System

Abstract

To provide a system.SOLUTION: A system includes: means for analyzing learning contents input by a user to extract an important point; means for generating a test problem using a generative AI model on the basis of a prompt sentence including the extracted important point; means for monitoring a feeling of the user who works on the test problem; means for adjusting difficulty of the test problem on the basis of the monitored feeling; and means for providing the user with the adjusted test problem.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the field of education, reducing the workload of teachers and staff shortages are serious issues. In particular, creating test questions and explanations consumes a lot of teachers' time and effort. [Means for solving the problem]

[0005] The present invention provides a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions, thereby reducing the workload of teachers and resolving the problem of staff shortages. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The present invention is a system for use in educational settings. This system has a learning means for studying curriculum guidelines and textbook content. Specifically, the system analyzes the content of each chapter and section of the textbook and stores it in a database. Furthermore, the system extracts content to be studied based on the curriculum guidelines and then studies that content.

[0029] "Example 2"

[0030] Furthermore, the system of the present invention has a question creation means for creating test questions based on the content learned. Specifically, important points are extracted from the content learned and questions are created based on them. For example, if the content learned is "how to calculate the area of ​​a triangle," questions related to that content are created.

[0031] "Example 3"

[0032] The system of the present invention also has an explanation creation means for creating explanations for the created test questions. Specifically, the system explains the process and method of solving the created questions. For example, if the created question is "Find the area of ​​a triangle," the system will explain the process in detail. This helps students understand the questions and answer them.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The system learns the curriculum and textbook content. Specifically, it analyzes the content of each chapter and section of the textbook and stores it in a database.

[0036] Step 2: Based on the curriculum guidelines, extract the content to be learned and study it.

[0037] "Example 2"

[0038] Step 1: Create test questions based on what you have learned. Specifically, extract important points from what you have learned and create questions based on them.

[0039] Step 2: For example, if the content learned is "How to find the area of ​​a triangle," create a problem related to that.

[0040] "Example 3"

[0041] Step 1: Create an explanation for the test questions you have created. Specifically, explain the process and method of solving the questions you have created.

[0042] Step 2: For example, if the problem you created is "Find the area of ​​a triangle," explain the solution process in detail. This will help students understand the problem and solve it.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form 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."

[0045] In conventional educational systems, there is a lack of efficient ways to study curriculum guidelines and teaching materials, which increases the workload of educators and exacerbates the staff shortage problem.In addition, analysis and extraction of learning content is often done manually, which takes time and effort, making it difficult to provide efficient learning support in educational settings.

[0046] 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.

[0047] In this invention, the server includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content. This reduces the workload of educators, contributes to solving the problem of staff shortages, and enables efficient learning support.

[0048] A "curriculum guideline" is a document that outlines the learning content and educational goals set by an educational institution.

[0049] "Teaching material content" refers to the learning content contained in educational materials such as textbooks and reference books.

[0050] "Learning tools" are methods and tools for learning the curriculum and teaching material content.

[0051] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[0052] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[0053] "Analysis means" refers to methods and tools for analyzing the content of each chapter or section of the teaching material and storing it in a database.

[0054] "Extraction means" refers to methods or tools for extracting content to be learned based on the curriculum guidelines.

[0055] "Providing means" refers to the methods and tools used to provide extracted learning content to users.

[0056] "Educator" refers to occupations such as teachers and lecturers who provide instruction and education in educational settings.

[0057] "Workload" refers to the amount and difficulty of the work that educators perform on a daily basis.

[0058] The "staffing shortage problem" refers to a situation in which there are not enough educators in the educational field.

[0059] The present invention is a system for use in educational settings, which provides a means for efficiently learning curriculum guidelines and teaching material content. A specific embodiment of this system will be described below.

[0060] Generating a Program

[0061] The server generates a program for the system to be used in the educational field. This program includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content.

[0062] Program processing

[0063] The server uses natural language processing (NLP) technology to analyze the content of each chapter and section of the textbook. Specifically, it uses the Python libraries NLTK and spaCy to analyze the text data. The analyzed data is stored in a database such as MySQL (registered trademark) or PostgreSQL.

[0064] The server then extracts the learning content based on the curriculum guidelines. This process uses rule-based algorithms and machine learning models. The extracted content is then provided as a web application for users to study. This web application is built using a front-end framework such as React or Angular.

[0065] Specific examples

[0066] For example, if a user inputs "I would like to study Chapter 3 of the junior high school mathematics textbook," the server performs the following process.

[0067] 1. The server analyzes the content of Chapter 3 of the textbook and stores it in the database.

[0068] 2. The server extracts the content to be learned in Chapter 3 based on the curriculum guidelines.

[0069] 3. The extracted content is provided to the user through a web application.

[0070] Example prompts to input to a generative AI model:

[0071] "Analyze the contents of Chapter 3 of a junior high school mathematics textbook and extract the content that should be studied."

[0072] In this way, the system allows users to efficiently learn the necessary learning content in the educational setting.

[0073] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0074] Step 1:

[0075] Textbook data entry

[0076] The user uploads textbook data to the system. The device sends the PDF or text file of the textbook specified by the user to the server. The input is the textbook data file, and the output is the textbook data sent to the server. Specifically, the user selects the textbook file using the file selection dialog on the device and clicks the upload button.

[0077] Step 2:

[0078] Textbook content analysis

[0079] The server analyzes the received textbook data. Specifically, it uses the Python libraries NLTK and spaCy to analyze the content of each chapter and section of the textbook using natural language processing technology. The input is the textbook data sent to the server, and the output is the analyzed text data. Specifically, the server tokenizes the textbook data and extracts important keywords and phrases.

[0080] Step 3:

[0081] Storage in the database

[0082] The server stores the analyzed textbook content in a database. Specifically, it uses a database management system such as MySQL or PostgreSQL. The input is the analyzed text data, and the output is the data stored in the database. Specifically, the server organizes the data by chapter and section and creates indexes to enable efficient searches.

[0083] Step 4:

[0084] Extraction of learning content based on curriculum guidelines

[0085] The server extracts learning content based on the curriculum guidelines. Specifically, it uses rule-based algorithms and machine learning models to match the content of the textbook with the curriculum guidelines. The input is the textbook data stored in the database and the curriculum guidelines, and the output is the extracted learning content. Specifically, the server extracts relevant textbook sections based on the learning objectives described in the curriculum guidelines.

