questions. The generated explanation data is then sent back to the student's device.

[1571] Optimizing learning programs: Collect and analyze the test results of all students to identify their strengths and weaknesses. Based on this, an optimized learning program for each student is generated and stored in the database.

[1572] 3. Teacher terminal: A device that allows teachers to check students' learning status and provide feedback. This terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate for each student.

[1573] Hardware and software used

[1574] Hardware: Student devices (tablets, PCs, smartphones), teacher devices, servers

[1575] Software: Dedicated application for the educational support system, response data receiving module, automatic scoring module, AI explanation generation module, learning program optimization module, HTTP communication module

[1576] Specific examples

[1577] Example 1:

[1578] Students take a math test on a tablet. After completing the test, they tap the End Test button, encode their answers into JSON format, and then send it to the server as an HTTP POST request.

[1579] Example 2:

[1580] The server receives and analyzes the student's answer data. For example, if the student answers "4" to the question "2 + 3 =", the server checks it against a database of standard answers and marks it as incorrect, giving the student zero points.

[1581] Example 3:

[1582] If a student leaves the "addition of fractions" problem unanswered and quits, the server will identify the problem, and the AI ​​system will generate an explanation for "addition of fractions" and send it to the student's device.

[1583] Example 4:

[1584] If a student is found to have difficulty with "adding fractions," the server will optimize the next test or learning program to include more questions and materials related to "adding fractions."

[1585] Example 5:

[1586] The teacher opens the dashboard on the teacher's computer and sees that a student has a weakness in "adding fractions." The teacher then focuses instruction on that area in the next lesson.

[1587] Prompt Sentence Examples

[1588] Example prompt sentence:

[1589] "Please generate an explanation of how to add fractions. It is preferable that the explanation includes specific steps and examples."

[1590] The above is a concrete example of the educational support system. This system grasps each student's learning situation individually and provides quick and accurate feedback. It also reduces the burden on teachers and improves the quality of education.

[1591] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1592] Step 1:

[1593] The student device starts the test, and the user (student) enters the answers. After the test is completed, the student device taps the "End Test" button and sends the answer data to the server.

[1594] Input: Test answers entered by the user (student)

[1595] Output: JSON-encoded response data

[1596] Specific operation: When the user has finished answering all the questions, they tap the "Submit" button on the student's device, which encodes the answer data into JSON format and sends it to the server as an HTTP POST request.

[1597] Step 2:

[1598] The server decodes and analyzes the answer data received from the student's device, then automatically scores it by comparing it with a standard answer database, and calculates the score.The calculated score data is then saved in the database.

[1599] Input: JSON formatted response data

[1600] Output:Scoring result data

[1601] Specific operation: The server receives and analyzes the answer data sent from the student's device. For example, if the answer is "4" to the question "2 + 3 =", the server checks it against the standard answer database and marks it as incorrect, giving it a score of 0. This is then stored in the database.

[1602] Step 3:

[1603] The server identifies unanswered questions from the students' answer data and uses an AI system to generate explanations for each unanswered question. The generated explanation data is then sent back to the student's device.

[1604] Input: Student response data

[1605] Output: Commentary data

[1606] Specific operation: The server analyzes the response data and lists any unanswered questions. An AI system is used to generate detailed explanations for the unanswered questions and send the explanation data to the student's device. For example, if "adding fractions" is left unanswered, an explanation for that subject is generated and sent to the student's device.

[1607] Step 4:

[1608] The server collects and analyzes the test results of all students, identifies their strengths and weaknesses, and generates an optimized learning program for each student based on this information and stores it in a database.

[1609] Input: Test result data for all students

[1610] Output: Optimized learning program

[1611] Specific operation: The server aggregates and analyzes the test result data of all students. For example, if a student has a low score on "fraction addition," it identifies "fraction addition" as the student's weak point. It generates a learning program optimized for that student and stores it in the database.

[1612] Step 5:

[1613] The server sends optimized learning program data to the teacher's terminal, which displays it, and the teacher uses the data to provide appropriate feedback to each student.

[1614] Input: Optimized learning program data

[1615] Output: Teacher feedback

[1616] Specific operation: The teacher opens the dashboard on the teacher's device and checks the learning status of each student. For example, the teacher may determine that a student has a weakness in "adding fractions." In the next lesson, the teacher will focus on that area. The teacher will also provide individual feedback using the interface on the teacher's device.

