System

Abstract

A system is provided.SOLUTION: The system includes a means for analyzing uploaded educational data and automatically generating test questions using generative artificial intelligence, a means for a user to review and edit the generated test questions through a terminal, and a means for inputting and uploading student performance data.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] The purpose of this invention is to reduce the burden on teachers and improve the quality of education in the field of education. Specifically, the purpose is to provide an effective solution to problems such as long working hours, excessive administrative work, a decline in teaching ability due to a decrease in the number of teachers, and the difficulty of providing detailed support for the academic ability of each student. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing the following means. The system includes means for automatically generating test questions by analyzing uploaded educational data using generative artificial intelligence, means for users to review and edit the generated test questions via a terminal, and means for inputting and uploading student performance data. The system also includes means for analyzing the performance data, grasping the academic ability trends of each student, and automatically generating educational countermeasures. It also provides means for transmitting the generated educational countermeasures to a terminal, allowing users to view and share them. These measures significantly improve the efficiency of teachers' work and the quality of education.

[0006] "Generative AI" refers to an AI technology that analyzes patterns based on large amounts of data and generates new information and content to solve specific problems.

[0007] "Educational data" refers to a collection of information related to education, such as text, images, audio, and video, including textbooks, supplementary materials, and lesson materials.

[0008] "Test items" refers to a set of questions or problems used to assess a student's level of understanding or knowledge.

[0009] A "terminal" is an electronic device that a user operates, such as a PC, tablet, or smartphone.

[0010] "User" refers to teachers and other educational personnel who use this system.

[0011] "Academic performance data" refers to a collection of numerical values ​​and records related to student test results and assessments.

[0012] "Academic ability trends" refer to characteristics and patterns related to a student's learning performance, such as their strengths and weaknesses in subjects and their level of knowledge acquisition.

[0013] "Educational measures" refer to specific teaching methods, teaching materials, learning programs, etc. proposed with the aim of improving the academic ability of each student.

[0014] The term "system" refers to a collection of hardware and software for implementing the entire process of the present invention. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education.

[0037] System configuration and functions

[0038] 1. Uploading teaching material data

[0039] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[0040] Users select teaching material data, such as digital textbooks and slides they have created, using a computer or tablet and upload it to the system. This uploaded data is stored on the server and used for subsequent processing.

[0041] 2. Automatic generation of test creation

[0042] The server analyzes the educational data and automatically generates test questions using generative AI.

[0043] The server analyzes the uploaded educational data. Text mining technology is used for the analysis to extract important keywords and concepts. Based on these extraction results, the generative AI automatically generates appropriate test questions. The generated test questions come in multiple question formats (multiple choice, fill-in-the-blank, written, etc.).

[0044] 3. Check and edit the test content

[0045] User-generated test questions can be viewed and edited on the device

[0046] The user checks the automatically generated test questions on their device, checks the appropriateness of the questions, and makes any necessary modifications, such as adding or deleting questions or adjusting the difficulty level. After editing, the test questions are uploaded back to the server and saved in the system.

[0047] 4. Enter and upload grade data

[0048] The user enters the student's test results into the terminal and uploads them to the server.

[0049] After the test, the user enters the student's answers into the device and uploads the results data to the system. The results data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions. This data is also stored on the server.

[0050] 5. Analysis of academic performance data and academic ability analysis

[0051] The server analyzes the grade data and identifies the student's academic ability trends.

[0052] The server analyzes the uploaded grade data, using statistical analysis to identify each student's strengths and weaknesses and overall academic trends. If necessary, the same analysis can be performed for specific classes or groups selected by the teacher.

[0053] 6. Generating measures to improve academic ability

[0054] The server automatically generates educational strategies based on the results of the academic ability analysis.

[0055] Based on the analysis results, the server generates optimal educational strategies for each student, including remedial programs, additional learning materials, and self-study resources. For example, a student who struggles with fraction calculations in math might be provided with practice problems specific to that area.

[0056] 7. Providing and sharing countermeasures

[0057] The server sends the generated educational plan to the device, where the user can view and share it.

[0058] The server sends the generated educational strategies to the user's device. The user can review the strategies on their device and share them with students and parents as needed. This is expected to improve the accuracy of individualized instruction and lead to improved academic performance for students.

[0059] Specific examples

[0060] Below are some specific examples of how this system can be used.

[0061] Uploading teaching material data

[0062] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[0063] Auto-generated test creation

[0064] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[0065] Check and edit test content

[0066] The teacher checks the generated test questions, adjusts the difficulty of some questions, and saves them again on the server.

[0067] Entering and uploading grade data

[0068] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[0069] Analysis of academic performance data and academic ability analysis

[0070] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[0071] Generate measures to improve academic performance

[0072] The server generates a set of fraction calculation practice problems and a home study program for Mr. A.

[0073] Providing and sharing countermeasures

[0074] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[0075] The introduction of this system will significantly reduce the burden on teachers and improve the quality of education.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The user selects the teaching material data

[0079] The user (teacher) uses a computer or tablet to select the target digital teaching material data (e.g., textbooks, slides, supplementary materials, etc.) in a file browser.

[0080] Step 2:

[0081] Upload the teaching material data selected by the user from the device to the server.

[0082] The user clicks a dedicated upload button to upload the selected teaching material data to the system. The teaching material data is transferred to the server via the Internet and stored on the server.

[0083] Step 3:

[0084] The server analyzes the uploaded educational data

[0085] The server analyzes the stored learning material data and uses text mining technology to extract important keywords and concepts from the text content of the learning material. Natural language processing technology is also utilized in this process.

[0086] Step 4:

[0087] The server automatically generates test questions using AI

[0088] The server uses generative AI to create test questions based on the extracted keywords and concepts. The generated test questions come in multiple formats, including multiple choice, fill-in-the-blank, and free-form questions.

[0089] Step 5:

[0090] User can view generated tests on device

[0091] The user checks the list of test questions automatically generated by the server on their device, checking the content, format, and difficulty of each question one by one.

[0092] Step 6:

[0093] User-generated test editing

[0094] Users can review the test questions and make corrections, additions, or deletions as needed. For example, they can change the question format or adjust the difficulty level. Once edited, the test is uploaded back to the server and saved.

[0095] Step 7:

[0096] The user enters the student's test results into the terminal.

[0097] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[0098] Step 8:

[0099] Upload the grade data entered by the user to the server

[0100] Once the data has been entered, the user uploads it to the system, where it is stored on the server and used for subsequent analysis.

[0101] Step 9:

[0102] The server analyzes the performance data

[0103] The server analyzes the stored grade data and uses statistical analysis tools to identify students' strengths and weaknesses, as well as academic trends.

[0104] Step 10:

[0105] The server generates the academic performance report.

[0106] The server then generates an academic performance report for each student based on the analysis results, including graphs, charts, and commentary based on the analysis results.

[0107] Step 11:

[0108] The server generates educational strategies.

[0109] Based on the generated academic achievement report, the server automatically generates educational strategies tailored to each student, including areas to strengthen in class and materials for home study.

[0110] Step 12:

[0111] The server generates an academic performance report and sends it to the device.

[0112] The server sends the generated report and countermeasures to the user's device, where the user can review it and share it with students and parents as needed.

[0113] Through these steps, the system can significantly improve the efficiency of teachers' work and improve the quality of education.

[0114] Example 1

[0115] 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."

[0116] In the field of education, teachers have a wide range of tasks, which creates a heavy workload. Furthermore, because they are required to deliver education efficiently while maintaining a certain level of quality, systems are needed that reduce the burden on teachers while improving the quality of education. In particular, tasks such as creating teaching materials, creating tests, and managing student grades are labor-intensive, and technology is needed to perform these tasks efficiently.

[0117] 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.

[0118] In this invention, the server includes means for analyzing uploaded educational data using a generation AI and automatically generating test questions, means for users to review and edit the generated test questions via a terminal, means for inputting and uploading student achievement data, means for analyzing the achievement data and identifying students' academic ability trends, means for automatically generating educational strategies based on the results of the academic ability analysis, and means for sending the generated educational strategies to the terminal so that users can view and share them. This enables efficient management and analysis of educational data, significantly reducing the workload of teachers and improving the quality of education.

[0119] "Generative AI" is an artificial intelligence technology that automatically generates new information and solutions based on uploaded data.

[0120] "Educational data" refers to information and materials related to education, such as digital textbooks and created slides.

[0121] "Test questions" are questions that are asked to assess a student's understanding and knowledge.

[0122] "Academic performance data" refers to data such as test scores and evaluation results obtained by students.

[0123] "Academic ability trends" refers to trends that indicate a student's strengths and weaknesses in subjects and their learning progress.

[0124] "Educational measures" are proposals for specific teaching methods and teaching materials to improve students' academic abilities.

[0125] A "terminal" is a device such as a computer or tablet that is directly operated by a user.

[0126] "Users" refer to teachers and other educational personnel who use this system.

[0127] A "server" is a computer system that provides services and resources on a computer network.

[0128] "Text mining" is an analytical technique for extracting useful information from natural language data.

[0129] "Statistical analysis" is an analytical method that aims to obtain information by analyzing data using statistical techniques.

[0130] "Visualization tools" are software and techniques for visually displaying data.

[0131] MODE FOR CARRYING OUT THE INVENTION

[0132] This invention is a system aimed at improving the work efficiency of teachers and the quality of education in the field of education. This system has the functions of analyzing uploaded educational data using generative AI and automatically generating test questions, allowing teachers to review and edit the generated test questions, inputting and uploading grade data, and automatically generating educational countermeasures based on student grade data to grasp academic ability trends.

[0133] Hardware and software used

[0134] Hardware

[0135] Server: Stores and analyzes educational data, and generates test questions and educational strategies.

[0136] Terminal: A device (e.g., PC, tablet) that teachers use to upload teaching material data, check and edit test questions, and enter and upload grade data.

[0137] software

[0138] Generative AI: Artificial intelligence that analyzes teaching material data and generates test questions and educational strategies (e.g., GPT-3 (registered trademark), BERT).

[0139] Text mining technology: Natural language processing engines (e.g., SpaCy, NLTK) for extracting important keywords and concepts from teaching material data.

[0140] Data analysis tools: Software for statistical analysis of performance data and identifying trends in student achievement (e.g., Pandas, NumPy).

[0141] Visualization tools: Tools for visually displaying the results of performance data analysis (e.g., Matplotlib, Seaborn).

[0142] Explanation of program processing

[0143] Uploading teaching material data

[0144] A user (teacher) uses a PC or tablet to select educational data (digital textbooks, created slides, etc.) and uploads them to the server from the device. The server saves the received data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[0145] Auto-generated test creation

[0146] The server analyzes the uploaded educational data using text mining technology to extract important keywords and concepts. Based on the extracted keywords and concepts, the generation AI generates appropriate test questions (multiple choice, fill-in-the-blank, essay, etc.). Examples of generated prompts include:

[0147] "Read the following text and select the appropriate option. Text: 『○○』"

[0148] Check and edit test content

[0149] The user checks the test questions generated on the device and makes corrections as necessary. The corrected test questions are then uploaded back to the server and saved.

[0150] Entering and uploading grade data

[0151] After the test, the user enters the student's answers into the device and uploads the results to the server, which then stores the received data in a database.

[0152] Analysis of academic performance data and academic ability analysis

[0153] The server analyzes the uploaded grade data using statistical analysis tools to identify each student's academic performance trends, and the analysis results are displayed visually using visualization tools.

[0154] Generate measures to improve academic performance

[0155] The server generates individualized educational strategies based on the results of the academic ability analysis. These strategies include remedial programs, additional learning materials, and self-study resources. Examples of generated prompts include:

[0156] "For the next student, please suggest the following strategies for those struggling with fractions in math:"

[0157] Providing and sharing countermeasures

[0158] The server sends the generated educational countermeasures plan to the user's device, where the user confirms it and then shares it with students and parents.The countermeasures plan is distributed via an educational portal site or email system, allowing students and parents to access it.

[0159] This will enable the efficient management and analysis of educational data, which is expected to significantly reduce the workload of teachers while improving the quality of education.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] System program processing flow

[0162] Step 1: Upload the teaching material data

[0163] Input: User-selected teaching material data (file format: PDF, PPT, etc.)

[0164] Output: Learning material data and file metadata stored on the server

[0165] Specific behavior:

[0166] Users select the teaching material data on their computers or tablets.

[0167] The terminal gets the file path through a file selection dialog.

[0168] The terminal sends the selected teaching material data to the server using an HTTP request.

[0169] The server stores the received teaching material data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[0170] Step 2: Analyzing Educational Data

[0171] Input: Teaching material data stored on the server

[0172] Output: Extracted terms and concepts

[0173] Specific behavior:

[0174] The server reads the teaching material data and analyzes it using text mining technology.

[0175] The server uses a natural language processing engine (e.g. SpaCy, NLTK) to extract important keywords and concepts.

[0176] The server temporarily stores the extracted keywords and concepts.

[0177] Step 3: Generate test questions

[0178] Input: Extracted keywords and concepts

[0179] Output: Auto-generated test questions

[0180] Specific behavior:

[0181] The server uses generative AI (e.g., GPT-3, BERT) to generate test questions based on the extracted keywords and concepts.

[0182] The server sets up a generation prompt and sends a request to the generative AI model.

[0183] Example prompt: "Generate three multiple choice questions using the following keywords: fractions, math, 5th grade"

[0184] The server formats and saves the test questions received from the generation AI.

[0185] Step 4: Review and edit the test content

[0186] Input: Auto-generated test questions

[0187] Output: Test questions corrected by the user

[0188] Specific behavior:

[0189] The server sends the generated test questions to the device.

[0190] The user checks the test questions generated on the terminal.

[0191] The user uses the editing screen of the web application to modify the test questions (add, delete, adjust the difficulty level, etc.).

[0192] The device uploads the modified test questions to the server.

[0193] Step 5: Enter and upload grade data

[0194] Input: Student answer results entered by the user

[0195] Output: Achievement data stored on the server

[0196] Specific behavior:

[0197] After the user takes the test, the student's answers are entered into the terminal.

[0198] The terminal uses a web application form to input each student's grade data.

[0199] The terminal sends the entered score data to the server using an HTTP request.

[0200] The server stores the received results data in a database.

[0201] Step 6: Analysis of academic performance data and academic achievement analysis

[0202] Input: Achievement data stored on the server

[0203] Output: Academic performance trend report for each student

[0204] Specific behavior:

[0205] The server reads the performance data and analyzes it using statistical analysis tools (e.g., Pandas, NumPy).

[0206] The server calculates each student's correct answer rate, average score, distribution, etc.

[0207] The server uses visualization tools (e.g., Matplotlib, Seaborn) to graph the results and generate academic performance trend reports.

[0208] Step 7: Generate strategies to improve academic performance

[0209] Input: Academic ability analysis results

[0210] Output: Automatically generated educational strategies

[0211] Specific behavior:

[0212] The server uses generative AI to generate educational strategy proposals based on the results of the academic ability analysis.

[0213] The server sets up a generation prompt and sends a request to the generative AI model.

[0214] Example prompt: "For the following student, please suggest the following strategies for solving problems with fractions in math:"

[0215] The server formats and saves the generated educational strategies.

[0216] Step 8: Provide and share countermeasures

[0217] Input: Automatically generated educational plan

[0218] Output: Solutions provided to users, students, and parents

[0219] Specific behavior:

[0220] The server sends the generated educational strategy plan to the user's terminal.

[0221] The user checks the educational measures on the device.

[0222] Users share the countermeasures with students and parents by distributing them via educational portal sites and email systems, making them viewable and downloadable.

[0223] (Application example 1)

[0224] 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."

[0225] In the field of education, teachers must take measures to improve the academic ability of each student while juggling a wide range of tasks. However, the series of tasks, such as preparing teaching materials, creating tests, managing grades, and creating countermeasures based on the results, are enormous and require time and effort. For this reason, a system is needed to carry out these tasks efficiently and effectively. In addition, to take effective educational measures, teachers need the ability to check and customize educational content in real time.

[0226] 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.

[0227] In this invention, the server includes means for analyzing uploaded educational data using a generation artificial intelligence and automatically generating test questions, means for searching and selecting teaching materials in a virtual space, means for a user to check and edit the generated test questions, means for previewing and editing educational strategies in real time through a terminal, means for inputting and uploading student achievement data, and means for previewing and editing educational strategies in the virtual space. This allows teachers to efficiently obtain the necessary teaching materials and strategies and customize educational content in real time.

[0228] "Generative AI" is an AI technology that has the ability to analyze uploaded educational data and automatically generate test questions and educational strategies.

[0229] "Educational data" is a general term for digital data related to education, such as textbooks, slides, and teaching materials.

[0230] A "virtual space" is a virtual environment constructed using virtual reality technology that allows users to visually and experientially explore and select educational materials.

[0231] "Device" is a general term for electronic devices such as computers, smartphones, and tablets that users use to check, edit, and upload educational data.

[0232] "Test questions" are questions to evaluate learning content that are automatically generated by generative artificial intelligence based on educational data.

[0233] "Academic performance data" refers to data that evaluates a student's learning outcomes and includes grade information based on the results.

[0234] "Educational strategy" is a general term for specific educational plans and supplementary materials that are generated by analyzing academic performance data in order to improve each student's academic ability.

[0235] "Real-time preview" is a function that allows users to instantly check educational data and countermeasures on their devices or in a virtual space.

[0236] "Editing" refers to the act of the user changing or modifying the content of the generated test questions or educational strategies.

[0237] This invention is a system aimed at improving work efficiency and the quality of education in the field of education. This system has the functions of allowing teachers to upload educational data, automatically generating test questions using generative artificial intelligence, and exploring teaching materials in a virtual space, previewing and editing them in real time. The specific configuration and processing required to realize this system are described below.

[0238] 1. Uploading teaching material data

[0239] Users upload educational material data, such as digital textbooks and slides they have created, from their devices (PCs or tablets) to the server. The uploaded data is stored on the server and used for subsequent processing.

[0240] 2. Automatic generation of test creation

[0241] The server analyzes the uploaded educational data. This analysis uses text mining technology implemented in Python to extract important keywords and concepts. Based on the extracted results, a generative artificial intelligence model using TENSORFLOW (registered trademark) and PyTorch automatically generates appropriate test questions. The generated test questions include multiple choice, fill-in-the-blank, and essay-style questions.

[0242] 3. Explore and preview learning materials in a virtual space

[0243] Users put on a VR headset (such as Oculus Quest 2) and enter a virtual space built with Unity or Unreal Engine. In the virtual space, users can explore and select learning materials and preview them in real time. The selected learning materials include test questions and supplementary materials automatically generated by the system.

[0244] 4. Check and edit the test content

[0245] Users can check the generated test questions on their device and edit them as needed. They can check the appropriateness of the questions with a real-time preview and add, delete, or adjust the difficulty level. After editing, the test questions are saved back to the server.

[0246] 5. Enter and upload grade data

[0247] After taking the test, the user enters the student's performance data into the device and uploads it to the server. The performance data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions, and is saved on the server.

[0248] 6. Analysis of academic performance data and academic ability analysis

[0249] The server analyzes the uploaded grade data, using Python-based statistical analysis algorithms to identify each student's strengths and weaknesses, as well as overall academic performance trends.

[0250] 7. Generating measures to improve academic ability

[0251] Based on the analysis of the grade data, the server generates optimal educational strategies, including supplementary learning programs, additional teaching materials, and self-study resources.

[0252] 8. Providing and sharing countermeasures

[0253] The generated educational strategies are sent from the server to the user's device, where the user can view and share them, improving the accuracy of individualized instruction.

[0254] Examples of specific examples and prompts

[0255] Below are some specific examples of prompt sentences to input into the generative AI model.

[0256] "Generate multiple-choice quiz questions based on 5th grade math materials."

[0257] "Based on the above teaching materials, please generate a supplementary workbook that specializes in fraction calculations."

[0258] This allows teachers to carry out educational activities effectively and efficiently.

[0259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0260] Step 1:

[0261] Users use their devices to upload educational material data (digital textbooks, created slides, etc.) to the server.

[0262] Input: Teaching material data

[0263] Output: Teaching material data saved on the server

[0264] Specific operation: The user uses a PC or tablet to select teaching material data from the system interface and clicks the "Upload" button.

[0265] Step 2:

[0266] The server analyzes the uploaded educational data and extracts important keywords and concepts.

[0267] Input: Teaching material data stored on the server

[0268] Output: Extracted keywords and concepts

[0269] Specific operation: The server runs a text mining algorithm implemented in Python to analyze the teaching material data, extracting keywords and concepts and storing them in a database.

[0270] Step 3:

[0271] The server automatically generates test questions using a generative AI model based on the extracted keywords and concepts.

[0272] Input: Extracted keywords and concepts

[0273] Output: Auto-generated test questions

[0274] Specific operation: The server feeds input data (extracted keywords and concepts) into a generative AI model built with TensorFlow or PyTorch, and generates test questions.

[0275] Step 4:

[0276] The user uses a VR headset to enter a teaching material shop in a virtual space and search for and select teaching material data.

[0277] Input: Teaching materials in virtual space

[0278] Output: Selected teaching material data

[0279] Specific operations: The user puts on a VR headset such as Oculus Quest 2 and moves around a virtual space built with Unity or Unreal Engine to find, pick up and select educational materials.

[0280] Step 5:

[0281] The user reviews and edits the automatically generated test questions on the device.

[0282] Input: Auto-generated test questions

[0283] Output: Test questions edited by the user

[0284] Specific operation: The user views the test questions through the device, and adds, deletes, and adjusts the difficulty of questions as needed. The edited content is saved back to the server.

[0285] Step 6:

[0286] After the user takes the test, the student's performance data is entered into the terminal and uploaded to the server.

[0287] Input: Student answer results

[0288] Output: Grade data saved on the server

[0289] Specific operation: The user enters the student's answer results into the grade management system and clicks the "Upload" button.

[0290] Step 7:

[0291] The server analyzes the grade data and identifies each student's academic ability trends.

[0292] Input: Student performance data

[0293] Output: Academic trend report

[0294] Specific operation: The server uses Python statistical analysis algorithms to analyze the grade data, identify strong and weak subjects, and compile trends into a report.

[0295] Step 8:

[0296] The server generates educational strategies for each student based on their academic ability trends.