[0086] Step 5:

[0087] Providing learning content

[0088] The server provides the extracted learning content to the user through a web application. The terminal displays the learning content through the web browser accessed by the user. The input is the extracted learning content, and the output is the learning content provided to the user. Specifically, the server uses front-end frameworks such as React and Angular to provide an interface that the user can operate intuitively.

[0089] (Application example 1)

[0090] Next, a description will be given of Application Example 1 of Embodiment 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."

[0091] In the field of education, the workload of teachers is increasing and staff shortages are becoming a serious problem. There are also issues such as the difficulty of formulating effective learning plans based on curriculum guidelines and managing learning progress. Furthermore, there is a lack of systems that can efficiently analyze the content of teaching materials and propose optimal learning plans for learners. To solve these issues, a system is needed that can efficiently study curriculum guidelines and textbook content, propose learning plans, and manage progress.

[0092] 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.

[0093] In this invention, the server includes a learning means for learning the curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a content analysis means for analyzing the content of the teaching materials and storing the results in a database, a learning plan proposal means for proposing a learning plan based on the curriculum guidelines, and a progress management means for managing learning progress and providing feedback. This reduces the workload of teachers in educational settings, contributes to solving the problem of staff shortages, and enables the creation of effective learning plans and management of learning progress based on the curriculum guidelines.

[0094] A "curriculum guideline" is an official document that outlines the learning content and educational policies established by an educational institution.

[0095] "Textbook content" refers to the content of teaching materials that systematically compile knowledge and information about a specific subject.

[0096] "Learning tools" are methods and tools that allow learners to effectively learn the curriculum and textbook content.

[0097] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[0098] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[0099] "Content analysis means" refers to methods and tools for analyzing the content of teaching materials and storing that information in a database.

[0100] "Study plan suggestion means" refers to methods or tools for proposing optimal study plans to learners based on the curriculum guidelines.

[0101] "Progress management means" are methods and tools for managing learners' learning progress and providing feedback.

[0102] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[0103] "Feedback" means providing evaluation and advice on a learner's learning progress and achievements.

[0104] To put the present invention into practice, it is necessary to build a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system is shown below.

[0105] server

[0106] The server has the following main functions:

[0107] 1. Learning means for curriculum guidelines and textbook contents: The server stores curriculum guidelines and textbook contents in a database and makes them accessible to learners. This includes content analysis means for analyzing the contents of the teaching materials and storing them in a database.

[0108] 2. Question Creation: The server generates test questions based on the content learned. This includes the ability to create test questions for a specified grade, subject, and chapter.

[0109] 3. Explanation creation means: The server generates explanations for the created test questions.

[0110] 4. Means for suggesting learning plans: The server proposes optimal learning plans for learners based on the curriculum guidelines.

[0111] 5. Progress management means: The server manages the learner's learning progress and provides feedback.

[0112] Terminal

[0113] A terminal is a device that a user uses to access a server. Examples include smartphones, tablets, and PCs. A terminal has the following functions:

[0114] 1. Search materials: Users can easily find textbooks and learning materials by scanning barcodes or searching by keyword.

[0115] 2. Display of study plan: The study plan proposed by the server is displayed, and the user can proceed with their studies according to it.

[0116] 3. Progress Management Display: Display learning progress and provide feedback to users.

[0117] User

[0118] The user is a learner or an educator. The user accesses the server using a terminal and performs the following operations:

[0119] 1. Selecting learning materials: The user selects a textbook or learning material and studies its contents.

[0120] 2. Answering test questions: The user answers the test questions generated by the server and checks the results.

[0121] 3. Execution of the study plan: The user proceeds with the study according to the study plan proposed by the server.

[0122] 4. Check progress: Users can check their own learning progress and adjust their learning plan as needed.

[0123] Hardware and software used

[0124] Hardware: smartphones, tablets, PCs, servers

[0125] Software: Python (registered trademark), BarcodeScanner library, requests library, database (e.g., SQLite), AI model (e.g., TENSORFLOW (registered trademark))

[0126] Data processing and calculation

[0127] The server analyzes the content of the learning materials and stores it in a database. This process includes analyzing the content of the learning materials using an AI model. The server also generates a learning plan based on the curriculum guidelines and proposes it to the user. The server also manages the user's learning progress and provides feedback.

[0128] Specific examples

[0129] When a user scans a barcode to purchase a math textbook, the application will retrieve information about the material and suggest an optimal study plan based on the curriculum guidelines. The application will also include a function to allow students to study according to the study plan and manage their progress within the app.

[0130] Prompt Sentence Examples

[0131] Develop an application that, when a user scans a barcode to purchase a math textbook, retrieves the learning material information and suggests an optimal study plan based on the curriculum guidelines. Include a function to progress according to the study plan and manage progress in the app.

[0132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0133] Step 1:

[0134] A user uses a terminal to scan a barcode on a textbook.

[0135] Input: Textbook barcode

[0136] Output: Textbook information (title, author, content, etc.)

[0137] Specific operation: The device uses the barcode scanner function to read the barcode of the textbook and sends the information to the server. The server retrieves the textbook information from the database based on the barcode and sends it back to the device.

[0138] Step 2:

[0139] The device displays textbook information.

[0140] Input: Textbook information (title, author, content, etc.)

[0141] Output: Display detailed information about the textbook

[0142] Specific operation: The terminal displays the textbook information received from the server to the user, who can then check detailed information about the textbook.

[0143] Step 3:

[0144] The server analyzes the contents of the textbook and stores them in a database.

[0145] Input: Textbook content

[0146] Output: Parsed textbook content (stored in a database)

[0147] How it works: The server uses an AI model to analyze the content of the textbook and stores the results in a database. The analysis uses natural language processing technology.

[0148] Step 4:

[0149] The server generates a learning plan based on the curriculum guidelines and proposes it to the user.

[0150] Input: Curriculum guidelines, analyzed textbook content, user learning history

[0151] Output: Learning plan

[0152] Specific operation: The server uses an AI model to generate an optimal learning plan based on the curriculum guidelines, the analyzed textbook content, and the user's learning history. The generated learning plan is sent to the device and displayed to the user.