[1617] (Application example 1)

[1618] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1619] Conventional educational support systems did not adequately provide optimal learning programs tailored to individual needs or provide feedback based on students' level of understanding when they progressed through online learning. Furthermore, even when students could not attend a physical classroom, there was no environment in place for them to learn while interacting with other students. Furthermore, there was a lack of systems that integrated advanced functions such as AI-based explanation generation and learning support in virtual classrooms, making it difficult to provide effective online education.

[1620] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1621] In this invention, the server includes: means for the student terminal to notify the server of the completion of the test and transmit answer data to the server; means for the server to receive the answer data, compare it with a standard answer database, automatically grade it, and store the graded results in a database; means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using a generative AI model, and transmit the explanation data to the student terminal; means for the server to analyze the test result data of all students and optimize the next test and study program; means for the teacher terminal to display the optimized study program data received from the server and provide feedback to the students; and means for providing virtual classroom access in a virtual space so that students can participate in classes with other students in the virtual space. This allows students to study with an optimal program that meets their individual learning needs, even in an online environment, and to learn effectively while interacting with other students.

[1622] A "student device" is a device (smartphone, tablet, PC, smart glasses, head-mounted display, etc.) used by a student to take a test or participate in a learning program.

[1623] The "server" is a central processing unit that receives and processes answer data, and is a computer system that performs automatic scoring, analysis, explanation generation, and optimization of the learning program.

[1624] A "standard answer database" is a database that stores standard correct answers, allowing the server to automatically grade student answers.

[1625] A "generative AI model" is an artificial intelligence model used to automatically generate explanations for unanswered questions. Examples include natural language processing models.

[1626] A "virtual space" is a virtual reality or augmented reality environment that provides a virtual classroom where students can participate in online classes with other students.

[1627] "Virtual classroom access" is a feature that allows students to log in to a virtual space and participate in classes with other students.

[1628] "Optimized learning program data" refers to data on an educational program that is tailored to each student based on their test results and strengths and weaknesses.

[1629] "Feedback" refers to evaluations and advice provided to students by teachers or systems, which helps students improve their understanding.

[1630] "Test result data" refers to data that includes the answers given by students on tests and the results of their grading.

[1631] An "HTTP POST request" is one of the HTTP protocol methods used to send data from a client (student terminal) to a server.

[1632] "Statistical Analysis Module" means an analytical software module used to identify areas of strength and weakness for each Student.

[1633] "Explanation data" is data that is used to generate explanations for students' unanswered questions using a generative AI model and send them to the student's device.

[1634] "Optimizing the learning program" involves analyzing the test result data collected by the server and adjusting the content of the next test or learning program based on each student's strengths and weaknesses.

[1635] System Overview

[1636] This invention is an educational support system that uses student terminals, a server, and a teacher terminal. This system allows students to take tests online, the server automatically scores and analyzes the results, and teachers to provide individual learning support.

[1637] System configuration

[1638] 1. Student devices:

[1639] A device used by students to take tests. Devices include smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[1640] The student terminals are equipped with an interface for starting and ending the test, and for inputting and submitting answers.

[1641] 2. Server:

[1642] The server is a central processing unit that forms the core of the educational support system.

[1643] The server receives the answer data and automatically scores it by comparing it with a standard answer database.

[1644] The results of the scoring are stored in a database.

[1645] The server identifies unanswered questions from the student's response data and generates explanations using a generative AI model (such as the T5 Transformers model).

[1646] The explanation data is sent to the student's device, and appropriate explanations are provided based on prompts using an AI model.

[1647] The server analyzes the test result data of all students and uses a statistical analysis module to identify the strengths and weaknesses of each student and optimize the next test or learning program.

[1648] 3. Teacher's terminal:

[1649] This is a device that teachers can use to check students' learning status and provide feedback. Devices include PCs and tablets.

[1650] The teacher's terminal receives optimized learning program data from the server and is equipped with an interface that provides feedback appropriate to each student.

[1651] Example of operation

[1652] 1. Testing and Completion

[1653] On the student's device, the user starts the test and enters the answers. When the user presses the end test button, the answers are encoded as JSON data and sent to the server via an HTTP POST request.

[1654] 2. Automatic scoring and analysis

[1655] The server decodes the received answer data, compares it with a standard answer database, and calculates the score. The calculated score data is saved in the database as the scoring result for each student.

[1656] For example, if a student answers "4" to the question "2+3=", the server compares it with the standard answer and marks it as incorrect, giving it a score of 0.

[1657] 3. Explanation generation for unanswered questions

[1658] The server identifies unanswered questions and generates explanations using a generative AI model.

[1659] As a specific example, if a student finishes a test without answering a question about "adding fractions," the server will identify the question, generate an explanation for "adding fractions" using a generative AI model, and send it to the student's device.