[0297] Input: Academic Trend Report

[0298] Output: Educational measures

[0299] Specific operation: The server uses the generated AI model to generate supplementary learning programs and additional teaching materials tailored to specific academic trends.

[0300] Step 9:

[0301] The server sends the generated educational strategy plan to the user's device, where the user can review and share it.

[0302] Input: Educational measures proposal

[0303] Output: Educational measures displayed on the user's device

[0304] Specific operation: The server sends the proposed countermeasures to the user's device, and the user reviews the contents and shares them with students and parents as necessary.

[0305] 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.

[0306] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education, and by combining it with an emotion engine, realizes educational support that takes into account the emotions of students and teachers.

[0307] System configuration and functions

[0308] 1. Uploading teaching material data

[0309] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[0310] Users select and upload teaching material data using a computer or tablet, and this data is stored on a server for later analysis and test creation.

[0311] 2. Automatic generation of test creation

[0312] The server analyzes the educational data and automatically generates test questions using generative AI.

[0313] The server analyzes the uploaded educational data using text mining technology, and the AI ​​automatically generates appropriate test questions, ranging from multiple choice questions to free-form questions.

[0314] 3. Check and edit the test content

[0315] User-generated tests can be viewed and edited on the device

[0316] Users can view the test questions generated on their devices, add, delete, or modify questions, and the edited test is saved back to the server.

[0317] 4. Use of Emotion Engine

[0318] The server uses an emotion engine to recognize the user's emotions and adjust the difficulty and content of the test questions.

[0319] When a teacher is reviewing and editing test questions, the emotion engine analyzes the teacher's emotions from their facial expressions and tone of voice, optimizing the difficulty level and question format of the proposed content.

[0320] 5. Enter and upload grade data

[0321] The user enters the student's test results into the terminal and uploads them to the server.

[0322] After the test, the user enters the results data for each student into the terminal and uploads it. This data is also saved on the server.

[0323] 6. Analysis of academic performance data and academic ability analysis

[0324] The server analyzes the grade data and identifies the student's academic ability trends.

[0325] Based on the uploaded grade data, the server performs statistical analysis of students' strong and weak subjects and academic trends.

[0326] 7. Generating measures to improve academic ability

[0327] The server automatically generates educational strategies based on the results of the academic ability analysis.

[0328] Based on the analysis results, the server generates optimal educational strategies for each student, including supplementary learning programs and home study materials.

[0329] 8. Adjusting academic achievement strategies using an emotion engine

[0330] The server uses an emotion engine to recognize students' emotions and generate strategies to improve motivation for individual instruction.

[0331] The server recognizes students' emotions in real time and generates teaching guidelines and countermeasures that take their motivation into account.

[0332] 9. Providing and sharing countermeasures

[0333] The server sends the generated educational plan to the device, where the user can view and share it.

[0334] The server sends the generated countermeasures to the teacher's device, where the user can check the countermeasures and share them with students and parents to improve the quality of individual instruction.

[0335] Specific examples

[0336] Below are some specific examples of how this system can be used.

[0337] Uploading teaching material data

[0338] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[0339] Auto-generated test creation

[0340] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[0341] Check and edit test content

[0342] The teacher reviews the generated test questions, adjusts the difficulty of some questions, and saves them back on the server. At this time, the emotion engine analyzes the teacher's emotions and automatically suggests the difficulty level of the test questions.

[0343] Entering and uploading grade data

[0344] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[0345] Analysis of academic performance data and academic ability analysis

[0346] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[0347] Generation of measures to improve academic performance and adjustment using an emotion engine

[0348] The server generates a set of fraction calculation practice problems and a home study program for Mr. A. Furthermore, the emotion engine recognizes Mr. A's emotions and suggests teaching methods to improve his motivation.

[0349] Providing and sharing countermeasures

[0350] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[0351] The introduction of this system will significantly reduce the burden on teachers and further improve the quality of education by taking emotional factors into consideration.

[0352] The processing flow will be explained below.

[0353] Step 1:

[0354] The user selects the teaching material data

[0355] The user (teacher) uses a computer or tablet to select the target teaching material data (e.g., digital textbook, slides, supplementary materials) in a file browser.

[0356] Step 2:

[0357] Upload the teaching material data selected by the user from the device to the server.

[0358] The user clicks a button to upload the selected teaching material data to the system, which is then transferred to the server via the Internet and stored on the server.

[0359] Step 3:

[0360] The server analyzes the uploaded educational data

[0361] The server analyzes the stored teaching material data and uses text mining and natural language processing technologies to extract important keywords and concepts.

[0362] Step 4:

[0363] The server automatically generates test questions using AI

[0364] The server uses generative AI to automatically generate appropriate test questions based on the extracted keywords and concepts. The generated test questions come in a variety of formats, including multiple choice, fill-in-the-blank, and free-form questions.

[0365] Step 5:

[0366] User can view generated tests on device

[0367] The user checks the list of test questions automatically generated by the server on the terminal, checking the content, format, and difficulty of each question one by one.

[0368] Step 6:

[0369] User-generated test editing

[0370] Users can review the test questions and make corrections, additions, or deletions as necessary. For example, they can change the question format or adjust the difficulty level. Once edits are complete, the test is uploaded back to the server and saved.

[0371] Step 7:

[0372] Use an emotion engine to recognize user emotions and adjust test questions accordingly

[0373] While the user is editing the test content, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and if stress or confusion is recognized, the server makes suggestions to readjust the difficulty level or content of the questions.

[0374] Step 8:

[0375] The user enters the student's test results into the terminal.

[0376] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[0377] Step 9:

[0378] Upload the grade data entered by the user to the server

[0379] Once the user has completed entering the data, they upload it to the system, where it is stored on the server and used for subsequent analysis.

[0380] Step 10:

[0381] The server analyzes the grade data and identifies the student's academic ability trends.

[0382] The server analyzes the stored academic data using statistical analysis tools to display students' strengths and weaknesses, as well as their overall academic performance trends.

[0383] Step 11:

[0384] The server generates the academic performance report.

[0385] The server then generates an individual student performance report based on the analysis results, which includes graphs, charts, specific data, and explanations based on the analysis results.

[0386] Step 12:

[0387] The server generates educational strategies.

[0388] Based on the generated academic achievement report, the server generates an optimal educational plan for each student, including specific supplementary learning programs, home study materials, and self-study resources.

[0389] Step 13:

[0390] Use an emotion engine to recognize student emotions and generate motivational strategies for individualized instruction

[0391] The server recognizes students' real-time emotional data and generates strategies that reflect their emotional state during learning. For example, if a student is feeling stressed, it suggests starting with easy problems.

[0392] Step 14:

[0393] The server generates an academic performance report and sends it to the device.

[0394] The server sends the generated academic performance report and countermeasures to the user's device, where the user can check it and share it with students and parents.

[0395] Through these steps, the system will significantly streamline teachers' work and, by taking emotional factors into account, will enable more effective individualized instruction and improved educational quality.

[0396] Example 2

[0397] 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."

[0398] In order to reduce the workload of teachers and improve the quality of education, it is necessary to streamline various tasks, such as creating teaching materials, managing student grades, and proposing individual educational measures. There is also a need for educational support that takes into account the emotions of students and teachers, but existing systems are insufficiently optimized to reflect emotions. Therefore, there is a need for a system that utilizes emotion recognition technology to provide more effective educational support.

[0399] 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.

[0400] In this invention, the server includes means for analyzing uploaded educational data using generative artificial intelligence and automatically generating test questions, means for the user to check and edit the generated test questions via a terminal, means for analyzing the user's emotions using emotion recognition technology and adjusting the difficulty and content of the test questions, means for adjusting the generated educational strategy based on the student's emotions using emotion recognition technology, and means for inputting and uploading student achievement data, which greatly improves the work efficiency of teachers and enables appropriate educational support that takes emotions into consideration.

[0401] "Generative AI" is an AI technology that generates and predicts natural language based on various data.

[0402] "Educational data" refers to data that includes information related to education, such as teaching materials, textbooks, and learning materials.

[0403] "Test questions" are questions or exercises that are generated by analyzing educational data and are used to assess a learner's level of understanding.

[0404] "Device" refers to the device (PC, tablet, smartphone, etc.) used by the user to upload educational data and check and edit test questions.

[0405] "Emotion recognition technology" is a technology that detects and analyzes human emotions from facial expressions, tone of voice, body movements, etc.

[0406] "Performance Data" means data relating to a student's scores or performance on a test or assessment.

[0407] "Educational measures" are proposals and programs generated based on academic performance data and academic trends, with the aim of improving academic performance or providing support for specific subjects.

[0408] This invention aims to improve the efficiency of teachers' work and the quality of education in the field of education by combining an emotion engine to realize educational support that takes into account the emotions of students and teachers. This system is mainly composed of three entities: a server, a terminal, and a user.

[0409] Uploading teaching material data

[0410] The user (teacher) first selects educational data (e.g., digital textbooks in PDF or Word format) using their own device, such as a computer or tablet, and uploads it to the server. The device is provided with a dedicated interface through which the user can easily upload data.

[0411] Automatic test generation

[0412] When the server receives the uploaded educational data, it analyzes the data using text mining technology (for example, using Python's NLTK or spaCy). Based on the analysis results, it automatically generates test questions using a generative AI model (for example, OpenAI's GPT-4 (registered trademark)). These test questions are generated in a variety of formats, including multiple-choice and free-response questions.

[0413] Check and edit test content

[0414] The generated test questions are provided to the user via the terminal. The user can review the test questions and add, delete, or modify questions as needed. The edited test questions are then saved back to the server.

[0415] Use of emotion engine

[0416] While the user is reviewing and editing the test questions, the server uses emotion recognition technology (such as Microsoft® Emotion API) to analyze the user's emotions from their facial expressions and tone of voice. Based on this emotional data, the server makes suggestions to optimize the difficulty and content of the test questions.

[0417] Entering and uploading grade data

[0418] After the test, the user inputs each student's performance data into the terminal and uploads it to the server. The performance data is stored in a database and used for later analysis.

[0419] Analysis of academic performance data and academic ability analysis

[0420] The server performs statistical analysis of the uploaded grade data using Python libraries such as Pandas and NumPy, providing a detailed understanding of students' strengths and weaknesses, as well as their academic ability trends.

[0421] Generate measures to improve academic performance

[0422] Based on the analysis of the grade data, the server uses a generative AI model to automatically generate educational strategies, including supplementary learning programs and home learning materials.

[0423] Adjusting academic achievement measures using an emotion engine

[0424] The server recognizes students' emotional data in real time and generates countermeasures aimed at improving motivation during individual instruction. These countermeasures include suggesting learning materials and methods that will stimulate students' interest in learning.

[0425] Providing and sharing countermeasures

[0426] The generated teaching strategies are sent to the device and can be viewed and shared by the user. Users can share these strategies with students and their parents to improve the quality of individualized instruction.

[0427] Prompt Sentence Examples

[0428] Below is an example of a prompt sentence to input to the generative AI model.

[0429] Automatic generation of test questions

[0430] "Create calculation and multiple choice questions for quizzes from a digital math textbook for fifth graders."

[0431] Proposal of countermeasures

[0432] "Based on Mr. A's grade data, please suggest a set of practice problems for fraction calculations and an effective home study program."

[0433] The introduction of this system will significantly reduce the workload of teachers and provide optimal educational support that takes emotions into consideration.

[0434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] The user selects the teaching material data and uploads it to the server from the terminal.

[0437] Input: The user selects the teaching material data (PDF, Word document, etc.) in the device interface.

[0438] Specific operation: The user selects the teaching material data using the file selection dialog on their computer or tablet.

[0439] Data processing: The terminal converts the selected file into binary data and creates an HTTP request.

[0440] Output: The teaching material data is uploaded to the server.

[0441] Step 2:

[0442] The server receives the training data and stores it in a database.

[0443] Input: Uploaded teaching material data file.

[0444] What happens: The server receives an HTTP request, saves the file in the specified directory on the file system, and records the metadata (file name, upload date, etc.) in a database.

[0445] Data calculation: The server calculates the hash value of the file and verifies the integrity of the data.

[0446] Output: The teaching material data and its metadata are saved in the server's file system and database.

[0447] Step 3:

[0448] The server analyzes the uploaded teaching material data and automatically generates test questions using a generation AI.

[0449] Input: Saved teaching material data file.

[0450] Specific operation: The server uses text mining technology (libraries such as NLTK and spaCy) to analyze the teaching material data into text.

[0451] Data processing: Preprocessing the generated text data and inputting the analysis results into the generative AI model. Creating prompt sentences and sending them to the generative AI model.

[0452] Output: Auto-generated test questions as responses from the generative AI model.

[0453] Step 4:

[0454] The terminal displays the generated test questions to the user.

[0455] Input: Auto-generated test questions.

[0456] Specific operation: Generates a UI (user interface) for the device to display the test question data received from the server.

[0457] Output: A list of test questions that the user can view on their device.

[0458] Step 5:

[0459] Users review and edit test questions.

[0460] Input: Test questions displayed on the terminal.

[0461] Specific operation: The user checks the test questions through the interface, and deletes, adds, or modifies questions as needed. The edits are then sent from the device to the server.

[0462] Output: The edited test question.

[0463] Step 6:

[0464] The server saves the edited test questions.

[0465] Input: Edited test question data.

[0466] Specific operation: The server reflects the received edited data on the original test question set and saves it in the database.

[0467] Output: The most recent saved test question set.

[0468] Step 7:

[0469] The server uses emotion recognition technology to analyze the user's emotions and adjust the difficulty and content of the test questions.

[0470] Input: User's facial expression and voice data.

[0471] Specific operation: The server calls the emotion recognition API and obtains the analysis results of facial expressions and voice.

[0472] Data Computation: Analyzes emotional data and generates suggestions to optimize the difficulty and format of test questions based on the user's emotional state.

[0473] Output: Suggested adjustments to test questions based on sentiment analysis.

[0474] Step 8:

[0475] The user inputs the student's grade data into the terminal and uploads it to the server.

[0476] Input: Performance data entered by the user into the device.

[0477] Specific operation: The user uses the terminal interface to input the performance results for each student.

[0478] Data processing: The terminal organizes the entered performance data and sends it to the server.

[0479] Output: The grade data is uploaded to the server.

[0480] Step 9:

[0481] The server analyzes the grade data and identifies students' academic trends.

[0482] Input: Uploaded grade data.

[0483] Specific operation: The server performs statistical analysis on the performance data using Pandas and NumPy.

[0484] Data calculation: Analyze patterns of strong and weak subjects, as well as academic performance trends.

[0485] Output: Student academic performance trend data as the analysis result.

[0486] Step 10:

[0487] The server automatically generates educational strategies based on the results of the academic ability analysis.

[0488] Input: Student academic performance trend data.

[0489] How it works: The server uses the generative AI model to create optimal educational strategies for each student.

[0490] Data calculation: Educational measures include automatically generating supplementary programs and home learning materials.

[0491] Output: Automatically generated educational strategies.

[0492] Step 11:

[0493] The server uses emotion recognition technology to recognize students' emotions and generates countermeasures to improve motivation during individual instruction.

[0494] Input: Student emotion data.

[0495] Specific operation: The server calls the emotion recognition API in real time to obtain the student's emotions.

[0496] Data calculation: Optimizing individualized instruction methods to improve motivation based on emotional data.

[0497] Output: Optimized educational strategies for improving motivation.

[0498] Step 12:

[0499] The generated educational strategy plan is sent to the terminal and can be viewed and shared by the user.

[0500] Input: Optimized educational strategy.

[0501] Specific operation: The server sends the countermeasure proposal to the user's device, which provides an interface to display the countermeasure proposal.

[0502] Output: The educational plan displayed on the device. The user can view the plan and share it with students and parents.

[0503] (Application example 2)

[0504] 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."

[0505] Conventional factory robot-based work support systems are unable to generate work instructions or provide guidance that takes into account the emotions of workers, making it difficult to implement efficient and flexible work improvement. Furthermore, instructions that ignore the emotions and motivation of workers can lead to reduced work efficiency and inconsistent quality. The present invention aims to solve these problems by providing optimal work instructions and work improvement proposals that take into account the emotions of workers.

[0506] 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.

[0507] In this invention, the server includes means for analyzing uploaded information using generative artificial intelligence and automatically generating work instructions, means for workers to confirm and edit the work instructions generated through the device, means for inputting and uploading work results, means for recognizing the emotions of workers using an emotion engine and adjusting the difficulty and content of the work instructions, and means for sending the generated work improvement proposals to the device so that workers can view and share them. This makes it possible to provide flexible and efficient work instructions and work improvement proposals that take emotions into consideration.

[0508] "Uploading" is the act of sending and storing information from one device to another computer system, such as a server or cloud.

[0509] "Analysis" is the act of examining data or information in detail to clarify its structure, content, and meaning.

[0510] "Automatic generation" refers to the use of artificial intelligence or specific algorithms to generate the necessary information or data without manual intervention.

[0511] "Work instructions" are information used to communicate specific work content and procedures to workers.

[0512] An "apparatus" is a mechanical or electronic device used for a specific purpose.

[0513] "Verification" is the process of verifying whether the generated data or instructions are correct.

[0514] "Editing" is the act of modifying or changing generated data or instructions.

[0515] "Work results" are the results or performance of the work performed by a worker.

[0516] The "Emotion Engine" is an artificial intelligence technology that recognizes and analyzes emotions from facial expressions, voice, actions, etc.

[0517] "Cognition" is the ability or act of understanding and identifying specific information.

[0518] "Difficulty" refers to the degree of difficulty in accomplishing a task or problem.

[0519] "Content" refers to the specific content of information or data.

[0520] "Adjustment" is the act of changing content or standards to meet specific goals or conditions.

[0521] A "business improvement proposal" is a specific method or means proposed to improve the efficiency or quality of work or operations.

[0522] "Viewing" is the act of checking and looking at the generated data and information.

[0523] "Sharing" is the act of using specific information or data together with other users.

[0524] The present invention relates to a work support system for factory robots, and by combining an emotion engine and generative artificial intelligence, it provides optimal work instructions and work improvement proposals according to the emotions of workers. Specific embodiments are described below.

[0525] System Configuration

[0526] 1. Hardware

[0527] Server: A high-performance computer that processes data analysis, generative artificial intelligence, and emotion engines.

[0528] Devices: Computers, tablets, and smartphones used by workers and managers.

[0529] Camera device: A camera for recognizing the facial expressions of workers.

[0530] 2. Software

[0531] Python: Used as a programming language.

[0532] OpenCV: An image processing library used for facial expression recognition.

[0533] TextBlob: A library for text parsing and generation.

[0534] scikit-learn: A machine learning library for sentiment classification.

[0535] Operation process

[0536] 1. Uploading Information

[0537] The administrator uploads the work procedure data to the server, which then analyzes the data and uses it as the basis for work instructions.

[0538] 2. Automatic generation of work instructions

[0539] The server analyzes the uploaded work procedure data and automatically generates work instructions using a generative AI model, which include specific work content and procedures.

[0540] 3. Review and edit work instructions

[0541] The worker checks the generated work instructions through their terminal and edits them as necessary. At this time, the emotion engine analyzes the worker's facial expressions and tone of voice to suggest the most appropriate instructions and level of difficulty.

[0542] 4. Enter and upload labor results

[0543] After completing their work, workers enter their work results into a terminal and upload them to the server, which then obtains the information necessary for the next data analysis.

[0544] 5. Use of Emotion Engine

[0545] The server uses an emotion engine to recognize the worker's emotions in real time and adjusts optimal work instructions and business improvement proposals based on the worker's motivation and emotions.

[0546] 6. Analyzing work results and generating work improvement proposals

[0547] The server analyzes the uploaded work results and evaluates the worker's work efficiency and quality. Based on this, it generates business improvement proposals using a generative AI model.

[0548] 7. Providing and sharing business improvement proposals

[0549] The server sends the generated business improvement proposals to the terminals, where workers and managers can view and share them, thereby achieving efficient and high-quality work.

[0550] Specific examples

[0551] 1. Facial Recognition Prompts

[0552] Example: image_path = 'worker_face.jpg'; emotions = recognize_emotion(image_path)

[0553] 2. Prompt for work order generation

[0554] Example: template = "Generate instructions for"; data = {"task": "assemble", "parts": ["screw", "nut"]}; work_instruction = generate_work_instruction(template, data)

[0555] This will enable flexible and efficient work instructions and business improvement proposals that take emotions into account.In addition, the use of specific devices and software makes the system realistic and practical to implement.

[0556] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0557] Step 1:

[0558] The user uploads the work procedure data to the server via the terminal.

[0559] Input: Work procedure data (e.g., assembly instructions)

[0560] Data processing and calculation: The server stores the uploaded data and analyzes its contents.

[0561] Output: Analyzed work procedure data

[0562] Step 2:

[0563] The server uses the analyzed work procedure data to automatically generate work instructions using a generative artificial intelligence model.

[0564] Input: Parsed work procedure data

[0565] Data processing and calculation: The generative artificial intelligence model understands the content of the work procedures and generates specific work instructions.

[0566] Output: Generated work instructions (e.g., specific assembly steps)

[0567] Step 3:

[0568] The user can check the work instructions generated from the server through the terminal and edit them as necessary.

[0569] Input: Generated Work Order

[0570] Data processing and calculation: Users can check the instructions on the terminal and make corrections or additions, for example, by adding details to the work procedure or changing the order of the steps.

[0571] Output: Reviewed and edited work instructions

[0572] Step 4:

[0573] The server uses an emotion engine to recognize emotions while the user is editing the work instructions and suggests editing content and difficulty.

[0574] Input: User's facial expression data and voice data

[0575] Data processing and calculation: The emotion engine analyzes facial expression and voice data to evaluate the user's emotional state. Based on this, it makes suggestions regarding editing content and difficulty.

[0576] Output: Sentiment analysis results and suggested edits and difficulty changes

[0577] Step 5:

[0578] After the user completes the work, he / she inputs the results of the work through the terminal and uploads them to the server.

[0579] Input: Work result data (e.g., work completion report)

[0580] Data processing and calculation: Labor outcome data is collected and stored on a server for future analysis.

[0581] Output: Saved labor result data

[0582] Step 6:

[0583] The server analyzes the uploaded work result data and evaluates work efficiency and quality.

[0584] Input: Saved labor result data

[0585] Data processing and calculation: Analyzes work result data and generates statistical information on work efficiency and quality, such as the time required for work and error rate.