[0153] Step 5:

[0154] The user progresses through the study according to the study plan.

[0155] Input:Study plan

[0156] Output: Learning progress data

[0157] Specific operation: The user studies according to the study plan displayed on the device. The progress of the study is sent from the device to the server, and the server stores the data in a database.

[0158] Step 6:

[0159] The server manages the learning progress and provides feedback.

[0160] Input: Learning progress data

[0161] Output: Feedback

[0162] Specific operation: The server analyzes the learning progress data stored in the database and generates feedback for the user. The feedback is sent to the terminal and displayed to the user.

[0163] Step 7:

[0164] The user reviews the feedback and adjusts the learning plan as needed.

[0165] Input: Feedback

[0166] Output: Revised lesson plan

[0167] Specific operation: The user checks the feedback displayed on the device and modifies the study plan as necessary. The modified study plan is sent from the device to the server, which stores the data in a database.

[0168] Example 2

[0169] Next, a description will be given of Example 2 of Form 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."

[0170] In conventional educational systems, teachers must manually create test questions, which places a heavy burden on the teacher's work. The shortage of teachers is also a serious problem. Furthermore, it is difficult to quickly create appropriate test questions based on the learning content, which can lead to a decline in the quality of education. To solve these issues, a system is needed that automatically generates test questions from the learning content.

[0171] 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.

[0172] In this invention, the server includes an input means for inputting learning content, a receiving means for receiving the input learning content, a prompt generating means for creating a prompt sentence based on the received learning content and inputting it into the generative AI model, a point extracting means for extracting important points from the generative AI model, a question generating means for generating test questions based on the extracted points, and a providing means for providing the generated test questions. This enables the automatic generation of test questions based on the learning content.

[0173] "Learning content" refers to the information and knowledge that a user inputs in order to learn.

[0174] "Input means" refers to a device or interface that allows a user to input learning content into the system.

[0175] The "receiving means" refers to a device or function that receives the learning content transmitted from the input means.

[0176] A "generative AI model" is a model that uses artificial intelligence to perform a specific task, and in this case is used to extract key points from learning content.

[0177] A "prompt generation means" is a device or function that creates prompt sentences to be input into a generative AI model based on received learning content.

[0178] "Point extraction means" refers to a device or function that uses a generative AI model to extract important points from the learning content.

[0179] "Question generation means" refers to a device or function that generates test questions based on the extracted important points.

[0180] "Providing means" refers to a device or function that provides the generated test questions to the user.

[0181] The present invention relates to a system for automatically generating test questions based on learning content. A specific embodiment of this system will be described below.

[0182] System configuration

[0183] This system is mainly composed of the following hardware and software.

[0184] 1. Terminal: The device on which the user inputs learning content. For example, a computer or tablet.

[0185] 2. Server: A central processing unit that receives training content and generates test questions using a generative AI model. The server has software installed to run the generative AI model (e.g., GPT-4 (registered trademark)).

[0186] Program processing

[0187] Input and receive learning content

[0188] The user inputs the learning content using the terminal. For example, the learning content is "How to find the area of ​​a triangle." The terminal transmits the input learning content to the server.

[0189] The server receives the learning content sent from the device and stores it as text data. The receiving method uses communication protocols such as HTTP requests and WebSocket.

[0190] Generate prompt statement

[0191] The server creates a prompt sentence to be input to the generative AI model based on the received learning content. For example, it generates a prompt sentence like the following:

[0192] Learning content: How to find the area of ​​a triangle

[0193] Extract the key points.

[0194] This prompt sentence is input into the generative AI model.

[0195] Extracting important points

[0196] The server uses a generative AI model (e.g., GPT-4) to extract key points from the learning content. Based on the input prompt, the generative AI model returns the key point, "The formula for calculating the area of ​​a triangle is base x height ÷ 2."

[0197] Generate test questions

[0198] The server generates test questions based on the extracted key points. For example, it generates questions like the following:

[0199] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0200] Providing test questions

[0201] The server transmits the generated test questions to the terminal and provides them to the user, who can check the generated test questions through the terminal.

[0202] Specific examples

[0203] As a concrete example, the following prompt sentence is input into the generative AI model:

[0204] Learning content: How to find the area of ​​a triangle

[0205] Key Point: The formula for the area of ​​a triangle is base x height / 2.

[0206] Question Creation: Create test questions based on these points.

[0207] An example of a problem that may be generated is as follows:

[0208] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0209] In this way, the server extracts important points from the learning content, generates test questions based on them, and provides them to the user, thereby realizing a system.

[0210] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0211] Step 1:

[0212] The user inputs the learning content.

[0213] Input: The user enters the learning content (e.g., "How to find the area of ​​a triangle") into the input form on the device.

[0214] Specific operation: The user enters "How to find the area of ​​a triangle" into the input form on the terminal and clicks the submit button.

[0215] Output: The device sends the input learning content to the server.

[0216] Step 2:

[0217] The server receives the input learning content.

[0218] Input: The learning content sent from the device (e.g., "How to find the area of ​​a triangle").

[0219] Specific operation: The server receives the HTTP request and saves the learning content as text data.

[0220] Output: Text data of the learning content stored on the server.

[0221] Step 3:

[0222] The server creates and inputs prompt sentences to the generative AI model.

[0223] Input: Text data of learning content stored on the server.

[0224] Specific operation: The server creates a prompt sentence like the following based on what it has learned.

[0225] Learning content: How to find the area of ​​a triangle

[0226] Extract the key points.

[0227] Output: The prompt sentence to be input to the generative AI model.

[0228] Step 4:

[0229] The server extracts key points from the generated AI model.

[0230] Input: The prompt text fed into the generative AI model.

[0231] How it works: A generative AI model (e.g., GPT-4) extracts key points based on the prompt and returns results like this:

[0232] The formula for finding the area of ​​a triangle is base x height ÷ 2.

[0233] Output: Extracted key points.

[0234] Step 5:

[0235] The server generates test questions based on the extracted points.

[0236] Input: Extracted key points (e.g., "The formula for the area of ​​a triangle is base x height divided by 2").

[0237] Specific operation: The server generates test questions based on the key points, such as the following:

[0238] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0239] Output: The generated test questions.

[0240] Step 6:

[0241] The server provides the generated test questions to the user.