[1660] 4. Optimizing learning programs

[1661] The server collects and analyzes test result data for all students and identifies each student's strengths and weaknesses based on the generated prompts.

[1662] For example, if it turns out that a student has difficulty with "adding fractions," the next test or learning program will be adjusted to include more questions and materials related to "adding fractions."

[1663] 5. Virtual classroom access in virtual space

[1664] Students can log in to a virtual space and participate in classes with other students, allowing them to learn while interacting with other students just as they would in a physical classroom.

[1665] Through these measures, it is possible to provide online programs that are optimally tailored to individual learning needs and to create an environment where students can learn effectively while interacting with other students.

[1666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1667] Step 1: Conducting and Finishing the Test

[1668] The user (student) starts the test using the student terminal and enters the answers. Specifically, the student operates the terminal interface to answer the questions and presses the end button.

[1669] Input: Student answer data

[1670] Output: Test completion notification and answer data encoded in JSON format

[1671] Data processing: Encode answer data into JSON format

[1672] The student terminal sends the encoded answer data to the server via an HTTP POST request along with a test completion notification.

[1673] Step 2: Automated scoring and analysis

[1674] The server decodes the received answer data and checks it against a database of standard answers. Specifically, the server analyzes the answer data and compares each answer with the standard answers.

[1675] Input: Answer data (JSON format)

[1676] Output: Grade results for each student

[1677] Data processing: Matching the decoded answer data with the standard answer data

[1678] The server calculates the scores and stores the results in a database as the grades for each student.

[1679] Step 3: Generate explanations for unanswered questions

[1680] The server identifies unanswered questions from the student's answer data. Specifically, the server checks the answer data and checks for blank spaces.

[1681] Input: Answer data and standard answer data

[1682] Output: List of unanswered questions

[1683] Data processing: Identifying missing responses

[1684] The server uses a generative AI model to generate an explanation for each unanswered question. Specifically, the AI ​​model generates an explanation based on the prompt sentence.

[1685] Input: List of unanswered questions, prompt text

[1686] Output: Commentary data

[1687] Data Computation: Generating Explanations with Generative AI Models

[1688] The server transmits the generated commentary data to the student terminal.

[1689] Step 4: Optimize your learning program

[1690] The server collects and analyzes test result data for all students and uses a statistical analysis module to identify each student's strengths and weaknesses.

[1691] Input: Test result data for all students

[1692] Output: Identification of strengths and weaknesses for each student

[1693] Data Computation: Statistical Analysis

[1694] The server uses this information to optimize the next test or study program, specifically adjusting the layout of questions and study materials to strengthen strengths and compensate for weaknesses.

[1695] Input: Strengths and weaknesses of each student

[1696] Output: Optimized learning program data

[1697] Data Computing: Learning Program Generation and Optimization

[1698] Step 5: Virtual classroom access in a virtual space

[1699] Users (students) log in to the virtual space and participate in classes with other students. Specifically, students wear smart glasses or a head-mounted display and access the virtual classroom.

[1700] Input: User login information

[1701] Output: Virtual classroom access permission

[1702] Data calculation: Login authentication and access right confirmation

[1703] Students can take live lessons with other students in a virtual classroom and interact in real time.

[1704] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1705] The present invention is an educational support system that is configured by combining student terminals, a server, a teacher terminal, and an emotion engine. The specific configuration and operation of this system will be described below.

[1706] System configuration

[1707] 1. Student Device: A device (tablet, PC, smartphone, etc.) used by students to take tests and receive feedback. This device is equipped with an interface for starting and ending tests and inputting and submitting answers. It also has an integrated emotion engine that can analyze students' facial expressions and reactions to generate emotion data.

[1708] 2. Server: This is the central part of the educational support system. This server has the following functions:

[1709] Test response data is received, compared with a standard answer database, and automatically scored.

[1710] Stores the marks in a database and identifies unanswered questions.

[1711] An AI system is used to generate an explanation for each unanswered question, and the explanation data is sent to the student's device.

[1712] Analyze test result data and emotional data for all students to optimize the next test and learning program.

[1713] 3. Teacher terminal: A device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotional data, supporting effective instruction.

[1714] 4. Emotion Engine: A system that analyzes students' facial expressions and reactions to generate emotional data. The emotional data is sent from the student's device to a server and used to optimize the learning program.

[1715] System Operation

[1716] 1. Testing and Completion

[1717] Student device: The user (student) starts the test and enters answers to the questions. When the test is finished, the student device sends a notification of the test completion and the answer data to the server. In addition, the device monitors the student's facial expressions and reactions during the test and generates emotion data in real time.