[0586] Output: Evaluation results of work efficiency and quality

[0587] Step 7:

[0588] Based on the evaluation results, the server generates business improvement proposals using a generative artificial intelligence model.

[0589] Input: Work efficiency and quality evaluation results

[0590] Data processing and calculation: The generative AI model analyzes the evaluation results and generates specific improvement proposals for improving efficiency and quality.

[0591] Output: Generated business improvement proposals (e.g., proposed changes to work procedures)

[0592] Step 8:

[0593] The server sends the generated business improvement proposals to the terminal, where the user can view and share them.

[0594] Input: Generated business improvement proposal

[0595] Data processing and calculation: The generated business improvement proposals are sent to the user's device so that they can be viewed and shared.

[0596] Output: Business improvement proposals displayed on the user's device

[0597] By following these steps, the server, terminal, and user interact with each other to provide flexible and efficient work instructions and business improvement proposals that respond to emotions.

[0598] 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.

[0599] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0600] 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.

[0601] [Second embodiment]

[0602] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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."

[0614] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education.

[0615] System configuration and functions

[0616] 1. Uploading teaching material data

[0617] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[0618] Users select teaching material data, such as digital textbooks and slides they have created, using a computer or tablet and upload it to the system. This uploaded data is stored on the server and used for subsequent processing.

[0619] 2. Automatic generation of test creation

[0620] The server analyzes the educational data and automatically generates test questions using generative AI.

[0621] The server analyzes the uploaded educational data. Text mining technology is used for the analysis to extract important keywords and concepts. Based on these extraction results, the generative AI automatically generates appropriate test questions. The generated test questions come in multiple question formats (multiple choice, fill-in-the-blank, written, etc.).

[0622] 3. Check and edit the test content

[0623] User-generated test questions can be viewed and edited on the device

[0624] The user checks the automatically generated test questions on their device, checks the appropriateness of the questions, and makes any necessary modifications, such as adding or deleting questions or adjusting the difficulty level. After editing, the test questions are uploaded back to the server and saved in the system.

[0625] 4. Enter and upload grade data

[0626] The user enters the student's test results into the terminal and uploads them to the server.

[0627] After the test, the user enters the student's answers into the device and uploads the results data to the system. The results data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions. This data is also stored on the server.

[0628] 5. Analysis of academic performance data and academic ability analysis

[0629] The server analyzes the grade data and identifies the student's academic ability trends.

[0630] The server analyzes the uploaded grade data, using statistical analysis to identify each student's strengths and weaknesses and overall academic trends. If necessary, the same analysis can be performed for specific classes or groups selected by the teacher.

[0631] 6. Generating measures to improve academic ability

[0632] The server automatically generates educational strategies based on the results of the academic ability analysis.

[0633] Based on the analysis results, the server generates optimal educational strategies for each student, including remedial programs, additional learning materials, and self-study resources. For example, a student who struggles with fraction calculations in math might be provided with practice problems specific to that area.

[0634] 7. Providing and sharing countermeasures

[0635] The server sends the generated educational plan to the device, where the user can view and share it.

[0636] The server sends the generated educational strategies to the user's device. The user can review the strategies on their device and share them with students and parents as needed. This is expected to improve the accuracy of individualized instruction and lead to improved academic performance for students.

[0637] Specific examples

[0638] Below are some specific examples of how this system can be used.

[0639] Uploading teaching material data

[0640] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[0641] Auto-generated test creation

[0642] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[0643] Check and edit test content

[0644] The teacher checks the generated test questions, adjusts the difficulty of some questions, and saves them again on the server.

[0645] Entering and uploading grade data

[0646] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[0647] Analysis of academic performance data and academic ability analysis

[0648] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[0649] Generate measures to improve academic performance

[0650] The server generates a set of fraction calculation practice problems and a home study program for Mr. A.

[0651] Providing and sharing countermeasures

[0652] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[0653] The introduction of this system will significantly reduce the burden on teachers and improve the quality of education.

[0654] The processing flow will be explained below.

[0655] Step 1:

[0656] The user selects the teaching material data

[0657] The user (teacher) uses a computer or tablet to select the target digital teaching material data (e.g., textbooks, slides, supplementary materials, etc.) in a file browser.

[0658] Step 2:

[0659] Upload the teaching material data selected by the user from the device to the server.

[0660] The user clicks a dedicated upload button to upload the selected teaching material data to the system. The teaching material data is transferred to the server via the Internet and stored on the server.

[0661] Step 3:

[0662] The server analyzes the uploaded educational data

[0663] The server analyzes the stored learning material data and uses text mining technology to extract important keywords and concepts from the text content of the learning material. Natural language processing technology is also utilized in this process.

[0664] Step 4:

[0665] The server automatically generates test questions using AI

[0666] The server uses generative AI to create test questions based on the extracted keywords and concepts. The generated test questions come in multiple formats, including multiple choice, fill-in-the-blank, and free-form questions.

[0667] Step 5:

[0668] User can view generated tests on device

[0669] The user checks the list of test questions automatically generated by the server on their device, checking the content, format, and difficulty of each question one by one.

[0670] Step 6:

[0671] User-generated test editing

[0672] Users can review the test questions and make corrections, additions, or deletions as needed. For example, they can change the question format or adjust the difficulty level. Once edited, the test is uploaded back to the server and saved.

[0673] Step 7:

[0674] The user enters the student's test results into the terminal.

[0675] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[0676] Step 8:

[0677] Upload the grade data entered by the user to the server

[0678] Once the data has been entered, the user uploads it to the system, where it is stored on the server and used for subsequent analysis.

[0679] Step 9:

[0680] The server analyzes the performance data

[0681] The server analyzes the stored grade data and uses statistical analysis tools to identify students' strengths and weaknesses, as well as academic trends.

[0682] Step 10:

[0683] The server generates the academic performance report.

[0684] The server then generates an academic performance report for each student based on the analysis results, including graphs, charts, and commentary based on the analysis results.

[0685] Step 11:

[0686] The server generates educational strategies.

[0687] Based on the generated academic achievement report, the server automatically generates educational strategies tailored to each student, including areas to strengthen in class and materials for home study.

[0688] Step 12:

[0689] The server generates an academic performance report and sends it to the device.

[0690] The server sends the generated report and countermeasures to the user's device, where the user can review it and share it with students and parents as needed.

[0691] Through these steps, the system can significantly improve the efficiency of teachers' work and improve the quality of education.

[0692] Example 1

[0693] 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."

[0694] In the field of education, teachers have a wide range of tasks, which creates a heavy workload. Furthermore, because they are required to deliver education efficiently while maintaining a certain level of quality, systems are needed that reduce the burden on teachers while improving the quality of education. In particular, tasks such as creating teaching materials, creating tests, and managing student grades are labor-intensive, and technology is needed to perform these tasks efficiently.

[0695] 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.

[0696] In this invention, the server includes means for analyzing uploaded educational data using a generation AI and automatically generating test questions, means for users to review and edit the generated test questions via a terminal, means for inputting and uploading student achievement data, means for analyzing the achievement data and identifying students' academic ability trends, means for automatically generating educational strategies based on the results of the academic ability analysis, and means for sending the generated educational strategies to the terminal so that users can view and share them. This enables efficient management and analysis of educational data, significantly reducing the workload of teachers and improving the quality of education.

[0697] "Generative AI" is an artificial intelligence technology that automatically generates new information and solutions based on uploaded data.

[0698] "Educational data" refers to information and materials related to education, such as digital textbooks and created slides.

[0699] "Test questions" are questions that are asked to assess a student's understanding and knowledge.

[0700] "Academic performance data" refers to data such as test scores and evaluation results obtained by students.

[0701] "Academic ability trends" refers to trends that indicate a student's strengths and weaknesses in subjects and their learning progress.

[0702] "Educational measures" are proposals for specific teaching methods and teaching materials to improve students' academic abilities.

[0703] A "terminal" is a device such as a computer or tablet that is directly operated by a user.

[0704] "Users" refer to teachers and other educational personnel who use this system.

[0705] A "server" is a computer system that provides services and resources on a computer network.

[0706] "Text mining" is an analytical technique for extracting useful information from natural language data.

[0707] "Statistical analysis" is an analytical method that aims to obtain information by analyzing data using statistical techniques.

[0708] "Visualization tools" are software and techniques for visually displaying data.

[0709] MODE FOR CARRYING OUT THE INVENTION

[0710] This invention is a system aimed at improving the work efficiency of teachers and the quality of education in the field of education. This system has the functions of analyzing uploaded educational data using generative AI and automatically generating test questions, allowing teachers to review and edit the generated test questions, inputting and uploading grade data, and automatically generating educational countermeasures based on student grade data to grasp academic ability trends.

[0711] Hardware and software used

[0712] Hardware

[0713] Server: Stores and analyzes educational data, and generates test questions and educational strategies.

[0714] Terminal: A device (e.g., PC, tablet) that teachers use to upload teaching material data, check and edit test questions, and enter and upload grade data.

[0715] software

[0716] Generative AI: Artificial intelligence that analyzes teaching material data and generates test questions and educational strategies (e.g., GPT-3, BERT).

[0717] Text mining technology: Natural language processing engines (e.g., SpaCy, NLTK) for extracting important keywords and concepts from teaching material data.

[0718] Data analysis tools: Software for statistical analysis of performance data and identifying trends in student achievement (e.g., Pandas, NumPy).

[0719] Visualization tools: Tools for visually displaying the results of performance data analysis (e.g., Matplotlib, Seaborn).

[0720] Explanation of program processing

[0721] Uploading teaching material data

[0722] A user (teacher) uses a PC or tablet to select educational data (digital textbooks, created slides, etc.) and uploads them to the server from the device. The server saves the received data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[0723] Auto-generated test creation

[0724] The server analyzes the uploaded educational data using text mining technology to extract important keywords and concepts. Based on the extracted keywords and concepts, the generation AI generates appropriate test questions (multiple choice, fill-in-the-blank, essay, etc.). Examples of generated prompts include:

[0725] "Read the following text and select the appropriate option. Text: 『○○』"

[0726] Check and edit test content

[0727] The user checks the test questions generated on the device and makes corrections as necessary. The corrected test questions are then uploaded back to the server and saved.

[0728] Entering and uploading grade data

[0729] After the test, the user enters the student's answers into the device and uploads the results to the server, which then stores the received data in a database.

[0730] Analysis of academic performance data and academic ability analysis

[0731] The server analyzes the uploaded grade data using statistical analysis tools to identify each student's academic performance trends, and the analysis results are displayed visually using visualization tools.

[0732] Generate measures to improve academic performance

[0733] The server generates individualized educational strategies based on the results of the academic ability analysis. These strategies include remedial programs, additional learning materials, and self-study resources. Examples of generated prompts include:

[0734] "For the next student, please suggest the following strategies for those struggling with fractions in math:"

[0735] Providing and sharing countermeasures

[0736] The server sends the generated educational countermeasures plan to the user's device, where the user confirms it and then shares it with students and parents.The countermeasures plan is distributed via an educational portal site or email system, allowing students and parents to access it.

[0737] This will enable the efficient management and analysis of educational data, which is expected to significantly reduce the workload of teachers while improving the quality of education.

[0738] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0739] System program processing flow

[0740] Step 1: Upload the teaching material data

[0741] Input: User-selected teaching material data (file format: PDF, PPT, etc.)

[0742] Output: Learning material data and file metadata stored on the server

[0743] Specific behavior:

[0744] Users select the teaching material data on their computers or tablets.

[0745] The terminal gets the file path through a file selection dialog.

[0746] The terminal sends the selected teaching material data to the server using an HTTP request.

[0747] The server stores the received teaching material data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[0748] Step 2: Analyzing Educational Data

[0749] Input: Teaching material data stored on the server

[0750] Output: Extracted terms and concepts

[0751] Specific behavior:

[0752] The server reads the teaching material data and analyzes it using text mining technology.

[0753] The server uses a natural language processing engine (e.g. SpaCy, NLTK) to extract important keywords and concepts.

[0754] The server temporarily stores the extracted keywords and concepts.

[0755] Step 3: Generate test questions

[0756] Input: Extracted keywords and concepts

[0757] Output: Auto-generated test questions

[0758] Specific behavior:

[0759] The server uses generative AI (e.g., GPT-3, BERT) to generate test questions based on the extracted keywords and concepts.

[0760] The server sets up a generation prompt and sends a request to the generative AI model.

[0761] Example prompt: "Generate three multiple choice questions using the following keywords: fractions, math, 5th grade"

[0762] The server formats and saves the test questions received from the generation AI.

[0763] Step 4: Review and edit the test content

[0764] Input: Auto-generated test questions

[0765] Output: Test questions corrected by the user

[0766] Specific behavior:

[0767] The server sends the generated test questions to the device.

[0768] The user checks the test questions generated on the terminal.

[0769] The user uses the editing screen of the web application to modify the test questions (add, delete, adjust the difficulty level, etc.).

[0770] The device uploads the modified test questions to the server.

[0771] Step 5: Enter and upload grade data

[0772] Input: Student answer results entered by the user

[0773] Output: Achievement data stored on the server

[0774] Specific behavior:

[0775] After the user takes the test, the student's answers are entered into the terminal.

[0776] The terminal uses a web application form to input each student's grade data.

[0777] The terminal sends the entered score data to the server using an HTTP request.

[0778] The server stores the received results data in a database.

[0779] Step 6: Analysis of academic performance data and academic achievement analysis

[0780] Input: Achievement data stored on the server

[0781] Output: Academic performance trend report for each student

[0782] Specific behavior:

[0783] The server reads the performance data and analyzes it using statistical analysis tools (e.g., Pandas, NumPy).

[0784] The server calculates each student's correct answer rate, average score, distribution, etc.

[0785] The server uses visualization tools (e.g., Matplotlib, Seaborn) to graph the results and generate academic performance trend reports.

[0786] Step 7: Generate strategies to improve academic performance

[0787] Input: Academic ability analysis results

[0788] Output: Automatically generated educational strategies

[0789] Specific behavior:

[0790] The server uses generative AI to generate educational strategy proposals based on the results of the academic ability analysis.

[0791] The server sets up a generation prompt and sends a request to the generative AI model.

[0792] Example prompt: "For the following student, please suggest the following strategies for solving problems with fractions in math:"

[0793] The server formats and saves the generated educational strategies.

[0794] Step 8: Provide and share countermeasures

[0795] Input: Automatically generated educational plan

[0796] Output: Solutions provided to users, students, and parents

[0797] Specific behavior:

[0798] The server sends the generated educational strategy plan to the user's terminal.

[0799] The user checks the educational measures on the device.

[0800] Users share the countermeasures with students and parents by distributing them via educational portal sites and email systems, making them viewable and downloadable.

[0801] (Application example 1)

[0802] 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."

[0803] In the field of education, teachers must take measures to improve the academic ability of each student while juggling a wide range of tasks. However, the series of tasks, such as preparing teaching materials, creating tests, managing grades, and creating countermeasures based on the results, are enormous and require time and effort. For this reason, a system is needed to carry out these tasks efficiently and effectively. In addition, to take effective educational measures, teachers need the ability to check and customize educational content in real time.

[0804] 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.

[0805] In this invention, the server includes means for analyzing uploaded educational data using a generation artificial intelligence and automatically generating test questions, means for searching and selecting teaching materials in a virtual space, means for a user to check and edit the generated test questions, means for previewing and editing educational strategies in real time through a terminal, means for inputting and uploading student achievement data, and means for previewing and editing educational strategies in the virtual space. This allows teachers to efficiently obtain the necessary teaching materials and strategies and customize educational content in real time.

[0806] "Generative AI" is an AI technology that has the ability to analyze uploaded educational data and automatically generate test questions and educational strategies.

[0807] "Educational data" is a general term for digital data related to education, such as textbooks, slides, and teaching materials.

[0808] A "virtual space" is a virtual environment constructed using virtual reality technology that allows users to visually and experientially explore and select educational materials.

[0809] "Device" is a general term for electronic devices such as computers, smartphones, and tablets that users use to check, edit, and upload educational data.

[0810] "Test questions" are questions to evaluate learning content that are automatically generated by generative artificial intelligence based on educational data.

[0811] "Academic performance data" refers to data that evaluates a student's learning outcomes and includes grade information based on the results.

[0812] "Educational strategy" is a general term for specific educational plans and supplementary materials that are generated by analyzing academic performance data in order to improve each student's academic ability.

[0813] "Real-time preview" is a function that allows users to instantly check educational data and countermeasures on their devices or in a virtual space.

[0814] "Editing" refers to the act of the user changing or modifying the content of the generated test questions or educational strategies.

[0815] This invention is a system aimed at improving work efficiency and the quality of education in the field of education. This system has the functions of allowing teachers to upload educational data, automatically generating test questions using generative artificial intelligence, and exploring teaching materials in a virtual space, previewing and editing them in real time. The specific configuration and processing required to realize this system are described below.

[0816] 1. Uploading teaching material data

[0817] Users upload educational material data, such as digital textbooks and slides they have created, from their devices (PCs or tablets) to the server. The uploaded data is stored on the server and used for subsequent processing.

[0818] 2. Automatic generation of test creation

[0819] The server analyzes the uploaded educational data. This analysis uses text mining technology implemented in Python to extract important keywords and concepts. Based on the extracted results, a generative artificial intelligence model using TensorFlow and PyTorch automatically generates appropriate test questions. The generated test questions include multiple choice, fill-in-the-blank, and essay questions.

[0820] 3. Explore and preview learning materials in a virtual space

[0821] Users put on a VR headset (such as Oculus Quest 2) and enter a virtual space built with Unity or Unreal Engine. In the virtual space, users can explore and select learning materials and preview them in real time. The selected learning materials include test questions and supplementary materials automatically generated by the system.

[0822] 4. Check and edit the test content

[0823] Users can check the generated test questions on their device and edit them as needed. They can check the appropriateness of the questions with a real-time preview and add, delete, or adjust the difficulty level. After editing, the test questions are saved back to the server.

[0824] 5. Enter and upload grade data

[0825] After taking the test, the user enters the student's performance data into the device and uploads it to the server. The performance data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions, and is saved on the server.

[0826] 6. Analysis of academic performance data and academic ability analysis

[0827] The server analyzes the uploaded grade data, using Python-based statistical analysis algorithms to identify each student's strengths and weaknesses, as well as overall academic performance trends.

[0828] 7. Generating measures to improve academic ability

[0829] Based on the analysis of the grade data, the server generates optimal educational strategies, including supplementary learning programs, additional teaching materials, and self-study resources.

[0830] 8. Providing and sharing countermeasures

[0831] The generated educational strategies are sent from the server to the user's device, where the user can view and share them, improving the accuracy of individualized instruction.

[0832] Examples of specific examples and prompts

[0833] Below are some specific examples of prompt sentences to input into the generative AI model.

[0834] "Generate multiple-choice quiz questions based on 5th grade math materials."

[0835] "Based on the above teaching materials, please generate a supplementary workbook that specializes in fraction calculations."

[0836] This allows teachers to carry out educational activities effectively and efficiently.

[0837] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0838] Step 1:

[0839] Users use their devices to upload educational material data (digital textbooks, created slides, etc.) to the server.

[0840] Input: Teaching material data

[0841] Output: Teaching material data saved on the server

[0842] Specific operation: The user uses a PC or tablet to select teaching material data from the system interface and clicks the "Upload" button.

[0843] Step 2:

[0844] The server analyzes the uploaded educational data and extracts important keywords and concepts.

[0845] Input: Teaching material data stored on the server

[0846] Output: Extracted keywords and concepts

[0847] Specific operation: The server runs a text mining algorithm implemented in Python to analyze the teaching material data, extracting keywords and concepts and storing them in a database.

[0848] Step 3:

[0849] The server automatically generates test questions using a generative AI model based on the extracted keywords and concepts.

[0850] Input: Extracted keywords and concepts

[0851] Output: Auto-generated test questions

[0852] Specific operation: The server feeds input data (extracted keywords and concepts) into a generative AI model built with TensorFlow or PyTorch, and generates test questions.

[0853] Step 4:

[0854] The user uses a VR headset to enter a teaching material shop in a virtual space and search for and select teaching material data.

[0855] Input: Teaching materials in virtual space

[0856] Output: Selected teaching material data

[0857] Specific operations: The user puts on a VR headset such as Oculus Quest 2 and moves around a virtual space built with Unity or Unreal Engine to find, pick up and select educational materials.

[0858] Step 5:

[0859] The user reviews and edits the automatically generated test questions on the device.

[0860] Input: Auto-generated test questions

[0861] Output: Test questions edited by the user

[0862] Specific operation: The user views the test questions through the device, and adds, deletes, and adjusts the difficulty of questions as needed. The edited content is saved back to the server.

[0863] Step 6:

[0864] After the user takes the test, the student's performance data is entered into the terminal and uploaded to the server.

[0865] Input: Student answer results

[0866] Output: Grade data saved on the server

[0867] Specific operation: The user enters the student's answer results into the grade management system and clicks the "Upload" button.

[0868] Step 7:

[0869] The server analyzes the grade data and identifies each student's academic ability trends.

[0870] Input: Student performance data

[0871] Output: Academic trend report

[0872] Specific operation: The server uses Python statistical analysis algorithms to analyze the grade data, identify strong and weak subjects, and compile trends into a report.

[0873] Step 8:

[0874] The server generates educational strategies for each student based on their academic ability trends.

[0875] Input: Academic Trend Report

[0876] Output: Educational measures

[0877] Specific operation: The server uses the generated AI model to generate supplementary learning programs and additional teaching materials tailored to specific academic trends.

[0878] Step 9:

[0879] The server sends the generated educational strategy plan to the user's device, where the user can review and share it.

[0880] Input: Educational measures proposal

[0881] Output: Educational measures displayed on the user's device

[0882] Specific operation: The server sends the proposed countermeasures to the user's device, and the user reviews the contents and shares them with students and parents as necessary.

[0883] 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.

[0884] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education, and by combining it with an emotion engine, realizes educational support that takes into account the emotions of students and teachers.

[0885] System configuration and functions

[0886] 1. Uploading teaching material data

[0887] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[0888] Users select and upload teaching material data using a computer or tablet, and this data is stored on a server for later analysis and test creation.