[0242] Input: The generated test questions.

[0243] Specific operation: The server sends the generated test questions to the device.

[0244] Output: The test questions displayed on the user's device.

[0245] (Application example 2)

[0246] Next, a description will be given of Application Example 2 of Form 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."

[0247] In conventional educational systems, test questions based on learning content are created manually, which places a heavy workload on teachers and creates serious staff shortages. Furthermore, the quality and variety of test questions is limited, making it difficult to accurately assess learners' understanding. Furthermore, there is a need for a system that can quickly generate appropriate test questions based on learning content.

[0248] 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.

[0249] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions. This reduces the workload of teachers, solves the problem of staff shortages, and makes it possible to quickly generate high-quality test questions for accurately assessing learners' understanding.

[0250] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[0251] "Textbook content" refers to the content of teaching materials that describe the knowledge and skills that learners should learn in a particular grade or subject.

[0252] "Learning tools" are the methods and tools that learners use to understand and master the curriculum and textbook content.

[0253] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[0254] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[0255] A "generative AI model" is a model that uses artificial intelligence technology to generate new information and content from data.

[0256] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0257] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions.

[0258] Server Roles

[0259] The server plays a central role in automatically generating test questions based on what the learner has learned. Specifically, the server performs the following processes:

[0260] 1. Learning tools: The server stores the curriculum and textbook contents in a database and makes them accessible to learners.

[0261] 2. Question creation method: The server extracts important points based on the content that the learner has studied and generates test questions based on them.

[0262] 3. Explanation creation means: The server automatically creates explanations for the generated test questions and provides them to the learner.

[0263] 4. Generative AI model: The server automatically generates test questions based on the learning content using a generative AI model, which uses an advanced natural language processing model such as OpenAI's GPT-3.

[0264] 5. Prompt sentence generation means: The server generates appropriate prompt sentences for the generative AI model and creates test questions based on them.

[0265] Device Role

[0266] The terminal is a device that allows learners to access the server, check the learning content, and answer test questions. Terminals include smartphones, tablets, and PCs.

[0267] User Roles

[0268] The user uses the system as a learner. The user accesses the server using a terminal, checks the learning content, and solves the generated test questions. The server automatically provides explanations for the test questions the user answers.

[0269] Specific examples

[0270] For example, if the user learns "How to find the area of ​​a triangle," the server generates the following prompt:

[0271] Create test questions based on the following: How to find the area of ​​a triangle

[0272] By inputting this prompt into the generative AI model, the server automatically generates a test question such as, "If the base of a triangle is 5 cm and the height is 10 cm, find its area." The generated test question is provided to the user via their device, and the user can answer it.

[0273] In this way, by having the server, terminal, and user work together, it becomes possible to quickly generate and provide high-quality test questions based on the learning content.

[0274] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0275] Step 1:

[0276] The server stores the curriculum and textbook contents in a database. It receives learning material data for users as input and saves it in the database. This creates learning resources that users can access.

[0277] Step 2:

[0278] The user accesses the server using a terminal and selects the content to be studied. The user selects the content they want to study as input, and the selection information is sent to the server. The server provides the user with related learning material data based on the selected content.

[0279] Step 3:

[0280] The server extracts important points based on the content the user has studied. It receives the study content data as input and uses natural language processing technology to extract important points. This provides the information that forms the basis of test questions.

[0281] Step 4:

[0282] The server uses a generative AI model to generate prompt sentences based on the extracted key points. The server receives the extracted key points data as input and generates prompt sentences. The generated prompt sentences are input into the generative AI model.

[0283] Step 5:

[0284] The server inputs a prompt sentence into the generative AI model to automatically generate test questions. The generative AI model receives the prompt sentence as input and generates test questions. The generated test questions are saved on the server.

[0285] Step 6:

[0286] The server automatically generates explanations for the generated test questions. The server receives the generated test questions as input and generates explanations using an explanation generator. The generated explanations are saved together with the test questions.

[0287] Step 7:

[0288] The user accesses and answers the generated test questions using a terminal. The server receives the user's answers and stores the answer data. After the user answers, the server automatically provides explanations.

[0289] Step 8:

[0290] The server analyzes the user's answer results and provides feedback. The server receives the user's answer data as input and analyzes it. Based on the analysis results, feedback is generated for the user and provided via the terminal.

[0291] Example 3

[0292] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0293] In the field of education, teachers spend a great deal of time and effort creating test questions based on curriculum guidelines and textbook content and providing explanations for them. Furthermore, as the workload of teachers increases, there is a risk that the quality of education will decline. Furthermore, there is a serious problem of staff shortages, and the introduction of an efficient educational support system is required. To solve these issues, a system is needed that automates the creation of test questions and their explanations, thereby reducing the workload of teachers.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0295] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model. This makes it possible to automate the creation of test questions and their explanations, reducing the workload of teachers and improving the quality of education.

[0296] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[0297] "Textbook content" refers to the content of teaching materials created based on curriculum guidelines, and includes specific information and knowledge that students need to learn.

[0298] "Learning tools" refers to the methods and tools used to learn curriculum and textbook content.

[0299] "Question creation means" refers to the methods and tools used to create test questions based on what has been learned.

[0300] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[0301] A "generative AI model" is a model that uses artificial intelligence technology to generate text and analyze data, and is particularly good at natural language processing.

[0302] A "prompt" is an instruction given to a generative AI model to make it perform a specific task.

[0303] The present invention is a system for reducing the workload of teachers in educational settings and improving the quality of education. This system includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model.

[0304] Hardware and software used

[0305] Hardware: Servers, terminals

[0306] Software: Generative AI models (e.g., GPT-4)

[0307] Specific operation of the system

[0308] 1. The user enters the question

[0309] A user uses the terminal interface to input a test question for which they would like an explanation. For example, the user inputs the question "Find the area of ​​a triangle."

[0310] 2. The device sends the problem to the server

[0311] The terminal receives the questions entered by the user and sends them to the server. Specifically, the terminal uses an HTTP request to send the question data to the server.

[0312] 3. The server sends a prompt to the generative AI model

[0313] Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[0314] The server sends the generated prompt to the generative AI model using an API request.