[1718] Examples:

[1719] While students are taking the Japanese language test, the device's camera monitors their facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the emotional data is sent to the server along with the students' answers.

[1720] 2. Automatic scoring and analysis

[1721] Server: The server decodes the received answer data, compares it with a standard answer database, and automatically scores each question. The scoring results are stored in a database.

[1722] Examples:

[1723] The server receives the students' answers, compares them with standard answers, and calculates a score for each question, including the reading of kanji. The results are recorded in the individual student's database.

[1724] 3. Explanation generation for unanswered questions

[1725] Server: The server identifies unanswered questions from the students' answer data, generates explanations using the AI ​​system, and sends the generated explanation data to the students' devices.

[1726] Examples:

[1727] If a student leaves a kanji writing question unanswered, the server will recognize this and the AI ​​system will generate an explanation on how to write the kanji and send it to the student's device.

[1728] 4. Optimizing learning programs

[1729] Server: The server collects and analyzes test results and emotional data from all students to individually optimize the next test and study program. For example, if a student feels stressed about a particular problem, the server generates a study program that includes additional learning materials or a different approach to that problem.

[1730] Examples:

[1731] If a student feels highly stressed by a "reading comprehension" question and this is reflected in the emotional data, the server will optimize the next learning program to include more practice questions and supplementary materials in that area.

[1732] 5. Display of learning materials and learning feedback

[1733] Teacher's terminal: The teacher's terminal displays the optimized learning program data and student's emotional data received from the server. Based on this, the teacher can provide appropriate feedback and guidance to the student.

[1734] Examples:

[1735] A teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations and practice of the geometry problem during class.

[1736] As described above, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[1737] The processing flow will be explained below.

[1738] Step 1:

[1739] The user (student) starts the test on the student's device. The student's device displays the test questions on the screen and provides an interface for entering answers. Meanwhile, the emotion engine installed on the device monitors the student's facial expressions and reactions in real time and generates emotion data.

[1740] Step 2:

[1741] The user (student) enters the answer to each question and presses the end test button after completing all questions. The student's device encodes the user's answer data and the emotion data collected during the test into JSON format.

[1742] Step 3:

[1743] The student device sends the encoded response data and emotion data to the server using an HTTP POST request. The server receives the request and begins analyzing the data.

[1744] Step 4:

[1745] The server decodes the received JSON data and extracts each question ID and answer data. The server checks the correctness of each question against a standard answer database and calculates the score. The calculated score is saved in a database.

[1746] Step 5:

[1747] The server identifies unanswered questions from the response data, passes the list of identified unanswered questions to the AI ​​system, and generates explanations for each question.

[1748] Step 6:

[1749] The AI ​​system generates appropriate explanations for each unanswered question, which are then encoded into JSON-formatted explanation data by the server.

[1750] Step 7:

[1751] The server sends the generated commentary data to the student's device via an HTTP POST request. The student's device decodes the received commentary data and displays it to the user (student).

[1752] Step 8:

[1753] The server periodically collects and analyzes test result data and emotional data for all students, and performs statistical analysis to identify each student's strengths and weaknesses.

[1754] Step 9:

[1755] The server then uses the analyzed data to individually optimize the next test or study program. For example, if a student feels particularly stressed about a particular problem, it will generate a study program that includes additional material or a different approach to that problem.

[1756] Step 10:

[1757] The server sends the optimized learning program data to the teacher's terminal via an HTTP POST request, which then displays a dashboard to provide optimal feedback to each student.

[1758] Step 11:

[1759] The teacher's terminal checks each student's progress based on the optimized learning program data and student emotion data sent from the server. The teacher uses this data to provide appropriate feedback to each student.

[1760] Step 12:

[1761] The teacher inputs the feedback he or she wants to provide to the student into the teacher's terminal and sends it to the server, which then collects this feedback data and uses it to optimize the learning program.

[1762] Example 2

[1763] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1764] Conventional educational support systems make it difficult to maximize the learning effect of individual students. Furthermore, they do not provide feedback that takes into account students' emotions, which can lead to a decrease in motivation to learn and stress. This increases the burden on teachers and often leads to a lack of individual instruction. Therefore, it is necessary to solve these issues.

[1765] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1766] In this invention, the server includes means for the student terminal to instruct the user to start the test, means for notifying the server of the end of the test and transmitting answer data and emotion data to the server, means for automatically scoring the received answer data and emotion data by comparing it with a standard answer database and saving the scoring results in the database, means for identifying unanswered questions from the student answer data and transmitting generated explanation data to the student terminal, means for analyzing the test result data and emotion data of all students and optimizing the next test or learning program, means for displaying the optimized learning program data and emotion data and providing feedback, and an emotion engine for the student terminal to generate emotion data in real time. This enables optimal feedback that takes into account each student's individual learning situation and emotions, resulting in effective learning support.