[0889] 2. Automatic generation of test creation

[0890] The server analyzes the educational data and automatically generates test questions using generative AI.

[0891] The server analyzes the uploaded educational data using text mining technology, and the AI ​​automatically generates appropriate test questions, ranging from multiple choice questions to free-form questions.

[0892] 3. Check and edit the test content

[0893] User-generated tests can be viewed and edited on the device

[0894] Users can view the test questions generated on their devices, add, delete, or modify questions, and the edited test is saved back to the server.

[0895] 4. Use of Emotion Engine

[0896] The server uses an emotion engine to recognize the user's emotions and adjust the difficulty and content of the test questions.

[0897] When a teacher is reviewing and editing test questions, the emotion engine analyzes the teacher's emotions from their facial expressions and tone of voice, optimizing the difficulty level and question format of the proposed content.

[0898] 5. Enter and upload grade data

[0899] The user enters the student's test results into the terminal and uploads them to the server.

[0900] After the test, the user enters the results data for each student into the terminal and uploads it. This data is also saved on the server.

[0901] 6. Analysis of academic performance data and academic ability analysis

[0902] The server analyzes the grade data and identifies the student's academic ability trends.

[0903] Based on the uploaded grade data, the server performs statistical analysis of students' strong and weak subjects and academic trends.

[0904] 7. Generating measures to improve academic ability

[0905] The server automatically generates educational strategies based on the results of the academic ability analysis.

[0906] Based on the analysis results, the server generates optimal educational strategies for each student, including supplementary learning programs and home study materials.

[0907] 8. Adjusting academic achievement strategies using an emotion engine

[0908] The server uses an emotion engine to recognize students' emotions and generate strategies to improve motivation for individual instruction.

[0909] The server recognizes students' emotions in real time and generates teaching guidelines and countermeasures that take their motivation into account.

[0910] 9. Providing and sharing countermeasures

[0911] The server sends the generated educational plan to the device, where the user can view and share it.

[0912] The server sends the generated countermeasures to the teacher's device, where the user can check the countermeasures and share them with students and parents to improve the quality of individual instruction.

[0913] Specific examples

[0914] Below are some specific examples of how this system can be used.

[0915] Uploading teaching material data

[0916] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[0917] Auto-generated test creation

[0918] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[0919] Check and edit test content

[0920] The teacher reviews the generated test questions, adjusts the difficulty of some questions, and saves them back on the server. At this time, the emotion engine analyzes the teacher's emotions and automatically suggests the difficulty level of the test questions.

[0921] Entering and uploading grade data

[0922] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[0923] Analysis of academic performance data and academic ability analysis

[0924] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[0925] Generation of measures to improve academic performance and adjustment using an emotion engine

[0926] The server generates a set of fraction calculation practice problems and a home study program for Mr. A. Furthermore, the emotion engine recognizes Mr. A's emotions and suggests teaching methods to improve his motivation.

[0927] Providing and sharing countermeasures

[0928] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[0929] The introduction of this system will significantly reduce the burden on teachers and further improve the quality of education by taking emotional factors into consideration.

[0930] The processing flow will be explained below.

[0931] Step 1:

[0932] The user selects the teaching material data

[0933] The user (teacher) uses a computer or tablet to select the target teaching material data (e.g., digital textbook, slides, supplementary materials) in a file browser.

[0934] Step 2:

[0935] Upload the teaching material data selected by the user from the device to the server.

[0936] The user clicks a button to upload the selected teaching material data to the system, which is then transferred to the server via the Internet and stored on the server.

[0937] Step 3:

[0938] The server analyzes the uploaded educational data

[0939] The server analyzes the stored teaching material data and uses text mining and natural language processing technologies to extract important keywords and concepts.

[0940] Step 4:

[0941] The server automatically generates test questions using AI

[0942] The server uses generative AI to automatically generate appropriate test questions based on the extracted keywords and concepts. The generated test questions come in a variety of formats, including multiple choice, fill-in-the-blank, and free-form questions.

[0943] Step 5:

[0944] User can view generated tests on device

[0945] The user checks the list of test questions automatically generated by the server on the terminal, checking the content, format, and difficulty of each question one by one.

[0946] Step 6:

[0947] User-generated test editing

[0948] Users can review the test questions and make corrections, additions, or deletions as necessary. For example, they can change the question format or adjust the difficulty level. Once edits are complete, the test is uploaded back to the server and saved.

[0949] Step 7:

[0950] Use an emotion engine to recognize user emotions and adjust test questions accordingly

[0951] While the user is editing the test content, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and if stress or confusion is recognized, the server makes suggestions to readjust the difficulty level or content of the questions.

[0952] Step 8:

[0953] The user enters the student's test results into the terminal.

[0954] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[0955] Step 9:

[0956] Upload the grade data entered by the user to the server

[0957] Once the user has completed entering the data, they upload it to the system, where it is stored on the server and used for subsequent analysis.

[0958] Step 10:

[0959] The server analyzes the grade data and identifies the student's academic ability trends.

[0960] The server analyzes the stored academic data using statistical analysis tools to display students' strengths and weaknesses, as well as their overall academic performance trends.

[0961] Step 11:

[0962] The server generates the academic performance report.

[0963] The server then generates an individual student performance report based on the analysis results, which includes graphs, charts, specific data, and explanations based on the analysis results.

[0964] Step 12:

[0965] The server generates educational strategies.

[0966] Based on the generated academic achievement report, the server generates an optimal educational plan for each student, including specific supplementary learning programs, home study materials, and self-study resources.

[0967] Step 13:

[0968] Use an emotion engine to recognize student emotions and generate motivational strategies for individualized instruction

[0969] The server recognizes students' real-time emotional data and generates strategies that reflect their emotional state during learning. For example, if a student is feeling stressed, it suggests starting with easy problems.

[0970] Step 14:

[0971] The server generates an academic performance report and sends it to the device.

[0972] The server sends the generated academic performance report and countermeasures to the user's device, where the user can check it and share it with students and parents.

[0973] Through these steps, the system will significantly streamline teachers' work and, by taking emotional factors into account, will enable more effective individualized instruction and improved educational quality.

[0974] Example 2

[0975] 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."

[0976] In order to reduce the workload of teachers and improve the quality of education, it is necessary to streamline various tasks, such as creating teaching materials, managing student grades, and proposing individual educational measures. There is also a need for educational support that takes into account the emotions of students and teachers, but existing systems are insufficiently optimized to reflect emotions. Therefore, there is a need for a system that utilizes emotion recognition technology to provide more effective educational support.

[0977] 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.

[0978] In this invention, the server includes means for analyzing uploaded educational data using generative artificial intelligence and automatically generating test questions, means for the user to check and edit the generated test questions via a terminal, means for analyzing the user's emotions using emotion recognition technology and adjusting the difficulty and content of the test questions, means for adjusting the generated educational strategy based on the student's emotions using emotion recognition technology, and means for inputting and uploading student achievement data, which greatly improves the work efficiency of teachers and enables appropriate educational support that takes emotions into consideration.

[0979] "Generative AI" is an AI technology that generates and predicts natural language based on various data.

[0980] "Educational data" refers to data that includes information related to education, such as teaching materials, textbooks, and learning materials.

[0981] "Test questions" are questions or exercises that are generated by analyzing educational data and are used to assess a learner's level of understanding.

[0982] "Device" refers to the device (PC, tablet, smartphone, etc.) used by the user to upload educational data and check and edit test questions.

[0983] "Emotion recognition technology" is a technology that detects and analyzes human emotions from facial expressions, tone of voice, body movements, etc.

[0984] "Performance Data" means data relating to a student's scores or performance on a test or assessment.

[0985] "Educational measures" are proposals and programs generated based on academic performance data and academic trends, with the aim of improving academic performance or providing support for specific subjects.

[0986] This invention aims to improve the efficiency of teachers' work and the quality of education in the field of education by combining an emotion engine to realize educational support that takes into account the emotions of students and teachers. This system is mainly composed of three entities: a server, a terminal, and a user.

[0987] Uploading teaching material data

[0988] The user (teacher) first selects educational data (e.g., digital textbooks in PDF or Word format) using their own device, such as a computer or tablet, and uploads it to the server. The device is provided with a dedicated interface through which the user can easily upload data.

[0989] Automatic test generation

[0990] When the server receives the uploaded educational data, it analyzes the data using text mining technology (for example, using Python's NLTK or spaCy). Based on the analysis results, it automatically generates test questions using a generative AI model (for example, OpenAI's GPT-4). These test questions are generated in a variety of formats, including multiple choice and free-form questions.

[0991] Check and edit test content

[0992] The generated test questions are provided to the user via the terminal. The user can review the test questions and add, delete, or modify questions as needed. The edited test questions are then saved back to the server.

[0993] Use of emotion engine

[0994] While the user is reviewing and editing the test questions, the server uses emotion recognition technology (such as Microsoft's Emotion API) to analyze the user's emotions from their facial expressions and tone of voice. Based on this emotional data, the server makes suggestions to optimize the difficulty and content of the test questions.

[0995] Entering and uploading grade data

[0996] After the test, the user inputs each student's performance data into the terminal and uploads it to the server. The performance data is stored in a database and used for later analysis.

[0997] Analysis of academic performance data and academic ability analysis

[0998] The server performs statistical analysis of the uploaded grade data using Python libraries such as Pandas and NumPy, providing a detailed understanding of students' strengths and weaknesses, as well as their academic ability trends.

[0999] Generate measures to improve academic performance

[1000] Based on the analysis of the grade data, the server uses a generative AI model to automatically generate educational strategies, including supplementary learning programs and home learning materials.

[1001] Adjusting academic achievement measures using an emotion engine

[1002] The server recognizes students' emotional data in real time and generates countermeasures aimed at improving motivation during individual instruction. These countermeasures include suggesting learning materials and methods that will stimulate students' interest in learning.

[1003] Providing and sharing countermeasures

[1004] The generated teaching strategies are sent to the device and can be viewed and shared by the user. Users can share these strategies with students and their parents to improve the quality of individualized instruction.

[1005] Prompt Sentence Examples

[1006] Below is an example of a prompt sentence to input to the generative AI model.

[1007] Automatic generation of test questions

[1008] "Create calculation and multiple choice questions for quizzes from a digital math textbook for fifth graders."

[1009] Proposal of countermeasures

[1010] "Based on Mr. A's grade data, please suggest a set of practice problems for fraction calculations and an effective home study program."

[1011] The introduction of this system will significantly reduce the workload of teachers and provide optimal educational support that takes emotions into consideration.

[1012] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1013] Step 1:

[1014] The user selects the teaching material data and uploads it to the server from the terminal.

[1015] Input: The user selects the teaching material data (PDF, Word document, etc.) in the device interface.

[1016] Specific operation: The user selects the teaching material data using the file selection dialog on their computer or tablet.

[1017] Data processing: The terminal converts the selected file into binary data and creates an HTTP request.

[1018] Output: The teaching material data is uploaded to the server.

[1019] Step 2:

[1020] The server receives the training data and stores it in a database.

[1021] Input: Uploaded teaching material data file.

[1022] What happens: The server receives an HTTP request, saves the file in the specified directory on the file system, and records the metadata (file name, upload date, etc.) in a database.

[1023] Data calculation: The server calculates the hash value of the file and verifies the integrity of the data.

[1024] Output: The teaching material data and its metadata are saved in the server's file system and database.

[1025] Step 3:

[1026] The server analyzes the uploaded teaching material data and automatically generates test questions using a generation AI.

[1027] Input: Saved teaching material data file.

[1028] Specific operation: The server uses text mining technology (libraries such as NLTK and spaCy) to analyze the teaching material data into text.

[1029] Data processing: Preprocessing the generated text data and inputting the analysis results into the generative AI model. Creating prompt sentences and sending them to the generative AI model.

[1030] Output: Auto-generated test questions as responses from the generative AI model.

[1031] Step 4:

[1032] The terminal displays the generated test questions to the user.

[1033] Input: Auto-generated test questions.

[1034] Specific operation: Generates a UI (user interface) for the device to display the test question data received from the server.

[1035] Output: A list of test questions that the user can view on their device.

[1036] Step 5:

[1037] Users review and edit test questions.

[1038] Input: Test questions displayed on the terminal.

[1039] Specific operation: The user checks the test questions through the interface, and deletes, adds, or modifies questions as needed. The edits are then sent from the device to the server.

[1040] Output: The edited test question.

[1041] Step 6:

[1042] The server saves the edited test questions.

[1043] Input: Edited test question data.

[1044] Specific operation: The server reflects the received edited data on the original test question set and saves it in the database.

[1045] Output: The most recent saved test question set.

[1046] Step 7:

[1047] The server uses emotion recognition technology to analyze the user's emotions and adjust the difficulty and content of the test questions.

[1048] Input: User's facial expression and voice data.

[1049] Specific operation: The server calls the emotion recognition API and obtains the analysis results of facial expressions and voice.

[1050] Data Computation: Analyzes emotional data and generates suggestions to optimize the difficulty and format of test questions based on the user's emotional state.

[1051] Output: Suggested adjustments to test questions based on sentiment analysis.

[1052] Step 8:

[1053] The user inputs the student's grade data into the terminal and uploads it to the server.

[1054] Input: Performance data entered by the user into the device.

[1055] Specific operation: The user uses the terminal interface to input the performance results for each student.

[1056] Data processing: The terminal organizes the entered performance data and sends it to the server.

[1057] Output: The grade data is uploaded to the server.

[1058] Step 9:

[1059] The server analyzes the grade data and identifies students' academic trends.

[1060] Input: Uploaded grade data.

[1061] Specific operation: The server performs statistical analysis on the performance data using Pandas and NumPy.

[1062] Data calculation: Analyze patterns of strong and weak subjects, as well as academic performance trends.

[1063] Output: Student academic performance trend data as the analysis result.

[1064] Step 10:

[1065] The server automatically generates educational strategies based on the results of the academic ability analysis.

[1066] Input: Student academic performance trend data.

[1067] How it works: The server uses the generative AI model to create optimal educational strategies for each student.

[1068] Data calculation: Educational measures include automatically generating supplementary programs and home learning materials.

[1069] Output: Automatically generated educational strategies.

[1070] Step 11:

[1071] The server uses emotion recognition technology to recognize students' emotions and generates countermeasures to improve motivation during individual instruction.

[1072] Input: Student emotion data.

[1073] Specific operation: The server calls the emotion recognition API in real time to obtain the student's emotions.

[1074] Data calculation: Optimizing individualized instruction methods to improve motivation based on emotional data.

[1075] Output: Optimized educational strategies for improving motivation.

[1076] Step 12:

[1077] The generated educational strategy plan is sent to the terminal and can be viewed and shared by the user.

[1078] Input: Optimized educational strategy.

[1079] Specific operation: The server sends the countermeasure proposal to the user's device, which provides an interface to display the countermeasure proposal.

[1080] Output: The educational plan displayed on the device. The user can view the plan and share it with students and parents.

[1081] (Application example 2)

[1082] 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."

[1083] Conventional factory robot-based work support systems are unable to generate work instructions or provide guidance that takes into account the emotions of workers, making it difficult to implement efficient and flexible work improvement. Furthermore, instructions that ignore the emotions and motivation of workers can lead to reduced work efficiency and inconsistent quality. The present invention aims to solve these problems by providing optimal work instructions and work improvement proposals that take into account the emotions of workers.

[1084] 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.

[1085] In this invention, the server includes means for analyzing uploaded information using generative artificial intelligence and automatically generating work instructions, means for workers to confirm and edit the work instructions generated through the device, means for inputting and uploading work results, means for recognizing the emotions of workers using an emotion engine and adjusting the difficulty and content of the work instructions, and means for sending the generated work improvement proposals to the device so that workers can view and share them. This makes it possible to provide flexible and efficient work instructions and work improvement proposals that take emotions into consideration.

[1086] "Uploading" is the act of sending and storing information from one device to another computer system, such as a server or cloud.

[1087] "Analysis" is the act of examining data or information in detail to clarify its structure, content, and meaning.

[1088] "Automatic generation" refers to the use of artificial intelligence or specific algorithms to generate the necessary information or data without manual intervention.

[1089] "Work instructions" are information used to communicate specific work content and procedures to workers.

[1090] An "apparatus" is a mechanical or electronic device used for a specific purpose.

[1091] "Verification" is the process of verifying whether the generated data or instructions are correct.

[1092] "Editing" is the act of modifying or changing generated data or instructions.

[1093] "Work results" are the results or performance of the work performed by a worker.

[1094] The "Emotion Engine" is an artificial intelligence technology that recognizes and analyzes emotions from facial expressions, voice, actions, etc.

[1095] "Cognition" is the ability or act of understanding and identifying specific information.

[1096] "Difficulty" refers to the degree of difficulty in accomplishing a task or problem.

[1097] "Content" refers to the specific content of information or data.

[1098] "Adjustment" is the act of changing content or standards to meet specific goals or conditions.

[1099] A "business improvement proposal" is a specific method or means proposed to improve the efficiency or quality of work or operations.

[1100] "Viewing" is the act of checking and looking at the generated data and information.

[1101] "Sharing" is the act of using specific information or data together with other users.

[1102] The present invention relates to a work support system for factory robots, and by combining an emotion engine and generative artificial intelligence, it provides optimal work instructions and work improvement proposals according to the emotions of workers. Specific embodiments are described below.

[1103] System Configuration

[1104] 1. Hardware

[1105] Server: A high-performance computer that processes data analysis, generative artificial intelligence, and emotion engines.

[1106] Devices: Computers, tablets, and smartphones used by workers and managers.

[1107] Camera device: A camera for recognizing the facial expressions of workers.

[1108] 2. Software

[1109] Python: Used as a programming language.

[1110] OpenCV: An image processing library used for facial expression recognition.

[1111] TextBlob: A library for text parsing and generation.

[1112] scikit-learn: A machine learning library for sentiment classification.

[1113] Operation process

[1114] 1. Uploading Information

[1115] The administrator uploads the work procedure data to the server, which then analyzes the data and uses it as the basis for work instructions.

[1116] 2. Automatic generation of work instructions

[1117] The server analyzes the uploaded work procedure data and automatically generates work instructions using a generative AI model, which include specific work content and procedures.

[1118] 3. Review and edit work instructions

[1119] The worker checks the generated work instructions through their terminal and edits them as necessary. At this time, the emotion engine analyzes the worker's facial expressions and tone of voice to suggest the most appropriate instructions and level of difficulty.

[1120] 4. Enter and upload labor results

[1121] After completing their work, workers enter their work results into a terminal and upload them to the server, which then obtains the information necessary for the next data analysis.

[1122] 5. Use of Emotion Engine

[1123] The server uses an emotion engine to recognize the worker's emotions in real time and adjusts optimal work instructions and business improvement proposals based on the worker's motivation and emotions.

[1124] 6. Analyzing work results and generating work improvement proposals

[1125] The server analyzes the uploaded work results and evaluates the worker's work efficiency and quality. Based on this, it generates business improvement proposals using a generative AI model.

[1126] 7. Providing and sharing business improvement proposals

[1127] The server sends the generated business improvement proposals to the terminals, where workers and managers can view and share them, thereby achieving efficient and high-quality work.

[1128] Specific examples

[1129] 1. Facial Recognition Prompts

[1130] Example: image_path = 'worker_face.jpg'; emotions = recognize_emotion(image_path)

[1131] 2. Prompt for work order generation

[1132] Example: template = "Generate instructions for"; data = {"task": "assemble", "parts": ["screw", "nut"]}; work_instruction = generate_work_instruction(template, data)

[1133] This will enable flexible and efficient work instructions and business improvement proposals that take emotions into account.In addition, the use of specific devices and software makes the system realistic and practical to implement.

[1134] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1135] Step 1:

[1136] The user uploads the work procedure data to the server via the terminal.

[1137] Input: Work procedure data (e.g., assembly instructions)

[1138] Data processing and calculation: The server stores the uploaded data and analyzes its contents.

[1139] Output: Analyzed work procedure data

[1140] Step 2:

[1141] The server uses the analyzed work procedure data to automatically generate work instructions using a generative artificial intelligence model.

[1142] Input: Parsed work procedure data

[1143] Data processing and calculation: The generative artificial intelligence model understands the content of the work procedures and generates specific work instructions.

[1144] Output: Generated work instructions (e.g., specific assembly steps)

[1145] Step 3:

[1146] The user can check the work instructions generated from the server through the terminal and edit them as necessary.

[1147] Input: Generated Work Order

[1148] Data processing and calculation: Users can check the instructions on the terminal and make corrections or additions, for example, by adding details to the work procedure or changing the order of the steps.

[1149] Output: Reviewed and edited work instructions

[1150] Step 4:

[1151] The server uses an emotion engine to recognize emotions while the user is editing the work instructions and suggests editing content and difficulty.

[1152] Input: User's facial expression data and voice data

[1153] Data processing and calculation: The emotion engine analyzes facial expression and voice data to evaluate the user's emotional state. Based on this, it makes suggestions regarding editing content and difficulty.

[1154] Output: Sentiment analysis results and suggested edits and difficulty changes

[1155] Step 5:

[1156] After the user completes the work, he / she inputs the results of the work through the terminal and uploads them to the server.

[1157] Input: Work result data (e.g., work completion report)

[1158] Data processing and calculation: Labor outcome data is collected and stored on a server for future analysis.

[1159] Output: Saved labor result data

[1160] Step 6:

[1161] The server analyzes the uploaded work result data and evaluates work efficiency and quality.

[1162] Input: Saved labor result data

[1163] Data processing and calculation: Analyzes work result data and generates statistical information on work efficiency and quality, such as the time required for work and error rate.

[1164] Output: Evaluation results of work efficiency and quality

[1165] Step 7:

[1166] Based on the evaluation results, the server generates business improvement proposals using a generative artificial intelligence model.

[1167] Input: Work efficiency and quality evaluation results

[1168] Data processing and calculation: The generative AI model analyzes the evaluation results and generates specific improvement proposals for improving efficiency and quality.

[1169] Output: Generated business improvement proposals (e.g., proposed changes to work procedures)

[1170] Step 8:

[1171] The server sends the generated business improvement proposals to the terminal, where the user can view and share them.

[1172] Input: Generated business improvement proposal

[1173] Data processing and calculation: The generated business improvement proposals are sent to the user's device so that they can be viewed and shared.