[0315] 4. Generative AI model generates commentary

[0316] The generative AI model analyzes the prompt received from the server and generates a solution to the problem. For example, it generates an explanation such as, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5 cm and the height is 10 cm, the area is (5 cm 10 cm) / 2 = 25 square centimeters."

[0317] 5. The server sends the commentary to the device.

[0318] The server sends the explanation received from the generative AI model to the device. Specifically, it sends the explanation data to the device using an HTTP response.

[0319] 6. The device displays the explanation to the user

[0320] The terminal displays the explanation received from the server to the user. Specifically, the explanation text is displayed on the terminal screen, allowing the user to understand the process of solving the problem.

[0321] Specific examples

[0322] Input question: "Find the area of ​​a triangle"

[0323] Prompt for generative AI model: "Please explain in detail how you solved the following problem: Find the area of ​​a triangle."

[0324] Generated explanation: "To find the area of ​​a triangle, multiply the base and height and divide by 2. For example, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[0325] In this way, the user can easily understand the process of solving the problem. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0326] Step 1:

[0327] The user enters the problem

[0328] Input: The user uses the terminal interface to enter the test question that requires explanation.

[0329] Specific action: The user enters "Find the area of ​​a triangle" into the input field of the terminal and clicks the submit button.

[0330] Output: The problem data entered into the terminal.

[0331] Step 2:

[0332] The device sends the problem to the server

[0333] Input: The problem data entered by the user.

[0334] Specific behavior: The device sends the problem data to the server using an HTTP POST request.

[0335] Output: The problem data sent to the server.

[0336] Step 3:

[0337] The server sends a prompt to the generative AI model

[0338] Input: The problem data sent to the server.

[0339] Specific operation: Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[0340] Output: The prompt sent to the generative AI model.

[0341] Step 4:

[0342] Generative AI model generates commentary

[0343] Input: The prompt sent to the generative AI model.

[0344] How it works: The generative AI model analyzes the prompt and generates a solution to the problem. For example, it generates an explanation like, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[0345] Output: The generated narrative data.

[0346] Step 5:

[0347] The server sends the commentary to the device.

[0348] Input: Commentary data received from the generative AI model.

[0349] Specific operation: The server sends explanatory data to the terminal using an HTTP response.

[0350] Output: Commentary data sent to the terminal.

[0351] Step 6:

[0352] The device displays the explanation to the user.

[0353] Input: Description data received from the server.

[0354] Specific operation: The device displays the received explanation on the screen, allowing the user to understand the process of solving the problem.

[0355] Output: Explanatory text displayed on the screen.

[0356] (Application example 3)

[0357] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0358] In traditional educational systems, it is difficult to provide detailed solutions to problems solved by students, and there is a lack of support for students to gain a deeper understanding of the problems. Furthermore, due to the heavy workload of teachers and limited time to provide individual feedback, the quality of education can decline. This poses a challenge, as students are unable to fully realize their learning potential.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0360] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing detailed explanations of the answering process based on the created answers. This allows students to be provided with detailed answering processes for the questions they have solved, allowing them to gain a deeper understanding of the questions. It also reduces the workload of teachers and allows them to have more time to provide individual feedback, thereby improving the quality of education.

[0361] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[0362] "Textbook content" refers to the content of learning materials created based on curriculum guidelines.

[0363] "Learning tools" are the methods and tools that students use to learn the curriculum and textbook content.

[0364] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[0365] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[0366] An "answer generation means" is a method or tool for generating an answer to a question.

[0367] An "explanation generating means" is a method or tool for providing a detailed explanation of the solution process based on the generated answer.

[0368] A "system" is a set of devices and programs that function in conjunction with multiple means.

[0369] The system for carrying out this invention comprises a server and a user terminal. The server includes a learning means for learning the curriculum guidelines and textbook contents, a question creation means for creating test questions based on the learned contents, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing a detailed explanation of the answering process based on the created answers.

[0370] Hardware and software used

[0371] Hardware: Servers, smartphones, tablets

[0372] Software: Python, OpenAI API

[0373] Data processing and calculation

[0374] The server receives test questions entered from the user's device and generates answers using a generative AI model. It then provides a detailed explanation of the answering process based on the generated answers. Specifically, the process is carried out as follows:

[0375] 1. Question input: Users input test questions using a smartphone or tablet.

[0376] 2. Answer generation: The server generates an answer to the problem using the OpenAI API. For example, if the problem is "Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm," the answer will be "The area of ​​a triangle is calculated by multiplying the base by the height by 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[0377] 3. Explanation Generation: The server provides a detailed explanation of the solution process based on the generated answer. For example, the server might generate an explanation like, "First, let's check the formula for calculating the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying the formula gives 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[0378] Examples of concrete examples and prompts

[0379] Specific examples

[0380] Question: "Find the area of ​​a triangle. Its base is 5cm and its height is 10cm."

[0381] Answer: "The area of ​​a triangle is base x height ÷ 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[0382] Explanation: First, let's look at the formula for finding the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying the formula we get 5 cm x 10 cm ÷ 2 = 25 square centimeters.

[0383] Prompt Sentence Examples

[0384] Solution generation prompt: "Question: What is the area of ​​a triangle? Its base is 5cm and its height is 10cm. Please generate an answer."

[0385] Explanation-generating prompt: "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Solution: The area of ​​a triangle is base x height ÷ 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters. Please explain your solution in detail."

[0386] This allows students to understand the problem more deeply by providing detailed solutions to the problems they solve, reducing the workload of teachers and freeing up time for individual feedback, thereby improving the quality of education.

[0387] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0388] Step 1:

[0389] The user enters test questions using a smartphone or tablet. The user enters the question text into the application's input form and presses the submit button. The entered question text is sent to the server.

[0390] Input: Test question (e.g., "Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm.")

[0391] Output: The problem statement sent to the server

[0392] Step 2:

[0393] The server calls the generative AI model (OpenAI API) to generate an answer based on the received question. The server sends the question to the generative AI model as a prompt, and the model generates an answer.

[0394] Input: The question sent to the server

[0395] Data processing: Convert the problem statement into a prompt statement (e.g., "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Please generate the answer.")

[0396] Output: The answer returned by the generative AI model (e.g., "The area of ​​a triangle is calculated by multiplying the base by the height and dividing by 2. Therefore, it is 5 cm x 10 cm ÷ 2 = 25 square centimeters.")