[1767] A "student device" is a device (e.g., tablet, PC, smartphone) used by a student to take a test or receive feedback.

[1768] The "server" is the central part of the educational support system, and is a device that receives, stores, analyzes, and optimizes various types of data.

[1769] The "emotion engine" is a system that analyzes students' facial expressions and reactions to generate emotional data, and is a device that collects emotional data from student devices in real time and transmits it to a server.

[1770] A "teacher terminal" is a device that allows a teacher to give feedback to students based on data received from the server.

[1771] "Standard answer database" refers to a database that stores correct answer data and is used by the server to automatically score tests.

[1772] "Scoring results" refers to score information generated after the server automatically scores the answer data it receives by comparing it with a standard answer database.

[1773] An "unanswered question" is a question that a student did not answer during the test.

[1774] "Explanation data" refers to information about explanations and commentaries generated by the server for unanswered questions, and is provided to help students deepen their understanding.

[1775] "Optimizing the next test or learning program" is the process in which the server analyzes the test result data and emotional data of all students and generates individually optimized test and learning program content.

[1776] "Feedback" is information that teachers use to provide guidance and areas for improvement to students' learning.

[1777] An "HTTP POST request" is one of the communication protocols used when a server sends data, and is a method of sending data from a client to a server.

[1778] "Statistical Analysis Module" means a software module that has the functionality to analyze data to identify areas of strength and weakness of a student.

[1779] The present invention is an educational support system that combines student terminals, a server, a teacher terminal, and an emotion engine. This system provides individually optimized education by cooperating with each hardware and software component.

[1780] Student Devices

[1781] The student device is a device (tablet, PC, smartphone, etc.) that students use to take tests and receive feedback. This device has an interface for starting and ending tests, and for entering and submitting answers. Furthermore, it is integrated with an emotion engine, which can analyze students' facial expressions and reactions to generate emotional data.

[1782] For example, while a student is taking a Japanese language test, the device's camera monitors the student's facial expressions and analyzes emotions such as nervousness and impatience in real time. At the end of the test, the student's emotional data is sent to the server along with their answer data.

[1783] server

[1784] The server is the central part of the educational support system. It has the following main functions:

[1785] 1. Automatic scoring: The server decodes the received answer data and automatically scores each question by comparing it with a standard answer database. The scoring results are stored in a database. For example, the server receives the student's answer data, compares questions including "how to read kanji" with the standard answers, and calculates the score for each.

[1786] 2. Generating explanations for unanswered questions: The server identifies unanswered questions from the student's answer data and generates explanations using the AI ​​system. The generated explanation data is sent to the student's device. For example, if a student leaves a "kanji dictation" question unanswered, the server recognizes this and the AI ​​system generates an explanation on "how to write that kanji" and sends it to the student's device.

[1787] 3. Optimizing learning programs: The server collects and analyzes test results and emotional data from all students, and then individually optimizes the next test and learning program. For students who feel particularly stressed by a particular problem, the server provides additional learning materials or different approaches to that problem.

[1788] Teacher's terminal

[1789] The teacher terminal is a device that allows teachers to provide feedback to students based on the data received from the server. The teacher terminal displays optimized learning program data and student emotion data to support effective instruction.

[1790] For example, a teacher can open the dashboard and recognize that a particular student is having difficulty with a "math geometry problem." Based on this information, the teacher can provide additional explanations or practice of the geometry problem during class.

[1791] Emotion Engine

[1792] The emotion engine is a system that analyzes students' facial expressions and reactions to generate emotion data. The emotion data is sent from the student's device to a server and used to optimize the learning program.

[1793] For example, if a student feels anxious or worried during a test, that emotional data is sent to the server in real time and reflected in the next learning program.

[1794] Using generative AI models

[1795] A generative AI model is used to optimize the entire system and generate explanations. Specific examples of prompts include "How to train an AI model to automatically generate explanations for unanswered questions" and "How to optimize learning programs by analyzing student sentiment data."

[1796] In this way, this system is designed to maximize the learning effect of each student while reducing the burden on teachers and staff in the classroom. In addition, by utilizing emotion data, it is possible to provide more appropriate feedback and guidance.

[1797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1798] Step 1:

[1799] Starting the test

[1800] User (Student): When the user presses the "Start Test" button on the student's device, the system displays the test interface and activates the device's camera to record the student's facial expression in real time.