[1174] Output: Business improvement proposals displayed on the user's device

[1175] By following these steps, the server, terminal, and user interact with each other to provide flexible and efficient work instructions and business improvement proposals that respond to emotions.

[1176] 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.

[1177] 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.

[1178] 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.

[1179] [Third embodiment]

[1180] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1181] 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.

[1182] 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).

[1183] 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.

[1184] 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.

[1185] 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).

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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."

[1192] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education.

[1193] System configuration and functions

[1194] 1. Uploading teaching material data

[1195] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[1196] Users select teaching material data, such as digital textbooks and slides they have created, using a computer or tablet and upload it to the system. This uploaded data is stored on the server and used for subsequent processing.

[1197] 2. Automatic generation of test creation

[1198] The server analyzes the educational data and automatically generates test questions using generative AI.

[1199] The server analyzes the uploaded educational data. Text mining technology is used for the analysis to extract important keywords and concepts. Based on these extraction results, the generative AI automatically generates appropriate test questions. The generated test questions come in multiple question formats (multiple choice, fill-in-the-blank, written, etc.).

[1200] 3. Check and edit the test content

[1201] User-generated test questions can be viewed and edited on the device

[1202] The user checks the automatically generated test questions on their device, checks the appropriateness of the questions, and makes any necessary modifications, such as adding or deleting questions or adjusting the difficulty level. After editing, the test questions are uploaded back to the server and saved in the system.

[1203] 4. Enter and upload grade data

[1204] The user enters the student's test results into the terminal and uploads them to the server.

[1205] After the test, the user enters the student's answers into the device and uploads the results data to the system. The results data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions. This data is also stored on the server.

[1206] 5. Analysis of academic performance data and academic ability analysis

[1207] The server analyzes the grade data and identifies the student's academic ability trends.

[1208] The server analyzes the uploaded grade data, using statistical analysis to identify each student's strengths and weaknesses and overall academic trends. If necessary, the same analysis can be performed for specific classes or groups selected by the teacher.

[1209] 6. Generating measures to improve academic ability

[1210] The server automatically generates educational strategies based on the results of the academic ability analysis.

[1211] Based on the analysis results, the server generates optimal educational strategies for each student, including remedial programs, additional learning materials, and self-study resources. For example, a student who struggles with fraction calculations in math might be provided with practice problems specific to that area.

[1212] 7. Providing and sharing countermeasures

[1213] The server sends the generated educational plan to the device, where the user can view and share it.

[1214] The server sends the generated educational strategies to the user's device. The user can review the strategies on their device and share them with students and parents as needed. This is expected to improve the accuracy of individualized instruction and lead to improved academic performance for students.

[1215] Specific examples

[1216] Below are some specific examples of how this system can be used.

[1217] Uploading teaching material data

[1218] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[1219] Auto-generated test creation

[1220] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[1221] Check and edit test content

[1222] The teacher checks the generated test questions, adjusts the difficulty of some questions, and saves them again on the server.

[1223] Entering and uploading grade data

[1224] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[1225] Analysis of academic performance data and academic ability analysis

[1226] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[1227] Generate measures to improve academic performance

[1228] The server generates a set of fraction calculation practice problems and a home study program for Mr. A.

[1229] Providing and sharing countermeasures

[1230] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[1231] The introduction of this system will significantly reduce the burden on teachers and improve the quality of education.

[1232] The processing flow will be explained below.

[1233] Step 1:

[1234] The user selects the teaching material data

[1235] The user (teacher) uses a computer or tablet to select the target digital teaching material data (e.g., textbooks, slides, supplementary materials, etc.) in a file browser.

[1236] Step 2:

[1237] Upload the teaching material data selected by the user from the device to the server.

[1238] The user clicks a dedicated upload button to upload the selected teaching material data to the system. The teaching material data is transferred to the server via the Internet and stored on the server.

[1239] Step 3:

[1240] The server analyzes the uploaded educational data

[1241] The server analyzes the stored learning material data and uses text mining technology to extract important keywords and concepts from the text content of the learning material. Natural language processing technology is also utilized in this process.

[1242] Step 4:

[1243] The server automatically generates test questions using AI

[1244] The server uses generative AI to create test questions based on the extracted keywords and concepts. The generated test questions come in multiple formats, including multiple choice, fill-in-the-blank, and free-form questions.

[1245] Step 5:

[1246] User can view generated tests on device

[1247] The user checks the list of test questions automatically generated by the server on their device, checking the content, format, and difficulty of each question one by one.

[1248] Step 6:

[1249] User-generated test editing

[1250] Users can review the test questions and make corrections, additions, or deletions as needed. For example, they can change the question format or adjust the difficulty level. Once edited, the test is uploaded back to the server and saved.

[1251] Step 7:

[1252] The user enters the student's test results into the terminal.

[1253] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[1254] Step 8:

[1255] Upload the grade data entered by the user to the server

[1256] Once the data has been entered, the user uploads it to the system, where it is stored on the server and used for subsequent analysis.

[1257] Step 9:

[1258] The server analyzes the performance data

[1259] The server analyzes the stored grade data and uses statistical analysis tools to identify students' strengths and weaknesses, as well as academic trends.

[1260] Step 10:

[1261] The server generates the academic performance report.

[1262] The server then generates an academic performance report for each student based on the analysis results, including graphs, charts, and commentary based on the analysis results.

[1263] Step 11:

[1264] The server generates educational strategies.

[1265] Based on the generated academic achievement report, the server automatically generates educational strategies tailored to each student, including areas to strengthen in class and materials for home study.

[1266] Step 12:

[1267] The server generates an academic performance report and sends it to the device.

[1268] The server sends the generated report and countermeasures to the user's device, where the user can review it and share it with students and parents as needed.

[1269] Through these steps, the system can significantly improve the efficiency of teachers' work and improve the quality of education.

[1270] Example 1

[1271] 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."

[1272] In the field of education, teachers have a wide range of tasks, which creates a heavy workload. Furthermore, because they are required to deliver education efficiently while maintaining a certain level of quality, systems are needed that reduce the burden on teachers while improving the quality of education. In particular, tasks such as creating teaching materials, creating tests, and managing student grades are labor-intensive, and technology is needed to perform these tasks efficiently.

[1273] 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.

[1274] In this invention, the server includes means for analyzing uploaded educational data using a generation AI and automatically generating test questions, means for users to review and edit the generated test questions via a terminal, means for inputting and uploading student achievement data, means for analyzing the achievement data and identifying students' academic ability trends, means for automatically generating educational strategies based on the results of the academic ability analysis, and means for sending the generated educational strategies to the terminal so that users can view and share them. This enables efficient management and analysis of educational data, significantly reducing the workload of teachers and improving the quality of education.

[1275] "Generative AI" is an artificial intelligence technology that automatically generates new information and solutions based on uploaded data.

[1276] "Educational data" refers to information and materials related to education, such as digital textbooks and created slides.

[1277] "Test questions" are questions that are asked to assess a student's understanding and knowledge.

[1278] "Academic performance data" refers to data such as test scores and evaluation results obtained by students.

[1279] "Academic ability trends" refers to trends that indicate a student's strengths and weaknesses in subjects and their learning progress.

[1280] "Educational measures" are proposals for specific teaching methods and teaching materials to improve students' academic abilities.

[1281] A "terminal" is a device such as a computer or tablet that is directly operated by a user.

[1282] "Users" refer to teachers and other educational personnel who use this system.

[1283] A "server" is a computer system that provides services and resources on a computer network.

[1284] "Text mining" is an analytical technique for extracting useful information from natural language data.

[1285] "Statistical analysis" is an analytical method that aims to obtain information by analyzing data using statistical techniques.

[1286] "Visualization tools" are software and techniques for visually displaying data.

[1287] MODE FOR CARRYING OUT THE INVENTION

[1288] This invention is a system aimed at improving the work efficiency of teachers and the quality of education in the field of education. This system has the functions of analyzing uploaded educational data using generative AI and automatically generating test questions, allowing teachers to review and edit the generated test questions, inputting and uploading grade data, and automatically generating educational countermeasures based on student grade data to grasp academic ability trends.

[1289] Hardware and software used

[1290] Hardware

[1291] Server: Stores and analyzes educational data, and generates test questions and educational strategies.

[1292] Terminal: A device (e.g., PC, tablet) that teachers use to upload teaching material data, check and edit test questions, and enter and upload grade data.

[1293] software

[1294] Generative AI: Artificial intelligence that analyzes teaching material data and generates test questions and educational strategies (e.g., GPT-3, BERT).

[1295] Text mining technology: Natural language processing engines (e.g., SpaCy, NLTK) for extracting important keywords and concepts from teaching material data.

[1296] Data analysis tools: Software for statistical analysis of performance data and identifying trends in student achievement (e.g., Pandas, NumPy).

[1297] Visualization tools: Tools for visually displaying the results of performance data analysis (e.g., Matplotlib, Seaborn).

[1298] Explanation of program processing

[1299] Uploading teaching material data

[1300] A user (teacher) uses a PC or tablet to select educational data (digital textbooks, created slides, etc.) and uploads them to the server from the device. The server saves the received data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[1301] Auto-generated test creation

[1302] The server analyzes the uploaded educational data using text mining technology to extract important keywords and concepts. Based on the extracted keywords and concepts, the generation AI generates appropriate test questions (multiple choice, fill-in-the-blank, essay, etc.). Examples of generated prompts include:

[1303] "Read the following text and select the appropriate option. Text: 『○○』"

[1304] Check and edit test content

[1305] The user checks the test questions generated on the device and makes corrections as necessary. The corrected test questions are then uploaded back to the server and saved.

[1306] Entering and uploading grade data

[1307] After the test, the user enters the student's answers into the device and uploads the results to the server, which then stores the received data in a database.

[1308] Analysis of academic performance data and academic ability analysis

[1309] The server analyzes the uploaded grade data using statistical analysis tools to identify each student's academic performance trends, and the analysis results are displayed visually using visualization tools.

[1310] Generate measures to improve academic performance

[1311] The server generates individualized educational strategies based on the results of the academic ability analysis. These strategies include remedial programs, additional learning materials, and self-study resources. Examples of generated prompts include:

[1312] "For the next student, please suggest the following strategies for those struggling with fractions in math:"

[1313] Providing and sharing countermeasures

[1314] The server sends the generated educational countermeasures plan to the user's device, where the user confirms it and then shares it with students and parents.The countermeasures plan is distributed via an educational portal site or email system, allowing students and parents to access it.

[1315] This will enable the efficient management and analysis of educational data, which is expected to significantly reduce the workload of teachers while improving the quality of education.

[1316] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1317] System program processing flow

[1318] Step 1: Upload the teaching material data

[1319] Input: User-selected teaching material data (file format: PDF, PPT, etc.)

[1320] Output: Learning material data and file metadata stored on the server

[1321] Specific behavior:

[1322] Users select the teaching material data on their computers or tablets.

[1323] The terminal gets the file path through a file selection dialog.

[1324] The terminal sends the selected teaching material data to the server using an HTTP request.

[1325] The server stores the received teaching material data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[1326] Step 2: Analyzing Educational Data

[1327] Input: Teaching material data stored on the server

[1328] Output: Extracted terms and concepts

[1329] Specific behavior:

[1330] The server reads the teaching material data and analyzes it using text mining technology.

[1331] The server uses a natural language processing engine (e.g. SpaCy, NLTK) to extract important keywords and concepts.

[1332] The server temporarily stores the extracted keywords and concepts.

[1333] Step 3: Generate test questions

[1334] Input: Extracted keywords and concepts

[1335] Output: Auto-generated test questions

[1336] Specific behavior:

[1337] The server uses generative AI (e.g., GPT-3, BERT) to generate test questions based on the extracted keywords and concepts.

[1338] The server sets up a generation prompt and sends a request to the generative AI model.

[1339] Example prompt: "Generate three multiple choice questions using the following keywords: fractions, math, 5th grade"

[1340] The server formats and saves the test questions received from the generation AI.

[1341] Step 4: Review and edit the test content

[1342] Input: Auto-generated test questions

[1343] Output: Test questions corrected by the user

[1344] Specific behavior:

[1345] The server sends the generated test questions to the device.

[1346] The user checks the test questions generated on the terminal.

[1347] The user uses the editing screen of the web application to modify the test questions (add, delete, adjust the difficulty level, etc.).

[1348] The device uploads the modified test questions to the server.

[1349] Step 5: Enter and upload grade data

[1350] Input: Student answer results entered by the user

[1351] Output: Achievement data stored on the server

[1352] Specific behavior:

[1353] After the user takes the test, the student's answers are entered into the terminal.

[1354] The terminal uses a web application form to input each student's grade data.

[1355] The terminal sends the entered score data to the server using an HTTP request.

[1356] The server stores the received results data in a database.

[1357] Step 6: Analysis of academic performance data and academic achievement analysis

[1358] Input: Achievement data stored on the server

[1359] Output: Academic performance trend report for each student

[1360] Specific behavior:

[1361] The server reads the performance data and analyzes it using statistical analysis tools (e.g., Pandas, NumPy).

[1362] The server calculates each student's correct answer rate, average score, distribution, etc.

[1363] The server uses visualization tools (e.g., Matplotlib, Seaborn) to graph the results and generate academic performance trend reports.

[1364] Step 7: Generate strategies to improve academic performance

[1365] Input: Academic ability analysis results

[1366] Output: Automatically generated educational strategies

[1367] Specific behavior:

[1368] The server uses generative AI to generate educational strategy proposals based on the results of the academic ability analysis.

[1369] The server sets up a generation prompt and sends a request to the generative AI model.

[1370] Example prompt: "For the following student, please suggest the following strategies for solving problems with fractions in math:"

[1371] The server formats and saves the generated educational strategies.

[1372] Step 8: Provide and share countermeasures

[1373] Input: Automatically generated educational plan

[1374] Output: Solutions provided to users, students, and parents

[1375] Specific behavior:

[1376] The server sends the generated educational strategy plan to the user's terminal.

[1377] The user checks the educational measures on the device.

[1378] Users share the countermeasures with students and parents by distributing them via educational portal sites and email systems, making them viewable and downloadable.

[1379] (Application example 1)

[1380] 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."

[1381] In the field of education, teachers must take measures to improve the academic ability of each student while juggling a wide range of tasks. However, the series of tasks, such as preparing teaching materials, creating tests, managing grades, and creating countermeasures based on the results, are enormous and require time and effort. For this reason, a system is needed to carry out these tasks efficiently and effectively. In addition, to take effective educational measures, teachers need the ability to check and customize educational content in real time.

[1382] 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.

[1383] In this invention, the server includes means for analyzing uploaded educational data using a generation artificial intelligence and automatically generating test questions, means for searching and selecting teaching materials in a virtual space, means for a user to check and edit the generated test questions, means for previewing and editing educational strategies in real time through a terminal, means for inputting and uploading student achievement data, and means for previewing and editing educational strategies in the virtual space. This allows teachers to efficiently obtain the necessary teaching materials and strategies and customize educational content in real time.

[1384] "Generative AI" is an AI technology that has the ability to analyze uploaded educational data and automatically generate test questions and educational strategies.

[1385] "Educational data" is a general term for digital data related to education, such as textbooks, slides, and teaching materials.

[1386] A "virtual space" is a virtual environment constructed using virtual reality technology that allows users to visually and experientially explore and select educational materials.

[1387] "Device" is a general term for electronic devices such as computers, smartphones, and tablets that users use to check, edit, and upload educational data.

[1388] "Test questions" are questions to evaluate learning content that are automatically generated by generative artificial intelligence based on educational data.

[1389] "Academic performance data" refers to data that evaluates a student's learning outcomes and includes grade information based on the results.

[1390] "Educational strategy" is a general term for specific educational plans and supplementary materials that are generated by analyzing academic performance data in order to improve each student's academic ability.

[1391] "Real-time preview" is a function that allows users to instantly check educational data and countermeasures on their devices or in a virtual space.

[1392] "Editing" refers to the act of the user changing or modifying the content of the generated test questions or educational strategies.

[1393] This invention is a system aimed at improving work efficiency and the quality of education in the field of education. This system has the functions of allowing teachers to upload educational data, automatically generating test questions using generative artificial intelligence, and exploring teaching materials in a virtual space, previewing and editing them in real time. The specific configuration and processing required to realize this system are described below.

[1394] 1. Uploading teaching material data

[1395] Users upload educational material data, such as digital textbooks and slides they have created, from their devices (PCs or tablets) to the server. The uploaded data is stored on the server and used for subsequent processing.

[1396] 2. Automatic generation of test creation

[1397] The server analyzes the uploaded educational data. This analysis uses text mining technology implemented in Python to extract important keywords and concepts. Based on the extracted results, a generative artificial intelligence model using TensorFlow and PyTorch automatically generates appropriate test questions. The generated test questions include multiple choice, fill-in-the-blank, and essay questions.

[1398] 3. Explore and preview learning materials in a virtual space

[1399] Users put on a VR headset (such as Oculus Quest 2) and enter a virtual space built with Unity or Unreal Engine. In the virtual space, users can explore and select learning materials and preview them in real time. The selected learning materials include test questions and supplementary materials automatically generated by the system.

[1400] 4. Check and edit the test content

[1401] Users can check the generated test questions on their device and edit them as needed. They can check the appropriateness of the questions with a real-time preview and add, delete, or adjust the difficulty level. After editing, the test questions are saved back to the server.

[1402] 5. Enter and upload grade data

[1403] After taking the test, the user enters the student's performance data into the device and uploads it to the server. The performance data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions, and is saved on the server.

[1404] 6. Analysis of academic performance data and academic ability analysis

[1405] The server analyzes the uploaded grade data, using Python-based statistical analysis algorithms to identify each student's strengths and weaknesses, as well as overall academic performance trends.

[1406] 7. Generating measures to improve academic ability

[1407] Based on the analysis of the grade data, the server generates optimal educational strategies, including supplementary learning programs, additional teaching materials, and self-study resources.

[1408] 8. Providing and sharing countermeasures

[1409] The generated educational strategies are sent from the server to the user's device, where the user can view and share them, improving the accuracy of individualized instruction.

[1410] Examples of specific examples and prompts

[1411] Below are some specific examples of prompt sentences to input into the generative AI model.

[1412] "Generate multiple-choice quiz questions based on 5th grade math materials."

[1413] "Based on the above teaching materials, please generate a supplementary workbook that specializes in fraction calculations."

[1414] This allows teachers to carry out educational activities effectively and efficiently.

[1415] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1416] Step 1:

[1417] Users use their devices to upload educational material data (digital textbooks, created slides, etc.) to the server.

[1418] Input: Teaching material data

[1419] Output: Teaching material data saved on the server

[1420] Specific operation: The user uses a PC or tablet to select teaching material data from the system interface and clicks the "Upload" button.

[1421] Step 2:

[1422] The server analyzes the uploaded educational data and extracts important keywords and concepts.

[1423] Input: Teaching material data stored on the server

[1424] Output: Extracted keywords and concepts

[1425] Specific operation: The server runs a text mining algorithm implemented in Python to analyze the teaching material data, extracting keywords and concepts and storing them in a database.

[1426] Step 3:

[1427] The server automatically generates test questions using a generative AI model based on the extracted keywords and concepts.

[1428] Input: Extracted keywords and concepts

[1429] Output: Auto-generated test questions

[1430] Specific operation: The server feeds input data (extracted keywords and concepts) into a generative AI model built with TensorFlow or PyTorch, and generates test questions.

[1431] Step 4:

[1432] The user uses a VR headset to enter a teaching material shop in a virtual space and search for and select teaching material data.

[1433] Input: Teaching materials in virtual space

[1434] Output: Selected teaching material data

[1435] Specific operations: The user puts on a VR headset such as Oculus Quest 2 and moves around a virtual space built with Unity or Unreal Engine to find, pick up and select educational materials.

[1436] Step 5:

[1437] The user reviews and edits the automatically generated test questions on the device.

[1438] Input: Auto-generated test questions

[1439] Output: Test questions edited by the user

[1440] Specific operation: The user views the test questions through the device, and adds, deletes, and adjusts the difficulty of questions as needed. The edited content is saved back to the server.

[1441] Step 6:

[1442] After the user takes the test, the student's performance data is entered into the terminal and uploaded to the server.

[1443] Input: Student answer results

[1444] Output: Grade data saved on the server

[1445] Specific operation: The user enters the student's answer results into the grade management system and clicks the "Upload" button.

[1446] Step 7:

[1447] The server analyzes the grade data and identifies each student's academic ability trends.

[1448] Input: Student performance data

[1449] Output: Academic trend report

[1450] Specific operation: The server uses Python statistical analysis algorithms to analyze the grade data, identify strong and weak subjects, and compile trends into a report.

[1451] Step 8:

[1452] The server generates educational strategies for each student based on their academic ability trends.

[1453] Input: Academic Trend Report

[1454] Output: Educational measures

[1455] Specific operation: The server uses the generated AI model to generate supplementary learning programs and additional teaching materials tailored to specific academic trends.

[1456] Step 9:

[1457] The server sends the generated educational strategy plan to the user's device, where the user can review and share it.

[1458] Input: Educational measures proposal

[1459] Output: Educational measures displayed on the user's device

[1460] Specific operation: The server sends the proposed countermeasures to the user's device, and the user reviews the contents and shares them with students and parents as necessary.

[1461] 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.

[1462] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education, and by combining it with an emotion engine, realizes educational support that takes into account the emotions of students and teachers.

[1463] System configuration and functions

[1464] 1. Uploading teaching material data

[1465] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[1466] Users select and upload teaching material data using a computer or tablet, and this data is stored on a server for later analysis and test creation.

[1467] 2. Automatic generation of test creation

[1468] The server analyzes the educational data and automatically generates test questions using generative AI.

[1469] The server analyzes the uploaded educational data using text mining technology, and the AI ​​automatically generates appropriate test questions, ranging from multiple choice questions to free-form questions.

[1470] 3. Check and edit the test content

[1471] User-generated tests can be viewed and edited on the device

[1472] Users can view the test questions generated on their devices, add, delete, or modify questions, and the edited test is saved back to the server.

[1473] 4. Use of Emotion Engine

[1474] The server uses an emotion engine to recognize the user's emotions and adjust the difficulty and content of the test questions.

[1475] When a teacher is reviewing and editing test questions, the emotion engine analyzes the teacher's emotions from their facial expressions and tone of voice, optimizing the difficulty level and question format of the proposed content.