[0397] Step 3:

[0398] The server calls the generative AI model again to provide a detailed explanation of the solution process based on the generated answer. The server sends the question and the generated answer as a prompt to the generative AI model, which then generates an explanation.

[0399] Input: The answer returned by the generative AI model

[0400] Data processing: Convert the problem and answer into a prompt (e.g., "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Answer: The area of ​​a triangle is calculated by multiplying the base by the height and dividing by 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters. Please explain in detail how you solved the problem.").

[0401] Output: Explanation returned by the generative AI model (e.g., "First, let's look at the formula for calculating the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying this formula we get 5 cm x 10 cm ÷ 2 = 25 square centimeters.")

[0402] Step 4:

[0403] The server then sends the generated answers and explanations to the user's device, where the user can check the answers and explanations on the screen of their smartphone or tablet.

[0404] Input: Answer and explanation returned by the generative AI model

[0405] Output: Answers and explanations sent to the user's device

[0406] Step 5:

[0407] The user can deepen their understanding of the problem based on the answers and explanations they receive. The user can also use the application's feedback function to send questions or comments about the answers or explanations to the server.

[0408] Input: Answers and explanations displayed on the user's device

[0409] Output: User understanding and feedback

[0410] In this way, the system provides detailed answers and explanations for the questions entered by the user, supporting the user's learning.

[0411] 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.

[0412] "Example 1"

[0413] In one embodiment of the present invention, an emotion engine is incorporated. This emotion engine recognizes the user's emotions and adjusts the learning content based on those emotions. Specifically, if the user is feeling stressed about the learning content, the emotion engine recognizes that stress and adjusts the learning content to be easier. Also, if the user is feeling excited or happy about the learning content, the emotion engine recognizes that excitement or joy and adjusts the learning content to be more difficult. This makes it possible to provide an optimal learning environment that corresponds to the user's emotions.

[0414] "Example 2"

[0415] In another embodiment of the present invention, the emotion engine adjusts the difficulty of the test questions. Specifically, if the user feels stressed about the test questions, the emotion engine recognizes that stress and lowers the difficulty of the test questions. Also, if the user feels confident about the test questions, the emotion engine recognizes that confidence and increases the difficulty of the test questions. This makes it possible to provide an optimal test environment according to the user's emotions.

[0416] "Example 3"

[0417] Furthermore, in another embodiment of the present invention, the emotion engine adjusts both the learning content and the test questions. Specifically, if the user is feeling stressed about the learning content, the emotion engine recognizes that stress and adjusts the learning content to be easier, while simultaneously lowering the difficulty of the test questions. Also, if the user is feeling excited or happy about the learning content, the emotion engine recognizes that excitement or joy and adjusts the learning content to be more difficult, while simultaneously increasing the difficulty of the test questions. This makes it possible to simultaneously provide an optimal learning environment and test environment that corresponds to the user's emotions.

[0418] The processing flow of each embodiment will be described below.

[0419] "Example 1"

[0420] Step 1: The user begins learning.

[0421] Step 2: The emotion engine recognizes the user's emotion.

[0422] Step 3: The emotion engine adapts the learning content based on the emotions it recognizes.

[0423] Step 4: Provide tailored learning content to users.

[0424] "Example 2"

[0425] Step 1: The user starts the test.

[0426] Step 2: The emotion engine recognizes the user's emotion.

[0427] Step 3: Adjust the difficulty of the test questions based on the emotions recognized by the emotion engine.

[0428] Step 4: Provide the adjusted test questions to the user.

[0429] "Example 3"

[0430] Step 1: The user begins learning.

[0431] Step 2: The emotion engine recognizes the user's emotion.

[0432] Step 3: Adjust the learning content and difficulty of test questions based on the emotions recognized by the emotion engine.

[0433] Step 4: Provide users with tailored learning content and test questions.

[0434] Example 1

[0435] Next, a description will be given of Example 1 of Form 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."

[0436] In the conventional education system, it was difficult to provide an optimal learning environment that suited each learner's feelings and level of understanding when learning curriculum guidelines and textbook content. Furthermore, teachers face a heavy workload and serious staff shortages. This leads to issues such as a decline in learners' learning efficiency and a lack of quality education.

[0437] 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.

[0438] In this invention, the server includes a learning means for learning the curriculum guidelines and textbook content, an analysis means for analyzing text data based on the learned content and extracting important keywords and concepts, a storage means for storing the extracted data in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on those emotions. This makes it possible to provide an optimal learning environment according to the emotions and level of understanding of each learner, contributing to reducing the workload of teachers and resolving the problem of staff shortages.

[0439] "Curriculum guidelines" are official guidelines that define the learning content and goals offered by educational institutions.

[0440] "Textbook content" refers to the learning content and information contained in textbooks used in educational institutions.

[0441] "Learning tools" refers to methods and tools for learning curriculum guidelines and textbook content.

[0442] "Analysis methods" refer to methods and tools for analyzing text data based on learned content and extracting important keywords and concepts.

[0443] "Storage means" refers to the methods and tools used to store the extracted data in a database.

[0444] "Extraction means" refers to methods and tools for extracting content to be learned based on the curriculum guidelines.

[0445] "Emotion recognition means" refers to methods or tools for recognizing a user's emotions and adjusting learning content based on those emotions.

[0446] A "database" is a system for systematically organizing and storing information.

[0447] "User" refers to an individual who uses this system to study.

[0448] A "server" refers to a computer system that manages the processing of the entire system and analyzes and stores various data.

[0449] This invention is a system for use in educational settings, and has a learning means for studying curriculum guidelines and textbook contents. Specifically, the system analyzes the contents of each chapter and section of a textbook and stores them in a database. It also extracts the content to be studied based on the curriculum guidelines and then studies it.

[0450] The server uses Python's NLTK library to analyze the content of each chapter and section of textbooks used in educational settings. NLTK is used to tokenize the text and extract important keywords and concepts. For example, when analyzing Chapter 1, "Integers and Fractions," of a junior high school mathematics textbook, the server extracts keywords such as "integer," "fraction," "reduced fraction," and "common fraction." The extracted data is stored in a MySQL database.