[1801] Input: User clicks the "Start Test" button.

[1802] Output: Display of test interface and start of camera.

[1803] How it works: When a student clicks the "Start Test" button on the tablet, the first question appears on the screen, and the camera begins monitoring the student's facial expressions.

[1804] Step 2:

[1805] Enter your answer

[1806] User (student): The user answers the questions by tapping the correct answer for multiple choice questions and typing the answer on the keyboard for written questions.

[1807] Input: User answer input.

[1808] Output: Temporarily save answer data.

[1809] Specific operation: The student enters the answer to the "Kanji reading" question using the keyboard. If it is a multiple choice question, they tap on the option. Once the answer is entered, the next question will be displayed.

[1810] Step 3:

[1811] End of test and data transmission

[1812] User (student): When the user has answered all questions or the time is up, a notification is displayed that the test is over. When the user presses the end button, the answer data and emotion data are sent to the server.

[1813] Input: Test end operation.

[1814] Output: Sending response data and sentiment data.

[1815] Specific operation: At the end of the test, a message saying "Test completed" is displayed. When the student clicks the "Exit" button, the answer data and real-time collected emotion data are sent to the server.

[1816] Step 4:

[1817] Receiving data

[1818] Server: The server receives the response data and emotion data sent from the device, decodes them, and stores them.

[1819] Input: Receives response data and emotion data.

[1820] Output: Save to database.

[1821] Specific operation: The server captures the data stream, decodes the response data and emotion data, and stores them in a database.

[1822] Step 5:

[1823] Automatic scoring

[1824] Server: The server compares the answer data with a standard answer database and automatically scores the answers. The scores are stored in a database.

[1825] Input: Response data.

[1826] Output: Scoring results.

[1827] Specific operation: The received answer data "Kanji reading" is compared with the standard answer, and if the answer is correct, points are awarded, and if the answer is incorrect, no points are awarded. The results are recorded in the database.

[1828] Step 6:

[1829] Identifying unanswered questions

[1830] Server: The server analyzes the response data to identify unanswered questions and, if any, generates a list of unanswered questions.

[1831] Input: Response data.

[1832] Output: A list of unanswered questions.

[1833] What happens: The server loops through the answer data and identifies any entries that are blank. If the "Kanji dictation" question has not been answered, that information is listed.

[1834] Step 7:

[1835] Generate explanations

[1836] Server: The server uses an AI system to generate explanations for unanswered questions. The generated explanation data is sent to the student's device.

[1837] Input: List of unanswered questions.

[1838] Output: The generated narrative data.

[1839] Specific operation: The AI ​​system generates correct writing methods and example sentences for "kanji dictation" problems. Explanation data is compiled and sent to the student's device.

[1840] Step 8:

[1841] Optimizing your learning program

[1842] Server: The server analyzes test results and emotional data for all students and individually optimizes the next test and learning program, providing additional learning materials and different approaches to high-stress problems.

[1843] Input: Test result data and emotion data of all students.

[1844] Output: An optimized learning program.

[1845] Specific operation: Based on data on students who felt highly stressed by the "reading comprehension" questions, the server configures the next learning program to include additional practice questions and supplementary materials.

[1846] Step 9:

[1847] Data Display and Feedback

[1848] Teacher terminal: The teacher terminal displays the optimized learning program data and emotion data received from the server. The teacher provides feedback based on the displayed data.

[1849] Input: Optimized learning program data and emotion data.

[1850] Output: Feedback.

[1851] Specific behavior: The test results and emotional data of specific students are displayed on the dashboard of the teacher's device, and the teacher can provide feedback to the students, such as "Add more focus on specific questions in the next learning program."

[1852] (Application example 2)

[1853] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1854] Conventional educational support systems have limited data collection and analysis to maximize students' learning outcomes, and are unable to provide optimal feedback or guidance that takes into account students' emotional data. Furthermore, in the maintenance of factory robots, appropriate maintenance suggestions that take into account the emotional state of the technicians were not provided, which can increase technician stress and reduce efficiency. It is necessary to provide a sustainable system that solves these issues.

[1855] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1856] In this invention, the server includes means for receiving students' answer data, comparing it with a standard answer database to automatically score the answers, and storing the scoring results in a database; means for identifying unanswered questions from the students' answer data, generating explanations for each unanswered question using an AI system, and transmitting the explanation data to the student terminals; means for analyzing the test result data and emotion data of all students and optimizing the next test or study program; means for receiving and analyzing the robot's sensor data to generate robot maintenance suggestions and transmit the necessary actions to the engineer terminal; and means for the engineer terminal to generate emotion data using camera footage and transmit it to the server. This enables effective feedback, guidance, and maintenance suggestions that take emotion data into account in both educational settings and factories.