[1476] 5. Enter and upload grade data

[1477] The user enters the student's test results into the terminal and uploads them to the server.

[1478] After the test, the user enters the results data for each student into the terminal and uploads it. This data is also saved on the server.

[1479] 6. Analysis of academic performance data and academic ability analysis

[1480] The server analyzes the grade data and identifies the student's academic ability trends.

[1481] Based on the uploaded grade data, the server performs statistical analysis of students' strong and weak subjects and academic trends.

[1482] 7. Generating measures to improve academic ability

[1483] The server automatically generates educational strategies based on the results of the academic ability analysis.

[1484] Based on the analysis results, the server generates optimal educational strategies for each student, including supplementary learning programs and home study materials.

[1485] 8. Adjusting academic achievement strategies using an emotion engine

[1486] The server uses an emotion engine to recognize students' emotions and generate strategies to improve motivation for individual instruction.

[1487] The server recognizes students' emotions in real time and generates teaching guidelines and countermeasures that take their motivation into account.

[1488] 9. Providing and sharing countermeasures

[1489] The server sends the generated educational plan to the device, where the user can view and share it.

[1490] The server sends the generated countermeasures to the teacher's device, where the user can check the countermeasures and share them with students and parents to improve the quality of individual instruction.

[1491] Specific examples

[1492] Below are some specific examples of how this system can be used.

[1493] Uploading teaching material data

[1494] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[1495] Auto-generated test creation

[1496] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[1497] Check and edit test content

[1498] The teacher reviews the generated test questions, adjusts the difficulty of some questions, and saves them back on the server. At this time, the emotion engine analyzes the teacher's emotions and automatically suggests the difficulty level of the test questions.

[1499] Entering and uploading grade data

[1500] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[1501] Analysis of academic performance data and academic ability analysis

[1502] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[1503] Generation of measures to improve academic performance and adjustment using an emotion engine

[1504] The server generates a set of fraction calculation practice problems and a home study program for Mr. A. Furthermore, the emotion engine recognizes Mr. A's emotions and suggests teaching methods to improve his motivation.

[1505] Providing and sharing countermeasures

[1506] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[1507] The introduction of this system will significantly reduce the burden on teachers and further improve the quality of education by taking emotional factors into consideration.

[1508] The processing flow will be explained below.

[1509] Step 1:

[1510] The user selects the teaching material data

[1511] The user (teacher) uses a computer or tablet to select the target teaching material data (e.g., digital textbook, slides, supplementary materials) in a file browser.

[1512] Step 2:

[1513] Upload the teaching material data selected by the user from the device to the server.

[1514] The user clicks a button to upload the selected teaching material data to the system, which is then transferred to the server via the Internet and stored on the server.

[1515] Step 3:

[1516] The server analyzes the uploaded educational data

[1517] The server analyzes the stored teaching material data and uses text mining and natural language processing technologies to extract important keywords and concepts.

[1518] Step 4:

[1519] The server automatically generates test questions using AI

[1520] The server uses generative AI to automatically generate appropriate test questions based on the extracted keywords and concepts. The generated test questions come in a variety of formats, including multiple choice, fill-in-the-blank, and free-form questions.

[1521] Step 5:

[1522] User can view generated tests on device

[1523] The user checks the list of test questions automatically generated by the server on the terminal, checking the content, format, and difficulty of each question one by one.

[1524] Step 6:

[1525] User-generated test editing

[1526] Users can review the test questions and make corrections, additions, or deletions as necessary. For example, they can change the question format or adjust the difficulty level. Once edits are complete, the test is uploaded back to the server and saved.

[1527] Step 7:

[1528] Use an emotion engine to recognize user emotions and adjust test questions accordingly

[1529] While the user is editing the test content, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and if stress or confusion is recognized, the server makes suggestions to readjust the difficulty level or content of the questions.

[1530] Step 8:

[1531] The user enters the student's test results into the terminal.

[1532] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[1533] Step 9:

[1534] Upload the grade data entered by the user to the server

[1535] Once the user has completed entering the data, they upload it to the system, where it is stored on the server and used for subsequent analysis.

[1536] Step 10:

[1537] The server analyzes the grade data and identifies the student's academic ability trends.

[1538] The server analyzes the stored academic data using statistical analysis tools to display students' strengths and weaknesses, as well as their overall academic performance trends.

[1539] Step 11:

[1540] The server generates the academic performance report.

[1541] The server then generates an individual student performance report based on the analysis results, which includes graphs, charts, specific data, and explanations based on the analysis results.

[1542] Step 12:

[1543] The server generates educational strategies.

[1544] Based on the generated academic achievement report, the server generates an optimal educational plan for each student, including specific supplementary learning programs, home study materials, and self-study resources.

[1545] Step 13:

[1546] Use an emotion engine to recognize student emotions and generate motivational strategies for individualized instruction

[1547] The server recognizes students' real-time emotional data and generates strategies that reflect their emotional state during learning. For example, if a student is feeling stressed, it suggests starting with easy problems.

[1548] Step 14:

[1549] The server generates an academic performance report and sends it to the device.

[1550] The server sends the generated academic performance report and countermeasures to the user's device, where the user can check it and share it with students and parents.

[1551] Through these steps, the system will significantly streamline teachers' work and, by taking emotional factors into account, will enable more effective individualized instruction and improved educational quality.

[1552] Example 2

[1553] 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."

[1554] In order to reduce the workload of teachers and improve the quality of education, it is necessary to streamline various tasks, such as creating teaching materials, managing student grades, and proposing individual educational measures. There is also a need for educational support that takes into account the emotions of students and teachers, but existing systems are insufficiently optimized to reflect emotions. Therefore, there is a need for a system that utilizes emotion recognition technology to provide more effective educational support.

[1555] 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.

[1556] In this invention, the server includes means for analyzing uploaded educational data using generative artificial intelligence and automatically generating test questions, means for the user to check and edit the generated test questions via a terminal, means for analyzing the user's emotions using emotion recognition technology and adjusting the difficulty and content of the test questions, means for adjusting the generated educational strategy based on the student's emotions using emotion recognition technology, and means for inputting and uploading student achievement data, which greatly improves the work efficiency of teachers and enables appropriate educational support that takes emotions into consideration.

[1557] "Generative AI" is an AI technology that generates and predicts natural language based on various data.

[1558] "Educational data" refers to data that includes information related to education, such as teaching materials, textbooks, and learning materials.

[1559] "Test questions" are questions or exercises that are generated by analyzing educational data and are used to assess a learner's level of understanding.

[1560] "Device" refers to the device (PC, tablet, smartphone, etc.) used by the user to upload educational data and check and edit test questions.

[1561] "Emotion recognition technology" is a technology that detects and analyzes human emotions from facial expressions, tone of voice, body movements, etc.

[1562] "Performance Data" means data relating to a student's scores or performance on a test or assessment.

[1563] "Educational measures" are proposals and programs generated based on academic performance data and academic trends, with the aim of improving academic performance or providing support for specific subjects.

[1564] This invention aims to improve the efficiency of teachers' work and the quality of education in the field of education by combining an emotion engine to realize educational support that takes into account the emotions of students and teachers. This system is mainly composed of three entities: a server, a terminal, and a user.

[1565] Uploading teaching material data

[1566] The user (teacher) first selects educational data (e.g., digital textbooks in PDF or Word format) using their own device, such as a computer or tablet, and uploads it to the server. The device is provided with a dedicated interface through which the user can easily upload data.

[1567] Automatic test generation

[1568] When the server receives the uploaded educational data, it analyzes the data using text mining technology (for example, using Python's NLTK or spaCy). Based on the analysis results, it automatically generates test questions using a generative AI model (for example, OpenAI's GPT-4). These test questions are generated in a variety of formats, including multiple choice and free-form questions.

[1569] Check and edit test content

[1570] The generated test questions are provided to the user via the terminal. The user can review the test questions and add, delete, or modify questions as needed. The edited test questions are then saved back to the server.

[1571] Use of emotion engine

[1572] While the user is reviewing and editing the test questions, the server uses emotion recognition technology (such as Microsoft's Emotion API) to analyze the user's emotions from their facial expressions and tone of voice. Based on this emotional data, the server makes suggestions to optimize the difficulty and content of the test questions.

[1573] Entering and uploading grade data

[1574] After the test, the user inputs each student's performance data into the terminal and uploads it to the server. The performance data is stored in a database and used for later analysis.

[1575] Analysis of academic performance data and academic ability analysis

[1576] The server performs statistical analysis of the uploaded grade data using Python libraries such as Pandas and NumPy, providing a detailed understanding of students' strengths and weaknesses, as well as their academic ability trends.

[1577] Generate measures to improve academic performance

[1578] Based on the analysis of the grade data, the server uses a generative AI model to automatically generate educational strategies, including supplementary learning programs and home learning materials.

[1579] Adjusting academic achievement measures using an emotion engine

[1580] The server recognizes students' emotional data in real time and generates countermeasures aimed at improving motivation during individual instruction. These countermeasures include suggesting learning materials and methods that will stimulate students' interest in learning.

[1581] Providing and sharing countermeasures

[1582] The generated teaching strategies are sent to the device and can be viewed and shared by the user. Users can share these strategies with students and their parents to improve the quality of individualized instruction.

[1583] Prompt Sentence Examples

[1584] Below is an example of a prompt sentence to input to the generative AI model.

[1585] Automatic generation of test questions

[1586] "Create calculation and multiple choice questions for quizzes from a digital math textbook for fifth graders."

[1587] Proposal of countermeasures

[1588] "Based on Mr. A's grade data, please suggest a set of practice problems for fraction calculations and an effective home study program."

[1589] The introduction of this system will significantly reduce the workload of teachers and provide optimal educational support that takes emotions into consideration.

[1590] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1591] Step 1:

[1592] The user selects the teaching material data and uploads it to the server from the terminal.

[1593] Input: The user selects the teaching material data (PDF, Word document, etc.) in the device interface.

[1594] Specific operation: The user selects the teaching material data using the file selection dialog on their computer or tablet.

[1595] Data processing: The terminal converts the selected file into binary data and creates an HTTP request.

[1596] Output: The teaching material data is uploaded to the server.

[1597] Step 2:

[1598] The server receives the training data and stores it in a database.

[1599] Input: Uploaded teaching material data file.

[1600] What happens: The server receives an HTTP request, saves the file in the specified directory on the file system, and records the metadata (file name, upload date, etc.) in a database.

[1601] Data calculation: The server calculates the hash value of the file and verifies the integrity of the data.

[1602] Output: The teaching material data and its metadata are saved in the server's file system and database.

[1603] Step 3:

[1604] The server analyzes the uploaded teaching material data and automatically generates test questions using a generation AI.

[1605] Input: Saved teaching material data file.

[1606] Specific operation: The server uses text mining technology (libraries such as NLTK and spaCy) to analyze the teaching material data into text.

[1607] Data processing: Preprocessing the generated text data and inputting the analysis results into the generative AI model. Creating prompt sentences and sending them to the generative AI model.

[1608] Output: Auto-generated test questions as responses from the generative AI model.

[1609] Step 4:

[1610] The terminal displays the generated test questions to the user.

[1611] Input: Auto-generated test questions.

[1612] Specific operation: Generates a UI (user interface) for the device to display the test question data received from the server.

[1613] Output: A list of test questions that the user can view on their device.

[1614] Step 5:

[1615] Users review and edit test questions.

[1616] Input: Test questions displayed on the terminal.

[1617] Specific operation: The user checks the test questions through the interface, and deletes, adds, or modifies questions as needed. The edits are then sent from the device to the server.

[1618] Output: The edited test question.

[1619] Step 6:

[1620] The server saves the edited test questions.

[1621] Input: Edited test question data.

[1622] Specific operation: The server reflects the received edited data on the original test question set and saves it in the database.

[1623] Output: The most recent saved test question set.

[1624] Step 7:

[1625] The server uses emotion recognition technology to analyze the user's emotions and adjust the difficulty and content of the test questions.

[1626] Input: User's facial expression and voice data.

[1627] Specific operation: The server calls the emotion recognition API and obtains the analysis results of facial expressions and voice.

[1628] Data Computation: Analyzes emotional data and generates suggestions to optimize the difficulty and format of test questions based on the user's emotional state.

[1629] Output: Suggested adjustments to test questions based on sentiment analysis.

[1630] Step 8:

[1631] The user inputs the student's grade data into the terminal and uploads it to the server.

[1632] Input: Performance data entered by the user into the device.

[1633] Specific operation: The user uses the terminal interface to input the performance results for each student.

[1634] Data processing: The terminal organizes the entered performance data and sends it to the server.

[1635] Output: The grade data is uploaded to the server.

[1636] Step 9:

[1637] The server analyzes the grade data and identifies students' academic trends.

[1638] Input: Uploaded grade data.

[1639] Specific operation: The server performs statistical analysis on the performance data using Pandas and NumPy.

[1640] Data calculation: Analyze patterns of strong and weak subjects, as well as academic performance trends.

[1641] Output: Student academic performance trend data as the analysis result.

[1642] Step 10:

[1643] The server automatically generates educational strategies based on the results of the academic ability analysis.

[1644] Input: Student academic performance trend data.

[1645] How it works: The server uses the generative AI model to create optimal educational strategies for each student.

[1646] Data calculation: Educational measures include automatically generating supplementary programs and home learning materials.

[1647] Output: Automatically generated educational strategies.

[1648] Step 11:

[1649] The server uses emotion recognition technology to recognize students' emotions and generates countermeasures to improve motivation during individual instruction.

[1650] Input: Student emotion data.

[1651] Specific operation: The server calls the emotion recognition API in real time to obtain the student's emotions.

[1652] Data calculation: Optimizing individualized instruction methods to improve motivation based on emotional data.

[1653] Output: Optimized educational strategies for improving motivation.

[1654] Step 12:

[1655] The generated educational strategy plan is sent to the terminal and can be viewed and shared by the user.

[1656] Input: Optimized educational strategy.

[1657] Specific operation: The server sends the countermeasure proposal to the user's device, which provides an interface to display the countermeasure proposal.

[1658] Output: The educational plan displayed on the device. The user can view the plan and share it with students and parents.

[1659] (Application example 2)

[1660] 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."

[1661] Conventional factory robot-based work support systems are unable to generate work instructions or provide guidance that takes into account the emotions of workers, making it difficult to implement efficient and flexible work improvement. Furthermore, instructions that ignore the emotions and motivation of workers can lead to reduced work efficiency and inconsistent quality. The present invention aims to solve these problems by providing optimal work instructions and work improvement proposals that take into account the emotions of workers.

[1662] 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.

[1663] In this invention, the server includes means for analyzing uploaded information using generative artificial intelligence and automatically generating work instructions, means for workers to confirm and edit the work instructions generated through the device, means for inputting and uploading work results, means for recognizing the emotions of workers using an emotion engine and adjusting the difficulty and content of the work instructions, and means for sending the generated work improvement proposals to the device so that workers can view and share them. This makes it possible to provide flexible and efficient work instructions and work improvement proposals that take emotions into consideration.

[1664] "Uploading" is the act of sending and storing information from one device to another computer system, such as a server or cloud.

[1665] "Analysis" is the act of examining data or information in detail to clarify its structure, content, and meaning.

[1666] "Automatic generation" refers to the use of artificial intelligence or specific algorithms to generate the necessary information or data without manual intervention.

[1667] "Work instructions" are information used to communicate specific work content and procedures to workers.

[1668] An "apparatus" is a mechanical or electronic device used for a specific purpose.

[1669] "Verification" is the process of verifying whether the generated data or instructions are correct.

[1670] "Editing" is the act of modifying or changing generated data or instructions.

[1671] "Work results" are the results or performance of the work performed by a worker.

[1672] The "Emotion Engine" is an artificial intelligence technology that recognizes and analyzes emotions from facial expressions, voice, actions, etc.

[1673] "Cognition" is the ability or act of understanding and identifying specific information.

[1674] "Difficulty" refers to the degree of difficulty in accomplishing a task or problem.

[1675] "Content" refers to the specific content of information or data.

[1676] "Adjustment" is the act of changing content or standards to meet specific goals or conditions.

[1677] A "business improvement proposal" is a specific method or means proposed to improve the efficiency or quality of work or operations.

[1678] "Viewing" is the act of checking and looking at the generated data and information.

[1679] "Sharing" is the act of using specific information or data together with other users.

[1680] The present invention relates to a work support system for factory robots, and by combining an emotion engine and generative artificial intelligence, it provides optimal work instructions and work improvement proposals according to the emotions of workers. Specific embodiments are described below.

[1681] System Configuration

[1682] 1. Hardware

[1683] Server: A high-performance computer that processes data analysis, generative artificial intelligence, and emotion engines.

[1684] Devices: Computers, tablets, and smartphones used by workers and managers.

[1685] Camera device: A camera for recognizing the facial expressions of workers.

[1686] 2. Software

[1687] Python: Used as a programming language.

[1688] OpenCV: An image processing library used for facial expression recognition.

[1689] TextBlob: A library for text parsing and generation.

[1690] scikit-learn: A machine learning library for sentiment classification.

[1691] Operation process

[1692] 1. Uploading Information

[1693] The administrator uploads the work procedure data to the server, which then analyzes the data and uses it as the basis for work instructions.

[1694] 2. Automatic generation of work instructions

[1695] The server analyzes the uploaded work procedure data and automatically generates work instructions using a generative AI model, which include specific work content and procedures.

[1696] 3. Review and edit work instructions

[1697] The worker checks the generated work instructions through their terminal and edits them as necessary. At this time, the emotion engine analyzes the worker's facial expressions and tone of voice to suggest the most appropriate instructions and level of difficulty.

[1698] 4. Enter and upload labor results

[1699] After completing their work, workers enter their work results into a terminal and upload them to the server, which then obtains the information necessary for the next data analysis.

[1700] 5. Use of Emotion Engine

[1701] The server uses an emotion engine to recognize the worker's emotions in real time and adjusts optimal work instructions and business improvement proposals based on the worker's motivation and emotions.

[1702] 6. Analyzing work results and generating work improvement proposals

[1703] The server analyzes the uploaded work results and evaluates the worker's work efficiency and quality. Based on this, it generates business improvement proposals using a generative AI model.

[1704] 7. Providing and sharing business improvement proposals

[1705] The server sends the generated business improvement proposals to the terminals, where workers and managers can view and share them, thereby achieving efficient and high-quality work.

[1706] Specific examples

[1707] 1. Facial Recognition Prompts

[1708] Example: image_path = 'worker_face.jpg'; emotions = recognize_emotion(image_path)

[1709] 2. Prompt for work order generation

[1710] Example: template = "Generate instructions for"; data = {"task": "assemble", "parts": ["screw", "nut"]}; work_instruction = generate_work_instruction(template, data)

[1711] This will enable flexible and efficient work instructions and business improvement proposals that take emotions into account.In addition, the use of specific devices and software makes the system realistic and practical to implement.

[1712] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1713] Step 1:

[1714] The user uploads the work procedure data to the server via the terminal.

[1715] Input: Work procedure data (e.g., assembly instructions)

[1716] Data processing and calculation: The server stores the uploaded data and analyzes its contents.

[1717] Output: Analyzed work procedure data

[1718] Step 2:

[1719] The server uses the analyzed work procedure data to automatically generate work instructions using a generative artificial intelligence model.

[1720] Input: Parsed work procedure data

[1721] Data processing and calculation: The generative artificial intelligence model understands the content of the work procedures and generates specific work instructions.

[1722] Output: Generated work instructions (e.g., specific assembly steps)

[1723] Step 3:

[1724] The user can check the work instructions generated from the server through the terminal and edit them as necessary.

[1725] Input: Generated Work Order

[1726] Data processing and calculation: Users can check the instructions on the terminal and make corrections or additions, for example, by adding details to the work procedure or changing the order of the steps.

[1727] Output: Reviewed and edited work instructions

[1728] Step 4:

[1729] The server uses an emotion engine to recognize emotions while the user is editing the work instructions and suggests editing content and difficulty.

[1730] Input: User's facial expression data and voice data

[1731] Data processing and calculation: The emotion engine analyzes facial expression and voice data to evaluate the user's emotional state. Based on this, it makes suggestions regarding editing content and difficulty.

[1732] Output: Sentiment analysis results and suggested edits and difficulty changes

[1733] Step 5:

[1734] After the user completes the work, he / she inputs the results of the work through the terminal and uploads them to the server.

[1735] Input: Work result data (e.g., work completion report)

[1736] Data processing and calculation: Labor outcome data is collected and stored on a server for future analysis.

[1737] Output: Saved labor result data

[1738] Step 6:

[1739] The server analyzes the uploaded work result data and evaluates work efficiency and quality.

[1740] Input: Saved labor result data

[1741] Data processing and calculation: Analyzes work result data and generates statistical information on work efficiency and quality, such as the time required for work and error rate.

[1742] Output: Evaluation results of work efficiency and quality

[1743] Step 7:

[1744] Based on the evaluation results, the server generates business improvement proposals using a generative artificial intelligence model.

[1745] Input: Work efficiency and quality evaluation results

[1746] Data processing and calculation: The generative AI model analyzes the evaluation results and generates specific improvement proposals for improving efficiency and quality.

[1747] Output: Generated business improvement proposals (e.g., proposed changes to work procedures)

[1748] Step 8:

[1749] The server sends the generated business improvement proposals to the terminal, where the user can view and share them.

[1750] Input: Generated business improvement proposal

[1751] Data processing and calculation: The generated business improvement proposals are sent to the user's device so that they can be viewed and shared.

[1752] Output: Business improvement proposals displayed on the user's device

[1753] By following these steps, the server, terminal, and user interact with each other to provide flexible and efficient work instructions and business improvement proposals that respond to emotions.

[1754] 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.

[1755] 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.

[1756] 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.

[1757] [Fourth embodiment]

[1758] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1759] 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.

[1760] 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).

[1761] 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.

[1762] 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.

[1763] 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).

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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."

[1771] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education.

[1772] System configuration and functions

[1773] 1. Uploading teaching material data

[1774] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[1775] Users select teaching material data, such as digital textbooks and slides they have created, using a computer or tablet and upload it to the system. This uploaded data is stored on the server and used for subsequent processing.

[1776] 2. Automatic generation of test creation

[1777] The server analyzes the educational data and automatically generates test questions using generative AI.