[0451] The server also uses the NLTK library to parse the text of the curriculum guidelines and extract the learning content. The text is tokenized and learning objectives and important topics are extracted. For example, when extracting the learning objective of "integers and fractions" from the junior high school mathematics curriculum guidelines, the server extracts learning objectives such as "addition, subtraction, multiplication, and division of integers" and "reduction and reduction of fractions" and stores them in a database.

[0452] The device uses an emotion engine to recognize the user's emotions. This emotion engine uses OpenCV and TensorFlow to analyze the user's facial expressions and voice to recognize emotions. For example, if a user is feeling stressed while learning "integers and fractions," the device will use its camera and microphone to capture the user's facial expressions and voice, perform facial recognition using OpenCV, and analyze the emotion using TensorFlow. The recognized emotion is sent to the server.

[0453] The server adjusts the learning content based on the user's emotions. If the user is feeling stressed, the server retrieves easier learning content from the database and sends it to the device. Conversely, if the user is feeling excited or happy, the server retrieves more difficult learning content from the database and sends it to the device.

[0454] As a concrete example, the following prompt sentence analyzes the contents of Chapter 1, "Integers and Fractions," of a junior high school mathematics textbook and extracts important keywords.

[0455] "Analyze the content of Chapter 1, "Integers and Fractions," in a junior high school mathematics textbook and extract important keywords. Also, extract learning objectives based on the curriculum guidelines and store them in a database. If the user feels stressed while studying, use an emotion engine to adjust the learning content."

[0456] In this way, it becomes possible to provide an optimal learning environment that suits each individual learner's feelings and level of understanding, which contributes to reducing the workload of teachers and resolving the problem of staff shortages.

[0457] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0458] Step 1:

[0459] The server reads PDF files of textbooks used in educational settings. It receives the PDF files of textbooks as input and generates text data as output. Specifically, the server opens the PDF files and extracts the text from each page.

[0460] Step 2:

[0461] The server analyzes the extracted text data. It receives the text data as input and extracts important keywords and concepts as output. Specifically, the server uses Python's NLTK library to tokenize the text and extract frequently occurring words and phrases.

[0462] Step 3:

[0463] The server stores the extracted keywords and concepts in a database. It receives the extracted keywords and concepts as input and saves them in the database as output. Specifically, the server connects to a MySQL database, creates tables for each chapter and section, and inserts data.

[0464] Step 4:

[0465] The server reads the PDF file of the curriculum guidelines. It receives the PDF file of the curriculum guidelines as input and generates text data as output. Specifically, the server opens the PDF file and extracts the text from each page.

[0466] Step 5:

[0467] The server analyzes the text data of the curriculum. It receives the text data as input and extracts learning objectives and important topics as output. Specifically, the server uses the NLTK library to tokenize the text and extract learning objectives and important topics.

[0468] Step 6:

[0469] The server stores the extracted learning objectives and topics in a database. It receives the extracted learning objectives and topics as input and saves them in the database as output. Specifically, the server connects to the database and inserts data into the appropriate tables.

[0470] Step 7:

[0471] The device uses a camera and microphone to capture the user's facial expressions and voice to recognize the user's emotions. It receives the user's facial and voice data as input and generates the captured data as output. Specifically, the device activates the camera and microphone and records the user's facial expressions and voice.

[0472] Step 8:

[0473] The device analyzes the captured data. It receives captured facial and voice data as input and recognizes the user's emotions as output. Specifically, the device uses OpenCV for facial recognition and TensorFlow for emotion analysis.

[0474] Step 9:

[0475] The terminal transmits the recognized emotion data to the server. The terminal receives the recognized emotion data as input and transmits it as output to the server. In specific operations, the terminal transmits the emotion data to the server via a network.

[0476] Step 10:

[0477] The server adjusts the learning content based on the user's emotional data. It receives the emotional data as input and generates adjusted learning content as output. Specifically, the server retrieves appropriate learning content from the database and adjusts the difficulty level according to the user's emotions.

[0478] Step 11:

[0479] The server transmits the adjusted learning content to the terminal. It receives the adjusted learning content as input and transmits it as output to the terminal. In specific operation, the server transmits the learning content to the terminal via a network.

[0480] Step 12:

[0481] The terminal presents the adjusted learning content received from the server to the user. The terminal receives the adjusted learning content as input and displays it to the user as output. Specifically, the terminal displays the learning content on the screen, allowing the user to continue learning.

[0482] (Application example 1)

[0483] Next, a description will be given of Application Example 1 of Embodiment 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."

[0484] Conventional educational systems provide uniform learning content without considering the learner's emotions, which can lead to stress and, conversely, to little excitement or joy, resulting in reduced learning effectiveness. Furthermore, teachers in the field face heavy workloads and serious staff shortages. To solve these issues, a system is needed that provides an optimal learning environment that responds to the learner's emotions.

[0485] 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.

[0486] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on the emotions. This provides an optimal learning environment according to the learner's emotions, reduces the workload of teachers in educational settings, and solves the problem of staff shortages.

[0487] "Curriculum guidelines" are official guidelines that define the content and goals that learners should learn at an educational institution.

[0488] "Textbook content" refers to the content of teaching materials that contain the specific knowledge and information that learners should learn.

[0489] "Learning tools" are the methods and tools that learners use to learn curriculum and textbook content.

[0490] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[0491] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[0492] An "emotion recognition means" is a method or tool for recognizing a user's emotions and adjusting the learning content based on those emotions.

[0493] A "database" is a system for systematically organizing and storing information.

[0494] An "educational setting" is a place where learners receive education, such as a school or cram school.

[0495] "Reducing workload" refers to reducing the workload of teachers and staff and improving efficiency.

[0496] The "staffing shortage problem" refers to a situation in which there are not enough teachers and staff members.

[0497] As an embodiment of the present invention, the following system is constructed.

[0498] System Overview

[0499] This system is a learning support system used in educational settings, and includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on those emotions.

[0500] Hardware and software used

[0501] Hardware: Camera, microphone, computer

[0502] Software: OpenCV (image processing library), EmotionRecognizer (emotion recognition library), TaskManager (task management library), Database (database management library)

[0503] Program processing explanation

[0504] emotion recognition means

[0505] The server uses a camera and microphone to capture the user's facial expressions and voice. This data is then processed using OpenCV and analyzed by EmotionRecognizer. As a result of the analysis, the user's emotions (e.g., stress, excitement, joy, etc.) are recognized.