[1857] A "student device" is a device used by students to take tests and receive feedback.

[1858] The "server" is a central processing unit that receives students' answer data, compares it with a standard answer database, automatically scores it, and analyzes the test result data and emotional data of all students.

[1859] A "standard answer database" is a database that stores standard answers for tests.

[1860] "Automatic scoring" is the process by which the server compares student response data with a database of standard answers and calculates scores without human intervention.

[1861] An "AI system" is a system that uses artificial intelligence and has the ability to automatically generate explanations for students' unanswered questions.

[1862] "Explanation data" refers to the explanations generated by the AI ​​system for unanswered questions.

[1863] "Emotional data" refers to data on the emotional state of students and engineers obtained by analyzing their facial expressions and reactions.

[1864] "Robot sensor data" is data that includes status information such as temperature and vibration collected from robots operating in factories.

[1865] A "maintenance proposal" is a maintenance method proposal generated by the server based on the robot's sensor data and the technician's emotional data.

[1866] An "engineer terminal" is a device used by engineers to perform maintenance and operation of the robot.

[1867] "Camera video" refers to video data acquired by a camera mounted on the engineer's terminal.

[1868] This invention is a system that is configured by combining student terminals, a server, a teacher terminal, an engineer terminal, and an emotion engine. The detailed configuration and operation of this system will be explained below.

[1869] System configuration

[1870] 1. Student devices

[1871] The student terminal is a device used by students taking courses, and is equipped with an interface for students to take tests and receive feedback. The student terminal is equipped with a camera to monitor the students' facial expressions and reactions during tests, and the emotion engine analyzes this to generate emotion data.

[1872] 2. Server

[1873] The server is the central part of the system and has the following functions:

[1874] The system receives answer data sent from student devices and automatically scores them by comparing them with a standard answer database.

[1875] The scoring results and emotion data are stored in a database and analyzed together with the test result data of all students.

[1876] Unanswered questions are identified and explanations are generated using an AI system and sent to student devices.

[1877] Analyze student response data and sentiment data to optimize the next test or learning program.

[1878] It receives and analyzes the robot's sensor data to generate maintenance suggestions and send them to the technician's terminal.

[1879] 3. Teacher's terminal

[1880] The teacher terminal is a device that allows teachers to monitor students' learning progress and provide feedback. It displays optimized learning program data and student emotional data, supporting effective instruction.

[1881] 4. Technician terminal

[1882] The engineer terminal is a device used to perform maintenance and operation of factory robots. The engineer terminal is equipped with a camera that monitors the face of the engineer and generates emotional data. The generated emotional data is sent to the server and used to generate maintenance suggestions.

[1883] 5. Emotion Engine

[1884] The emotion engine is a system that analyzes camera footage and generates emotion data from the facial expressions and reactions of students and engineers. The emotion data is sent from the student and engineer devices to a server and is used to optimize learning programs and generate maintenance suggestions.

[1885] System Operation

[1886] Operation as an educational support system

[1887] 1. Testing and Completion

[1888] The start and end of the test are notified from the student's device, and the answer data is sent to the server. At the same time, the camera on the student's device monitors the student's facial expressions and generates emotional data in real time.

[1889] 2. Automatic scoring and analysis

[1890] The server automatically scores the received answer data by comparing it with a standard answer database, and the results are stored in the database.

[1891] 3. Explanation generation for unanswered questions

[1892] The server identifies unanswered questions and generates explanations using an AI system, which are then sent to the student's device.

[1893] 4. Optimizing learning programs

[1894] The server analyzes the test results and emotional data of all students and individually optimizes their next test and learning program.

[1895] Operation as a maintenance system for factory robots

[1896] 1. Robot status monitoring

[1897] The server receives sensor data from the factory robots and monitors their status in real time.

[1898] 2. Collecting engineer emotion data

[1899] The engineer's terminal monitors the engineer's facial expression using camera images, and an emotion engine generates emotion data.

[1900] 3. Generate maintenance proposals

[1901] The server analyzes the received sensor data and emotion data and sends appropriate maintenance suggestions to the technician's terminal.

[1902] Specific examples

[1903] If a robot running in a factory is experiencing high temperatures and an engineer is feeling stressed about the situation, the system will:

[1904] The server recognizes from the robot's sensor data that Robot A's temperature has reached 90°C and generates a cooling suggestion.