[1778] The server analyzes the uploaded educational data. Text mining technology is used for the analysis to extract important keywords and concepts. Based on these extraction results, the generative AI automatically generates appropriate test questions. The generated test questions come in multiple question formats (multiple choice, fill-in-the-blank, written, etc.).

[1779] 3. Check and edit the test content

[1780] User-generated test questions can be viewed and edited on the device

[1781] The user checks the automatically generated test questions on their device, checks the appropriateness of the questions, and makes any necessary modifications, such as adding or deleting questions or adjusting the difficulty level. After editing, the test questions are uploaded back to the server and saved in the system.

[1782] 4. Enter and upload grade data

[1783] The user enters the student's test results into the terminal and uploads them to the server.

[1784] After the test, the user enters the student's answers into the device and uploads the results data to the system. The results data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions. This data is also stored on the server.

[1785] 5. Analysis of academic performance data and academic ability analysis

[1786] The server analyzes the grade data and identifies the student's academic ability trends.

[1787] The server analyzes the uploaded grade data, using statistical analysis to identify each student's strengths and weaknesses and overall academic trends. If necessary, the same analysis can be performed for specific classes or groups selected by the teacher.

[1788] 6. Generating measures to improve academic ability

[1789] The server automatically generates educational strategies based on the results of the academic ability analysis.

[1790] Based on the analysis results, the server generates optimal educational strategies for each student, including remedial programs, additional learning materials, and self-study resources. For example, a student who struggles with fraction calculations in math might be provided with practice problems specific to that area.

[1791] 7. Providing and sharing countermeasures

[1792] The server sends the generated educational plan to the device, where the user can view and share it.

[1793] The server sends the generated educational strategies to the user's device. The user can review the strategies on their device and share them with students and parents as needed. This is expected to improve the accuracy of individualized instruction and lead to improved academic performance for students.

[1794] Specific examples

[1795] Below are some specific examples of how this system can be used.

[1796] Uploading teaching material data

[1797] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[1798] Auto-generated test creation

[1799] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[1800] Check and edit test content

[1801] The teacher checks the generated test questions, adjusts the difficulty of some questions, and saves them again on the server.

[1802] Entering and uploading grade data

[1803] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[1804] Analysis of academic performance data and academic ability analysis

[1805] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[1806] Generate measures to improve academic performance

[1807] The server generates a set of fraction calculation practice problems and a home study program for Mr. A.

[1808] Providing and sharing countermeasures

[1809] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[1810] The introduction of this system will significantly reduce the burden on teachers and improve the quality of education.

[1811] The processing flow will be explained below.

[1812] Step 1:

[1813] The user selects the teaching material data

[1814] The user (teacher) uses a computer or tablet to select the target digital teaching material data (e.g., textbooks, slides, supplementary materials, etc.) in a file browser.

[1815] Step 2:

[1816] Upload the teaching material data selected by the user from the device to the server.

[1817] The user clicks a dedicated upload button to upload the selected teaching material data to the system. The teaching material data is transferred to the server via the Internet and stored on the server.

[1818] Step 3:

[1819] The server analyzes the uploaded educational data

[1820] The server analyzes the stored learning material data and uses text mining technology to extract important keywords and concepts from the text content of the learning material. Natural language processing technology is also utilized in this process.

[1821] Step 4:

[1822] The server automatically generates test questions using AI

[1823] The server uses generative AI to create test questions based on the extracted keywords and concepts. The generated test questions come in multiple formats, including multiple choice, fill-in-the-blank, and free-form questions.

[1824] Step 5:

[1825] User can view generated tests on device

[1826] The user checks the list of test questions automatically generated by the server on their device, checking the content, format, and difficulty of each question one by one.

[1827] Step 6:

[1828] User-generated test editing

[1829] Users can review the test questions and make corrections, additions, or deletions as needed. For example, they can change the question format or adjust the difficulty level. Once edited, the test is uploaded back to the server and saved.

[1830] Step 7:

[1831] The user enters the student's test results into the terminal.

[1832] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[1833] Step 8:

[1834] Upload the grade data entered by the user to the server

[1835] Once the data has been entered, the user uploads it to the system, where it is stored on the server and used for subsequent analysis.

[1836] Step 9:

[1837] The server analyzes the performance data

[1838] The server analyzes the stored grade data and uses statistical analysis tools to identify students' strengths and weaknesses, as well as academic trends.

[1839] Step 10:

[1840] The server generates the academic performance report.

[1841] The server then generates an academic performance report for each student based on the analysis results, including graphs, charts, and commentary based on the analysis results.

[1842] Step 11:

[1843] The server generates educational strategies.

[1844] Based on the generated academic achievement report, the server automatically generates educational strategies tailored to each student, including areas to strengthen in class and materials for home study.

[1845] Step 12:

[1846] The server generates an academic performance report and sends it to the device.

[1847] The server sends the generated report and countermeasures to the user's device, where the user can review it and share it with students and parents as needed.

[1848] Through these steps, the system can significantly improve the efficiency of teachers' work and improve the quality of education.

[1849] Example 1

[1850] 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."

[1851] In the field of education, teachers have a wide range of tasks, which creates a heavy workload. Furthermore, because they are required to deliver education efficiently while maintaining a certain level of quality, systems are needed that reduce the burden on teachers while improving the quality of education. In particular, tasks such as creating teaching materials, creating tests, and managing student grades are labor-intensive, and technology is needed to perform these tasks efficiently.

[1852] 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.

[1853] In this invention, the server includes means for analyzing uploaded educational data using a generation AI and automatically generating test questions, means for users to review and edit the generated test questions via a terminal, means for inputting and uploading student achievement data, means for analyzing the achievement data and identifying students' academic ability trends, means for automatically generating educational strategies based on the results of the academic ability analysis, and means for sending the generated educational strategies to the terminal so that users can view and share them. This enables efficient management and analysis of educational data, significantly reducing the workload of teachers and improving the quality of education.

[1854] "Generative AI" is an artificial intelligence technology that automatically generates new information and solutions based on uploaded data.

[1855] "Educational data" refers to information and materials related to education, such as digital textbooks and created slides.

[1856] "Test questions" are questions that are asked to assess a student's understanding and knowledge.

[1857] "Academic performance data" refers to data such as test scores and evaluation results obtained by students.

[1858] "Academic ability trends" refers to trends that indicate a student's strengths and weaknesses in subjects and their learning progress.

[1859] "Educational measures" are proposals for specific teaching methods and teaching materials to improve students' academic abilities.

[1860] A "terminal" is a device such as a computer or tablet that is directly operated by a user.

[1861] "Users" refer to teachers and other educational personnel who use this system.

[1862] A "server" is a computer system that provides services and resources on a computer network.

[1863] "Text mining" is an analytical technique for extracting useful information from natural language data.

[1864] "Statistical analysis" is an analytical method that aims to obtain information by analyzing data using statistical techniques.

[1865] "Visualization tools" are software and techniques for visually displaying data.

[1866] MODE FOR CARRYING OUT THE INVENTION

[1867] This invention is a system aimed at improving the work efficiency of teachers and the quality of education in the field of education. This system has the functions of analyzing uploaded educational data using generative AI and automatically generating test questions, allowing teachers to review and edit the generated test questions, inputting and uploading grade data, and automatically generating educational countermeasures based on student grade data to grasp academic ability trends.

[1868] Hardware and software used

[1869] Hardware

[1870] Server: Stores and analyzes educational data, and generates test questions and educational strategies.

[1871] Terminal: A device (e.g., PC, tablet) that teachers use to upload teaching material data, check and edit test questions, and enter and upload grade data.

[1872] software

[1873] Generative AI: Artificial intelligence that analyzes teaching material data and generates test questions and educational strategies (e.g., GPT-3, BERT).

[1874] Text mining technology: Natural language processing engines (e.g., SpaCy, NLTK) for extracting important keywords and concepts from teaching material data.

[1875] Data analysis tools: Software for statistical analysis of performance data and identifying trends in student achievement (e.g., Pandas, NumPy).

[1876] Visualization tools: Tools for visually displaying the results of performance data analysis (e.g., Matplotlib, Seaborn).

[1877] Explanation of program processing

[1878] Uploading teaching material data

[1879] A user (teacher) uses a PC or tablet to select educational data (digital textbooks, created slides, etc.) and uploads them to the server from the device. The server saves the received data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[1880] Auto-generated test creation

[1881] The server analyzes the uploaded educational data using text mining technology to extract important keywords and concepts. Based on the extracted keywords and concepts, the generation AI generates appropriate test questions (multiple choice, fill-in-the-blank, essay, etc.). Examples of generated prompts include:

[1882] "Read the following text and select the appropriate option. Text: 『○○』"

[1883] Check and edit test content

[1884] The user checks the test questions generated on the device and makes corrections as necessary. The corrected test questions are then uploaded back to the server and saved.

[1885] Entering and uploading grade data

[1886] After the test, the user enters the student's answers into the device and uploads the results to the server, which then stores the received data in a database.

[1887] Analysis of academic performance data and academic ability analysis

[1888] The server analyzes the uploaded grade data using statistical analysis tools to identify each student's academic performance trends, and the analysis results are displayed visually using visualization tools.

[1889] Generate measures to improve academic performance

[1890] The server generates individualized educational strategies based on the results of the academic ability analysis. These strategies include remedial programs, additional learning materials, and self-study resources. Examples of generated prompts include:

[1891] "For the next student, please suggest the following strategies for those struggling with fractions in math:"

[1892] Providing and sharing countermeasures

[1893] The server sends the generated educational countermeasures plan to the user's device, where the user confirms it and then shares it with students and parents.The countermeasures plan is distributed via an educational portal site or email system, allowing students and parents to access it.

[1894] This will enable the efficient management and analysis of educational data, which is expected to significantly reduce the workload of teachers while improving the quality of education.

[1895] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1896] System program processing flow

[1897] Step 1: Upload the teaching material data

[1898] Input: User-selected teaching material data (file format: PDF, PPT, etc.)

[1899] Output: Learning material data and file metadata stored on the server

[1900] Specific behavior:

[1901] Users select the teaching material data on their computers or tablets.

[1902] The terminal gets the file path through a file selection dialog.

[1903] The terminal sends the selected teaching material data to the server using an HTTP request.

[1904] The server stores the received teaching material data in storage and records the file metadata (file name, upload date and time, file size, etc.) in a database.

[1905] Step 2: Analyzing Educational Data

[1906] Input: Teaching material data stored on the server

[1907] Output: Extracted terms and concepts

[1908] Specific behavior:

[1909] The server reads the teaching material data and analyzes it using text mining technology.

[1910] The server uses a natural language processing engine (e.g. SpaCy, NLTK) to extract important keywords and concepts.

[1911] The server temporarily stores the extracted keywords and concepts.

[1912] Step 3: Generate test questions

[1913] Input: Extracted keywords and concepts

[1914] Output: Auto-generated test questions

[1915] Specific behavior:

[1916] The server uses generative AI (e.g., GPT-3, BERT) to generate test questions based on the extracted keywords and concepts.

[1917] The server sets up a generation prompt and sends a request to the generative AI model.

[1918] Example prompt: "Generate three multiple choice questions using the following keywords: fractions, math, 5th grade"

[1919] The server formats and saves the test questions received from the generation AI.

[1920] Step 4: Review and edit the test content

[1921] Input: Auto-generated test questions

[1922] Output: Test questions corrected by the user

[1923] Specific behavior:

[1924] The server sends the generated test questions to the device.

[1925] The user checks the test questions generated on the terminal.

[1926] The user uses the editing screen of the web application to modify the test questions (add, delete, adjust the difficulty level, etc.).

[1927] The device uploads the modified test questions to the server.

[1928] Step 5: Enter and upload grade data

[1929] Input: Student answer results entered by the user

[1930] Output: Achievement data stored on the server

[1931] Specific behavior:

[1932] After the user takes the test, the student's answers are entered into the terminal.

[1933] The terminal uses a web application form to input each student's grade data.

[1934] The terminal sends the entered score data to the server using an HTTP request.

[1935] The server stores the received results data in a database.

[1936] Step 6: Analysis of academic performance data and academic achievement analysis

[1937] Input: Achievement data stored on the server

[1938] Output: Academic performance trend report for each student

[1939] Specific behavior:

[1940] The server reads the performance data and analyzes it using statistical analysis tools (e.g., Pandas, NumPy).

[1941] The server calculates each student's correct answer rate, average score, distribution, etc.

[1942] The server uses visualization tools (e.g., Matplotlib, Seaborn) to graph the results and generate academic performance trend reports.

[1943] Step 7: Generate strategies to improve academic performance

[1944] Input: Academic ability analysis results

[1945] Output: Automatically generated educational strategies

[1946] Specific behavior:

[1947] The server uses generative AI to generate educational strategy proposals based on the results of the academic ability analysis.

[1948] The server sets up a generation prompt and sends a request to the generative AI model.

[1949] Example prompt: "For the following student, please suggest the following strategies for solving problems with fractions in math:"

[1950] The server formats and saves the generated educational strategies.

[1951] Step 8: Provide and share countermeasures

[1952] Input: Automatically generated educational plan

[1953] Output: Solutions provided to users, students, and parents

[1954] Specific behavior:

[1955] The server sends the generated educational strategy plan to the user's terminal.

[1956] The user checks the educational measures on the device.

[1957] Users share the countermeasures with students and parents by distributing them via educational portal sites and email systems, making them viewable and downloadable.

[1958] (Application example 1)

[1959] 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."

[1960] In the field of education, teachers must take measures to improve the academic ability of each student while juggling a wide range of tasks. However, the series of tasks, such as preparing teaching materials, creating tests, managing grades, and creating countermeasures based on the results, are enormous and require time and effort. For this reason, a system is needed to carry out these tasks efficiently and effectively. In addition, to take effective educational measures, teachers need the ability to check and customize educational content in real time.

[1961] 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.

[1962] In this invention, the server includes means for analyzing uploaded educational data using a generation artificial intelligence and automatically generating test questions, means for searching and selecting teaching materials in a virtual space, means for a user to check and edit the generated test questions, means for previewing and editing educational strategies in real time through a terminal, means for inputting and uploading student achievement data, and means for previewing and editing educational strategies in the virtual space. This allows teachers to efficiently obtain the necessary teaching materials and strategies and customize educational content in real time.

[1963] "Generative AI" is an AI technology that has the ability to analyze uploaded educational data and automatically generate test questions and educational strategies.

[1964] "Educational data" is a general term for digital data related to education, such as textbooks, slides, and teaching materials.

[1965] A "virtual space" is a virtual environment constructed using virtual reality technology that allows users to visually and experientially explore and select educational materials.

[1966] "Device" is a general term for electronic devices such as computers, smartphones, and tablets that users use to check, edit, and upload educational data.

[1967] "Test questions" are questions to evaluate learning content that are automatically generated by generative artificial intelligence based on educational data.

[1968] "Academic performance data" refers to data that evaluates a student's learning outcomes and includes grade information based on the results.

[1969] "Educational strategy" is a general term for specific educational plans and supplementary materials that are generated by analyzing academic performance data in order to improve each student's academic ability.

[1970] "Real-time preview" is a function that allows users to instantly check educational data and countermeasures on their devices or in a virtual space.

[1971] "Editing" refers to the act of the user changing or modifying the content of the generated test questions or educational strategies.

[1972] This invention is a system aimed at improving work efficiency and the quality of education in the field of education. This system has the functions of allowing teachers to upload educational data, automatically generating test questions using generative artificial intelligence, and exploring teaching materials in a virtual space, previewing and editing them in real time. The specific configuration and processing required to realize this system are described below.

[1973] 1. Uploading teaching material data

[1974] Users upload educational material data, such as digital textbooks and slides they have created, from their devices (PCs or tablets) to the server. The uploaded data is stored on the server and used for subsequent processing.

[1975] 2. Automatic generation of test creation

[1976] The server analyzes the uploaded educational data. This analysis uses text mining technology implemented in Python to extract important keywords and concepts. Based on the extracted results, a generative artificial intelligence model using TensorFlow and PyTorch automatically generates appropriate test questions. The generated test questions include multiple choice, fill-in-the-blank, and essay questions.

[1977] 3. Explore and preview learning materials in a virtual space

[1978] Users put on a VR headset (such as Oculus Quest 2) and enter a virtual space built with Unity or Unreal Engine. In the virtual space, users can explore and select learning materials and preview them in real time. The selected learning materials include test questions and supplementary materials automatically generated by the system.

[1979] 4. Check and edit the test content

[1980] Users can check the generated test questions on their device and edit them as needed. They can check the appropriateness of the questions with a real-time preview and add, delete, or adjust the difficulty level. After editing, the test questions are saved back to the server.

[1981] 5. Enter and upload grade data

[1982] After taking the test, the user enters the student's performance data into the device and uploads it to the server. The performance data includes correct and incorrect answers for multiple-choice questions and the scoring results for essay questions, and is saved on the server.

[1983] 6. Analysis of academic performance data and academic ability analysis

[1984] The server analyzes the uploaded grade data, using Python-based statistical analysis algorithms to identify each student's strengths and weaknesses, as well as overall academic performance trends.

[1985] 7. Generating measures to improve academic ability

[1986] Based on the analysis of the grade data, the server generates optimal educational strategies, including supplementary learning programs, additional teaching materials, and self-study resources.

[1987] 8. Providing and sharing countermeasures

[1988] The generated educational strategies are sent from the server to the user's device, where the user can view and share them, improving the accuracy of individualized instruction.

[1989] Examples of specific examples and prompts

[1990] Below are some specific examples of prompt sentences to input into the generative AI model.

[1991] "Generate multiple-choice quiz questions based on 5th grade math materials."

[1992] "Based on the above teaching materials, please generate a supplementary workbook that specializes in fraction calculations."

[1993] This allows teachers to carry out educational activities effectively and efficiently.

[1994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1995] Step 1:

[1996] Users use their devices to upload educational material data (digital textbooks, created slides, etc.) to the server.

[1997] Input: Teaching material data

[1998] Output: Teaching material data saved on the server

[1999] Specific operation: The user uses a PC or tablet to select teaching material data from the system interface and clicks the "Upload" button.

[2000] Step 2:

[2001] The server analyzes the uploaded educational data and extracts important keywords and concepts.

[2002] Input: Teaching material data stored on the server

[2003] Output: Extracted keywords and concepts

[2004] Specific operation: The server runs a text mining algorithm implemented in Python to analyze the teaching material data, extracting keywords and concepts and storing them in a database.

[2005] Step 3:

[2006] The server automatically generates test questions using a generative AI model based on the extracted keywords and concepts.

[2007] Input: Extracted keywords and concepts

[2008] Output: Auto-generated test questions

[2009] Specific operation: The server feeds input data (extracted keywords and concepts) into a generative AI model built with TensorFlow or PyTorch, and generates test questions.

[2010] Step 4:

[2011] The user uses a VR headset to enter a teaching material shop in a virtual space and search for and select teaching material data.

[2012] Input: Teaching materials in virtual space

[2013] Output: Selected teaching material data

[2014] Specific operations: The user puts on a VR headset such as Oculus Quest 2 and moves around a virtual space built with Unity or Unreal Engine to find, pick up and select educational materials.

[2015] Step 5:

[2016] The user reviews and edits the automatically generated test questions on the device.

[2017] Input: Auto-generated test questions

[2018] Output: Test questions edited by the user

[2019] Specific operation: The user views the test questions through the device, and adds, deletes, and adjusts the difficulty of questions as needed. The edited content is saved back to the server.

[2020] Step 6:

[2021] After the user takes the test, the student's performance data is entered into the terminal and uploaded to the server.

[2022] Input: Student answer results

[2023] Output: Grade data saved on the server

[2024] Specific operation: The user enters the student's answer results into the grade management system and clicks the "Upload" button.

[2025] Step 7:

[2026] The server analyzes the grade data and identifies each student's academic ability trends.

[2027] Input: Student performance data

[2028] Output: Academic trend report

[2029] Specific operation: The server uses Python statistical analysis algorithms to analyze the grade data, identify strong and weak subjects, and compile trends into a report.

[2030] Step 8:

[2031] The server generates educational strategies for each student based on their academic ability trends.

[2032] Input: Academic Trend Report

[2033] Output: Educational measures

[2034] Specific operation: The server uses the generated AI model to generate supplementary learning programs and additional teaching materials tailored to specific academic trends.

[2035] Step 9:

[2036] The server sends the generated educational strategy plan to the user's device, where the user can review and share it.

[2037] Input: Educational measures proposal

[2038] Output: Educational measures displayed on the user's device

[2039] Specific operation: The server sends the proposed countermeasures to the user's device, and the user reviews the contents and shares them with students and parents as necessary.

[2040] 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.

[2041] The present invention is a system that aims to improve the work efficiency of teachers and the quality of education in the field of education, and by combining it with an emotion engine, realizes educational support that takes into account the emotions of students and teachers.

[2042] System configuration and functions

[2043] 1. Uploading teaching material data

[2044] The user (teacher) selects the teaching material data and uploads it to the server from their device.

[2045] Users select and upload teaching material data using a computer or tablet, and this data is stored on a server for later analysis and test creation.

[2046] 2. Automatic generation of test creation

[2047] The server analyzes the educational data and automatically generates test questions using generative AI.

[2048] The server analyzes the uploaded educational data using text mining technology, and the AI ​​automatically generates appropriate test questions, ranging from multiple choice questions to free-form questions.

[2049] 3. Check and edit the test content

[2050] User-generated tests can be viewed and edited on the device

[2051] Users can view the test questions generated on their devices, add, delete, or modify questions, and the edited test is saved back to the server.

[2052] 4. Use of Emotion Engine

[2053] The server uses an emotion engine to recognize the user's emotions and adjust the difficulty and content of the test questions.

[2054] When a teacher is reviewing and editing test questions, the emotion engine analyzes the teacher's emotions from their facial expressions and tone of voice, optimizing the difficulty level and question format of the proposed content.

[2055] 5. Enter and upload grade data

[2056] The user enters the student's test results into the terminal and uploads them to the server.

[2057] After the test, the user enters the results data for each student into the terminal and uploads it. This data is also saved on the server.

[2058] 6. Analysis of academic performance data and academic ability analysis

[2059] The server analyzes the grade data and identifies the student's academic ability trends.

[2060] Based on the uploaded grade data, the server performs statistical analysis of students' strong and weak subjects and academic trends.