[1905] At the same time, the technician terminal detects from the camera footage that technician B's stress level is high and generates a break suggestion.

[1906] The server sends these suggestions to the technician's terminal, and the technician takes appropriate action accordingly.

[1907] Example prompts to input to the generative AI model

[1908] "Robot A's temperature is over 90°C. Also, Technician B's stress level is detected to be high. Please make appropriate maintenance suggestions."

[1909] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1910] Step 1:

[1911] Student device starts testing

[1912] The student device is operated by the user (student) and the test begins. The student device collects camera footage in real time, analyzes facial expressions, and generates emotion data.

[1913] Input: Start test by student operation, camera image

[1914] Output: Test start notification, real-time emotion data

[1915] Specific operation: The camera on the student's device captures the student's facial expression, which is then analyzed by the emotion engine to generate emotion data.

[1916] Step 2:

[1917] Student devices will receive a notification of test completion and send answer data.

[1918] The student's device notifies the server that the test has ended and sends the answer data. The emotion data collected during the test is also sent to the server.

[1919] Input: Test completion notification, answer data, emotion data

[1920] Output: Sending answer data and emotion data

[1921] Specific operation: After the student device finishes the test, it sends an HTTP request to the server and transmits the answer data and emotion data.

[1922] Step 3:

[1923] The server receives the answer data and scores it.

[1924] The server receives the answer data sent from the student's device, compares it with a standard answer database, and automatically scores it. The results are saved in the database.

[1925] Input: Answer data

[1926] Output: Scoring results, updated database

[1927] Specific operation: The server compares the answer data with the standard answer database, calculates the score, and stores it in the database.

[1928] Step 4:

[1929] The server identifies unanswered questions and generates explanations

[1930] The server analyzes the response data, identifies unanswered questions, uses an AI system to generate explanations for these questions, and sends the explanation data to the student's device.

[1931] Input: Answer data, standard answer database

[1932] Output: List of unanswered questions, explanation data

[1933] Specific operation: The server extracts unanswered questions from the response data, generates explanatory text using a generative AI model, and sends it to the student's device.

[1934] Step 5:

[1935] The server analyzes test results and emotional data to optimize the learning program.

[1936] The server analyzes the test result data and emotional data of all students and individually optimizes the next test and learning program.

[1937] Input: Test result data, emotion data

[1938] Output: Optimized learning program

[1939] How it works: The server analyzes the data using statistical analysis and machine learning models to generate an optimized learning program for each student.

[1940] Step 6:

[1941] The server receives and analyzes the robot's sensor data.

[1942] The server receives sensor data from the factory robots and analyzes the data in real time.

[1943] Input: Robot sensor data (temperature, vibration, etc.)

[1944] Output: Analysis results

[1945] Specific operation: The server analyzes temperature and vibration data and performs threshold judgments to detect abnormal conditions.

[1946] Step 7:

[1947] The engineer's terminal generates emotion data using camera footage.

[1948] The engineer's terminal monitors the engineer's facial expressions in real time, and the emotion engine generates emotion data and sends it to the server.

[1949] Input: Technician's camera feed

[1950] Output: Generated emotion data

[1951] Specific operation: The camera on the technician's terminal captures the technician's face, and the emotion engine analyzes the facial expressions to generate emotion data, which is then sent to the server.

[1952] Step 8:

[1953] Server generates and sends maintenance proposals

[1954] The server analyzes the received sensor data and emotion data, generates maintenance suggestions for the robot, and sends the suggestions to the technician's terminal.

[1955] Input: Sensor data, emotion data

[1956] Output: Maintenance suggestions

[1957] Specific operation: The server analyzes sensor data and emotion data using the generated AI model and recommends appropriate maintenance actions to the technician's terminal.

[1958] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1959] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1960] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1961] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1962] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1963] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1964] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1965] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1966] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1967] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1968] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1969] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1970] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1971] Alternatively, the spec...

Claims

1. means for the student terminal to notify the server of the end of the test and transmit answer data to the server; A server receives the answer data, compares it with a standard answer database, automatically scores it, and stores the score results in a database; A means for the server to identify unanswered questions from the students' answer data, generate explanations for each unanswered question using an AI system, and transmit the explanation data to the student's terminal; The server analyzes the test result data of all students and optimizes the next test and learning program. a means for displaying the optimized learning program data received by the teacher terminal from the server and providing feedback to the students; A system including:

2. 10. The system of claim 1, wherein the server identifies areas of strength and weakness for each student through a statistical analysis module and generates an optimized learning program.

3. 2. The system of claim 1, wherein the server transmits the instruction data and the optimized learning program data using an HTTP POST request.

Images