[2061] 7. Generating measures to improve academic ability

[2062] The server automatically generates educational strategies based on the results of the academic ability analysis.

[2063] Based on the analysis results, the server generates optimal educational strategies for each student, including supplementary learning programs and home study materials.

[2064] 8. Adjusting academic achievement strategies using an emotion engine

[2065] The server uses an emotion engine to recognize students' emotions and generate strategies to improve motivation for individual instruction.

[2066] The server recognizes students' emotions in real time and generates teaching guidelines and countermeasures that take their motivation into account.

[2067] 9. Providing and sharing countermeasures

[2068] The server sends the generated educational plan to the device, where the user can view and share it.

[2069] The server sends the generated countermeasures to the teacher's device, where the user can check the countermeasures and share them with students and parents to improve the quality of individual instruction.

[2070] Specific examples

[2071] Below are some specific examples of how this system can be used.

[2072] Uploading teaching material data

[2073] A user (teacher) uploads a digital math textbook for fifth graders to the system.

[2074] Auto-generated test creation

[2075] The server analyzes this teaching material data and uses generation AI to automatically generate multiple-choice questions and calculation questions in the form of short quizzes.

[2076] Check and edit test content

[2077] The teacher reviews the generated test questions, adjusts the difficulty of some questions, and saves them back on the server. At this time, the emotion engine analyzes the teacher's emotions and automatically suggests the difficulty level of the test questions.

[2078] Entering and uploading grade data

[2079] After the test is administered, the teacher enters the students' answers into the system and uploads them.

[2080] Analysis of academic performance data and academic ability analysis

[2081] The server analyzes the performance data and determines that Mr. A is particularly bad at calculating fractions.

[2082] Generation of measures to improve academic performance and adjustment using an emotion engine

[2083] The server generates a set of fraction calculation practice problems and a home study program for Mr. A. Furthermore, the emotion engine recognizes Mr. A's emotions and suggests teaching methods to improve his motivation.

[2084] Providing and sharing countermeasures

[2085] The teacher will review this plan and send it to A's parents via email to support his learning at home.

[2086] The introduction of this system will significantly reduce the burden on teachers and further improve the quality of education by taking emotional factors into consideration.

[2087] The processing flow will be explained below.

[2088] Step 1:

[2089] The user selects the teaching material data

[2090] The user (teacher) uses a computer or tablet to select the target teaching material data (e.g., digital textbook, slides, supplementary materials) in a file browser.

[2091] Step 2:

[2092] Upload the teaching material data selected by the user from the device to the server.

[2093] The user clicks a button to upload the selected teaching material data to the system, which is then transferred to the server via the Internet and stored on the server.

[2094] Step 3:

[2095] The server analyzes the uploaded educational data

[2096] The server analyzes the stored teaching material data and uses text mining and natural language processing technologies to extract important keywords and concepts.

[2097] Step 4:

[2098] The server automatically generates test questions using AI

[2099] The server uses generative AI to automatically generate appropriate test questions based on the extracted keywords and concepts. The generated test questions come in a variety of formats, including multiple choice, fill-in-the-blank, and free-form questions.

[2100] Step 5:

[2101] User can view generated tests on device

[2102] The user checks the list of test questions automatically generated by the server on the terminal, checking the content, format, and difficulty of each question one by one.

[2103] Step 6:

[2104] User-generated test editing

[2105] Users can review the test questions and make corrections, additions, or deletions as necessary. For example, they can change the question format or adjust the difficulty level. Once edits are complete, the test is uploaded back to the server and saved.

[2106] Step 7:

[2107] Use an emotion engine to recognize user emotions and adjust test questions accordingly

[2108] While the user is editing the test content, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and if stress or confusion is recognized, the server makes suggestions to readjust the difficulty level or content of the questions.

[2109] Step 8:

[2110] The user enters the student's test results into the terminal.

[2111] After the test, the user inputs the test results for each student into the terminal, including correct and incorrect answers for multiple-choice questions and the results of the written questions.

[2112] Step 9:

[2113] Upload the grade data entered by the user to the server

[2114] Once the user has completed entering the data, they upload it to the system, where it is stored on the server and used for subsequent analysis.

[2115] Step 10:

[2116] The server analyzes the grade data and identifies the student's academic ability trends.

[2117] The server analyzes the stored academic data using statistical analysis tools to display students' strengths and weaknesses, as well as their overall academic performance trends.

[2118] Step 11:

[2119] The server generates the academic performance report.

[2120] The server then generates an individual student performance report based on the analysis results, which includes graphs, charts, specific data, and explanations based on the analysis results.

[2121] Step 12:

[2122] The server generates educational strategies.

[2123] Based on the generated academic achievement report, the server generates an optimal educational plan for each student, including specific supplementary learning programs, home study materials, and self-study resources.

[2124] Step 13:

[2125] Use an emotion engine to recognize student emotions and generate motivational strategies for individualized instruction

[2126] The server recognizes students' real-time emotional data and generates strategies that reflect their emotional state during learning. For example, if a student is feeling stressed, it suggests starting with easy problems.

[2127] Step 14:

[2128] The server generates an academic performance report and sends it to the device.

[2129] The server sends the generated academic performance report and countermeasures to the user's device, where the user can check it and share it with students and parents.

[2130] Through these steps, the system will significantly streamline teachers' work and, by taking emotional factors into account, will enable more effective individualized instruction and improved educational quality.

[2131] Example 2

[2132] 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."

[2133] In order to reduce the workload of teachers and improve the quality of education, it is necessary to streamline various tasks, such as creating teaching materials, managing student grades, and proposing individual educational measures. There is also a need for educational support that takes into account the emotions of students and teachers, but existing systems are insufficiently optimized to reflect emotions. Therefore, there is a need for a system that utilizes emotion recognition technology to provide more effective educational support.

[2134] 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.

[2135] In this invention, the server includes means for analyzing uploaded educational data using generative artificial intelligence and automatically generating test questions, means for the user to check and edit the generated test questions via a terminal, means for analyzing the user's emotions using emotion recognition technology and adjusting the difficulty and content of the test questions, means for adjusting the generated educational strategy based on the student's emotions using emotion recognition technology, and means for inputting and uploading student achievement data, which greatly improves the work efficiency of teachers and enables appropriate educational support that takes emotions into consideration.

[2136] "Generative AI" is an AI technology that generates and predicts natural language based on various data.

[2137] "Educational data" refers to data that includes information related to education, such as teaching materials, textbooks, and learning materials.

[2138] "Test questions" are questions or exercises that are generated by analyzing educational data and are used to assess a learner's level of understanding.

[2139] "Device" refers to the device (PC, tablet, smartphone, etc.) used by the user to upload educational data and check and edit test questions.

[2140] "Emotion recognition technology" is a technology that detects and analyzes human emotions from facial expressions, tone of voice, body movements, etc.

[2141] "Performance Data" means data relating to a student's scores or performance on a test or assessment.

[2142] "Educational measures" are proposals and programs generated based on academic performance data and academic trends, with the aim of improving academic performance or providing support for specific subjects.

[2143] This invention aims to improve the efficiency of teachers' work and the quality of education in the field of education by combining an emotion engine to realize educational support that takes into account the emotions of students and teachers. This system is mainly composed of three entities: a server, a terminal, and a user.

[2144] Uploading teaching material data

[2145] The user (teacher) first selects educational data (e.g., digital textbooks in PDF or Word format) using their own device, such as a computer or tablet, and uploads it to the server. The device is provided with a dedicated interface through which the user can easily upload data.

[2146] Automatic test generation

[2147] When the server receives the uploaded educational data, it analyzes the data using text mining technology (for example, using Python's NLTK or spaCy). Based on the analysis results, it automatically generates test questions using a generative AI model (for example, OpenAI's GPT-4). These test questions are generated in a variety of formats, including multiple choice and free-form questions.

[2148] Check and edit test content

[2149] The generated test questions are provided to the user via the terminal. The user can review the test questions and add, delete, or modify questions as needed. The edited test questions are then saved back to the server.

[2150] Use of emotion engine

[2151] While the user is reviewing and editing the test questions, the server uses emotion recognition technology (such as Microsoft's Emotion API) to analyze the user's emotions from their facial expressions and tone of voice. Based on this emotional data, the server makes suggestions to optimize the difficulty and content of the test questions.

[2152] Entering and uploading grade data

[2153] After the test, the user inputs each student's performance data into the terminal and uploads it to the server. The performance data is stored in a database and used for later analysis.

[2154] Analysis of academic performance data and academic ability analysis

[2155] The server performs statistical analysis of the uploaded grade data using Python libraries such as Pandas and NumPy, providing a detailed understanding of students' strengths and weaknesses, as well as their academic ability trends.

[2156] Generate measures to improve academic performance

[2157] Based on the analysis of the grade data, the server uses a generative AI model to automatically generate educational strategies, including supplementary learning programs and home learning materials.

[2158] Adjusting academic achievement measures using an emotion engine

[2159] The server recognizes students' emotional data in real time and generates countermeasures aimed at improving motivation during individual instruction. These countermeasures include suggesting learning materials and methods that will stimulate students' interest in learning.

[2160] Providing and sharing countermeasures

[2161] The generated teaching strategies are sent to the device and can be viewed and shared by the user. Users can share these strategies with students and their parents to improve the quality of individualized instruction.

[2162] Prompt Sentence Examples

[2163] Below is an example of a prompt sentence to input to the generative AI model.

[2164] Automatic generation of test questions

[2165] "Create calculation and multiple choice questions for quizzes from a digital math textbook for fifth graders."

[2166] Proposal of countermeasures

[2167] "Based on Mr. A's grade data, please suggest a set of practice problems for fraction calculations and an effective home study program."

[2168] The introduction of this system will significantly reduce the workload of teachers and provide optimal educational support that takes emotions into consideration.

[2169] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2170] Step 1:

[2171] The user selects the teaching material data and uploads it to the server from the terminal.

[2172] Input: The user selects the teaching material data (PDF, Word document, etc.) in the device interface.

[2173] Specific operation: The user selects the teaching material data using the file selection dialog on their computer or tablet.

[2174] Data processing: The terminal converts the selected file into binary data and creates an HTTP request.

[2175] Output: The teaching material data is uploaded to the server.

[2176] Step 2:

[2177] The server receives the training data and stores it in a database.

[2178] Input: Uploaded teaching material data file.

[2179] What happens: The server receives an HTTP request, saves the file in the specified directory on the file system, and records the metadata (file name, upload date, etc.) in a database.

[2180] Data calculation: The server calculates the hash value of the file and verifies the integrity of the data.

[2181] Output: The teaching material data and its metadata are saved in the server's file system and database.

[2182] Step 3:

[2183] The server analyzes the uploaded teaching material data and automatically generates test questions using a generation AI.

[2184] Input: Saved teaching material data file.

[2185] Specific operation: The server uses text mining technology (libraries such as NLTK and spaCy) to analyze the teaching material data into text.

[2186] Data processing: Preprocessing the generated text data and inputting the analysis results into the generative AI model. Creating prompt sentences and sending them to the generative AI model.

[2187] Output: Auto-generated test questions as responses from the generative AI model.

[2188] Step 4:

[2189] The terminal displays the generated test questions to the user.

[2190] Input: Auto-generated test questions.

[2191] Specific operation: Generates a UI (user interface) for the device to display the test question data received from the server.

[2192] Output: A list of test questions that the user can view on their device.

[2193] Step 5:

[2194] Users review and edit test questions.

[2195] Input: Test questions displayed on the terminal.

[2196] Specific operation: The user checks the test questions through the interface, and deletes, adds, or modifies questions as needed. The edits are then sent from the device to the server.

[2197] Output: The edited test question.

[2198] Step 6:

[2199] The server saves the edited test questions.

[2200] Input: Edited test question data.

[2201] Specific operation: The server reflects the received edited data on the original test question set and saves it in the database.

[2202] Output: The most recent saved test question set.

[2203] Step 7:

[2204] The server uses emotion recognition technology to analyze the user's emotions and adjust the difficulty and content of the test questions.

[2205] Input: User's facial expression and voice data.

[2206] Specific operation: The server calls the emotion recognition API and obtains the analysis results of facial expressions and voice.

[2207] Data Computation: Analyzes emotional data and generates suggestions to optimize the difficulty and format of test questions based on the user's emotional state.

[2208] Output: Suggested adjustments to test questions based on sentiment analysis.

[2209] Step 8:

[2210] The user inputs the student's grade data into the terminal and uploads it to the server.

[2211] Input: Performance data entered by the user into the device.

[2212] Specific operation: The user uses the terminal interface to input the performance results for each student.

[2213] Data processing: The terminal organizes the entered performance data and sends it to the server.

[2214] Output: The grade data is uploaded to the server.

[2215] Step 9:

[2216] The server analyzes the grade data and identifies students' academic trends.

[2217] Input: Uploaded grade data.

[2218] Specific operation: The server performs statistical analysis on the performance data using Pandas and NumPy.

[2219] Data calculation: Analyze patterns of strong and weak subjects, as well as academic performance trends.

[2220] Output: Student academic performance trend data as the analysis result.

[2221] Step 10:

[2222] The server automatically generates educational strategies based on the results of the academic ability analysis.

[2223] Input: Student academic performance trend data.

[2224] How it works: The server uses the generative AI model to create optimal educational strategies for each student.

[2225] Data calculation: Educational measures include automatically generating supplementary programs and home learning materials.

[2226] Output: Automatically generated educational strategies.

[2227] Step 11:

[2228] The server uses emotion recognition technology to recognize students' emotions and generates countermeasures to improve motivation during individual instruction.

[2229] Input: Student emotion data.

[2230] Specific operation: The server calls the emotion recognition API in real time to obtain the student's emotions.

[2231] Data calculation: Optimizing individualized instruction methods to improve motivation based on emotional data.

[2232] Output: Optimized educational strategies for improving motivation.

[2233] Step 12:

[2234] The generated educational strategy plan is sent to the terminal and can be viewed and shared by the user.

[2235] Input: Optimized educational strategy.

[2236] Specific operation: The server sends the countermeasure proposal to the user's device, which provides an interface to display the countermeasure proposal.

[2237] Output: The educational plan displayed on the device. The user can view the plan and share it with students and parents.

[2238] (Application example 2)

[2239] 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."

[2240] Conventional factory robot-based work support systems are unable to generate work instructions or provide guidance that takes into account the emotions of workers, making it difficult to implement efficient and flexible work improvement. Furthermore, instructions that ignore the emotions and motivation of workers can lead to reduced work efficiency and inconsistent quality. The present invention aims to solve these problems by providing optimal work instructions and work improvement proposals that take into account the emotions of workers.

[2241] 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.

[2242] In this invention, the server includes means for analyzing uploaded information using generative artificial intelligence and automatically generating work instructions, means for workers to confirm and edit the work instructions generated through the device, means for inputting and uploading work results, means for recognizing the emotions of workers using an emotion engine and adjusting the difficulty and content of the work instructions, and means for sending the generated work improvement proposals to the device so that workers can view and share them. This makes it possible to provide flexible and efficient work instructions and work improvement proposals that take emotions into consideration.

[2243] "Uploading" is the act of sending and storing information from one device to another computer system, such as a server or cloud.

[2244] "Analysis" is the act of examining data or information in detail to clarify its structure, content, and meaning.

[2245] "Automatic generation" refers to the use of artificial intelligence or specific algorithms to generate the necessary information or data without manual intervention.

[2246] "Work instructions" are information used to communicate specific work content and procedures to workers.

[2247] An "apparatus" is a mechanical or electronic device used for a specific purpose.

[2248] "Verification" is the process of verifying whether the generated data or instructions are correct.

[2249] "Editing" is the act of modifying or changing generated data or instructions.

[2250] "Work results" are the results or performance of the work performed by a worker.

[2251] The "Emotion Engine" is an artificial intelligence technology that recognizes and analyzes emotions from facial expressions, voice, actions, etc.

[2252] "Cognition" is the ability or act of understanding and identifying specific information.

[2253] "Difficulty" refers to the degree of difficulty in accomplishing a task or problem.

[2254] "Content" refers to the specific content of information or data.

[2255] "Adjustment" is the act of changing content or standards to meet specific goals or conditions.

[2256] A "business improvement proposal" is a specific method or means proposed to improve the efficiency or quality of work or operations.

[2257] "Viewing" is the act of checking and looking at the generated data and information.

[2258] "Sharing" is the act of using specific information or data together with other users.

[2259] The present invention relates to a work support system for factory robots, and by combining an emotion engine and generative artificial intelligence, it provides optimal work instructions and work improvement proposals according to the emotions of workers. Specific embodiments are described below.

[2260] System Configuration

[2261] 1. Hardware

[2262] Server: A high-performance computer that processes data analysis, generative artificial intelligence, and emotion engines.

[2263] Devices: Computers, tablets, and smartphones used by workers and managers.

[2264] Camera device: A camera for recognizing the facial expressions of workers.

[2265] 2. Software

[2266] Python: Used as a programming language.

[2267] OpenCV: An image processing library used for facial expression recognition.

[2268] TextBlob: A library for text parsing and generation.

[2269] scikit-learn: A machine learning library for sentiment classification.

[2270] Operation process

[2271] 1. Uploading Information

[2272] The administrator uploads the work procedure data to the server, which then analyzes the data and uses it as the basis for work instructions.

[2273] 2. Automatic generation of work instructions

[2274] The server analyzes the uploaded work procedure data and automatically generates work instructions using a generative AI model, which include specific work content and procedures.

[2275] 3. Review and edit work instructions

[2276] The worker checks the generated work instructions through their terminal and edits them as necessary. At this time, the emotion engine analyzes the worker's facial expressions and tone of voice to suggest the most appropriate instructions and level of difficulty.

[2277] 4. Enter and upload labor results

[2278] After completing their work, workers enter their work results into a terminal and upload them to the server, which then obtains the information necessary for the next data analysis.

[2279] 5. Use of Emotion Engine

[2280] The server uses an emotion engine to recognize the worker's emotions in real time and adjusts optimal work instructions and business improvement proposals based on the worker's motivation and emotions.

[2281] 6. Analyzing work results and generating work improvement proposals

[2282] The server analyzes the uploaded work results and evaluates the worker's work efficiency and quality. Based on this, it generates business improvement proposals using a generative AI model.

[2283] 7. Providing and sharing business improvement proposals

[2284] The server sends the generated business improvement proposals to the terminals, where workers and managers can view and share them, thereby achieving efficient and high-quality work.

[2285] Specific examples

[2286] 1. Facial Recognition Prompts

[2287] Example: image_path = 'worker_face.jpg'; emotions = recognize_emotion(image_path)

[2288] 2. Prompt for work order generation

[2289] Example: template = "Generate instructions for"; data = {"task": "assemble", "parts": ["screw", "nut"]}; work_instruction = generate_work_instruction(template, data)

[2290] This will enable flexible and efficient work instructions and business improvement proposals that take emotions into account.In addition, the use of specific devices and software makes the system realistic and practical to implement.

[2291] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2292] Step 1:

[2293] The user uploads the work procedure data to the server via the terminal.

[2294] Input: Work procedure data (e.g., assembly instructions)

[2295] Data processing and calculation: The server stores the uploaded data and analyzes its contents.

[2296] Output: Analyzed work procedure data

[2297] Step 2:

[2298] The server uses the analyzed work procedure data to automatically generate work instructions using a generative artificial intelligence model.

[2299] Input: Parsed work procedure data

[2300] Data processing and calculation: The generative artificial intelligence model understands the content of the work procedures and generates specific work instructions.

[2301] Output: Generated work instructions (e.g., specific assembly steps)

[2302] Step 3:

[2303] The user can check the work instructions generated from the server through the terminal and edit them as necessary.

[2304] Input: Generated Work Order

[2305] Data processing and calculation: Users can check the instructions on the terminal and make corrections or additions, for example, by adding details to the work procedure or changing the order of the steps.

[2306] Output: Reviewed and edited work instructions

[2307] Step 4:

[2308] The server uses an emotion engine to recognize emotions while the user is editing the work instructions and suggests editing content and difficulty.

[2309] Input: User's facial expression data and voice data

[2310] Data processing and calculation: The emotion engine analyzes facial expression and voice data to evaluate the user's emotional state. Based on this, it makes suggestions regarding editing content and difficulty.

[2311] Output: Sentiment analysis results and suggested edits and difficulty changes

[2312] Step 5:

[2313] After the user completes the work, he / she inputs the results of the work through the terminal and uploads them to the server.

[2314] Input: Work result data (e.g., work completion report)

[2315] Data processing and calculation: Labor outcome data is collected and stored on a server for future analysis.

[2316] Output: Saved labor result data

[2317] Step 6:

[2318] The server analyzes the uploaded work result data and evaluates work efficiency and quality.

[2319] Input: Saved labor result data

[2320] Data processing and calculation: Analyzes work result data and generates statistical information on work efficiency and quality, such as the time required for work and error rate.

[2321] Output: Evaluation results of work efficiency and quality

[2322] Step 7:

[2323] Based on the evaluation results, the server generates business improvement proposals using a generative artificial intelligence model.

[2324] Input: Work efficiency and quality evaluation results

[2325] Data processing and calculation: The generative AI model analyzes the evaluation results and generates specific improvement proposals for improving efficiency and quality.

[2326] Output: Generated business improvement proposals (e.g., proposed changes to work procedures)

[2327] Step 8:

[2328] The server sends the generated business improvement proposals to the terminal, where the user can view and share them.

[2329] Input: Generated business improvement proposal

[2330] Data processing and calculation: The generated business improvement proposals are sent to the user's device so that they can be viewed and shared.

[2331] Output: Business improvement proposals displayed on the user's device

[2332] By following these steps, the server, terminal, and user interact with each other to provide flexible and efficient work instructions and business improvement proposals that respond to emotions.

[2333] 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.

[2334] 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 ...

Claims

1. A means for analyzing uploaded educational data and automatically generating test questions using generative artificial intelligence; means for a user to review and edit the test questions generated through the terminal; and a means for inputting and uploading student performance data.

2. 2. The system according to claim 1, further comprising means for analyzing the performance data, grasping the trends of the academic ability of each student, and automatically generating educational countermeasures.

3. The system according to claim 1, further comprising means for transmitting the generated educational countermeasures to a terminal, where the user can view and share the plan.

Images