[0506] Adjusting learning content

[0507] The server uses TaskManager to adjust the learning content in real time based on the recognized emotions: for example, if the user is stressed, the learning content will be made easier, and conversely, if the user is excited or happy, the learning content will be made more difficult.

[0508] Database Management

[0509] The server stores the recognized emotion data and adjusted learning content in a database, which allows for later analysis of the data and evaluation of learner tendencies and performance.

[0510] Specific examples

[0511] For example, while a user is solving a math problem, their facial expressions and voice are captured through a camera and microphone. If the EmotionRecognizer detects that the user is feeling stressed, the TaskManager lowers the difficulty of the problem and provides easier problems. Conversely, if the user is feeling happy, the TaskManager increases the difficulty and provides more challenging problems.

[0512] Prompt Sentence Examples

[0513] "Design a system that recognizes the emotions of workers and adjusts their work based on those emotions. Emotion recognition requires a camera and microphone, and real-time data processing is required to adjust work. Please also provide the specific program code."

[0514] In this way, it is possible to provide an optimal learning environment that suits the learner's emotions, reduce the workload of teachers in the classroom, and solve the problem of staff shortages.

[0515] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0516] Step 1:

[0517] The server uses a camera and a microphone to capture the user's facial expressions and voice. The input is real-time data from the camera and microphone, and the output is the captured image and voice data. Specifically, the camera captures the user's face and the microphone records the user's voice.

[0518] Step 2:

[0519] The server preprocesses the captured image data using OpenCV. The input is the image data obtained in step 1, and the output is the preprocessed image data. Specifically, it performs processes such as image resizing and noise removal.

[0520] Step 3:

[0521] The server inputs the preprocessed image data into EmotionRecognizer to analyze the user's emotions. The input is the preprocessed image data, and the output is the user's emotions (e.g., stress, excitement, joy, etc.). Specifically, EmotionRecognizer extracts facial features from the image data and classifies the emotions.

[0522] Step 4:

[0523] The server inputs the captured voice data into a voice recognition engine to analyze the user's emotions. The input is the voice data obtained in step 1, and the output is the user's emotions. Specifically, the voice recognition engine extracts emotional features from the voice data and classifies the emotions.

[0524] Step 5:

[0525] The server integrates the emotion data obtained in steps 3 and 4 to determine the final emotion. The input is emotion data obtained from images and audio, and the output is the integrated emotion data. Specifically, it compares both emotion data and selects the matching emotion as the final emotion.

[0526] Step 6:

[0527] The server adjusts the learning content using TaskManager based on the integrated emotional data. The input is the integrated emotional data, and the output is the adjusted learning content. Specifically, if the user feels stressed, the learning content is made easier, and conversely, if the user feels excited or happy, the learning content is made more difficult.

[0528] Step 7:

[0529] The server provides the adjusted learning content to the user. The input is the adjusted learning content, and the output is the learning content displayed to the user. Specifically, the learning content is displayed on the user's device, and the user studies it.

[0530] Step 8:

[0531] The server stores the recognized emotion data and adjusted learning content in a database. The input is emotion data and learning content, and the output is data stored in the database. Specifically, the emotion data and learning content are stored in the database so that they can be analyzed later.

[0532] Example 2

[0533] Next, a description will be given of Example 2 of Form 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."

[0534] In conventional learning systems, test questions based on learning content are often created manually, placing a heavy workload on teachers. Furthermore, it is difficult to provide test questions of an appropriate level of difficulty according to the user's learning progress and emotional state, which means that learning effectiveness is not maximized. Furthermore, there is a serious shortage of personnel in the educational field, and efficient learning support is required.

[0535] 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.

[0536] In this invention, the server includes means for inputting learning content, means for analyzing the input learning content and extracting important points, means for generating test questions based on the extracted important points, means for monitoring the user's emotions, means for adjusting the difficulty of the test questions based on the monitored emotions, and means for providing the adjusted test questions to the user. This makes it possible to automatically generate and provide test questions of an appropriate level of difficulty according to the user's learning progress and emotional state, thereby reducing the workload of teachers and contributing to solving the problem of staff shortages in educational settings.

[0537] "Means for inputting learning content" refers to a device or interface that allows a user to input the learning content into the system.

[0538] "Means for analyzing input learning content and extracting important points" refers to technologies and algorithms for analyzing input learning content and extracting important information and keywords from it.

[0539] The "means for generating test questions based on the extracted important points" refers to a technology or algorithm for automatically generating appropriate test questions based on the extracted important points.

[0540] "Means for monitoring user emotions" refers to devices or technologies for detecting a user's emotional state in real time from their facial expressions, voice, etc.

[0541] "Means for adjusting the difficulty of test questions based on monitored emotions" refers to techniques or algorithms for automatically adjusting the difficulty of test questions depending on the user's emotional state.

[0542] The "means for providing adjusted test questions to a user" refers to a device or interface for presenting adjusted test questions to a user.

[0543] MODE FOR CARRYING OUT THE INVENTION

[0544] The present invention is a system that creates test questions based on learning content and adjusts the difficulty of the questions depending on the emotional state of the user. Specific embodiments of this system will be described below.

[0545] Input of learning content

[0546] Users input what they have learned into the system. For example, if a user has learned how to calculate the area of ​​a triangle, they upload that information to the system as a text file. This input is done using a device such as a PC or tablet.

[0547] Analysis of learning content and extraction of important points

[0548] The server analyzes the input learning content and extracts key points. This process uses natural language processing technology. Specifically, it uses generative AI models such as Google's (registered trademark) BERT and OpenAI's GPT-3. This allows it to extract the keyword "how to find the area of ​​a triangle" from the learning content text.

[0549] Generate test questions

[0550] The server generates test questions based on the extracted key points. For example, it generates a question such as, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The server uses a generative AI model to automatically determine the format and content of the questions.

[0551] User Emotion Monitoring

[0552] The device monitors the user's emotions in real time. It uses emotion recognition APIs such as Microsoft's Azure Cognitive Services and IBM's Watson to recognize stress and self-confidence from the user's facial expressions and voice. For example, it uses a camera and microphone to capture the user's facial expressions and voice and analyzes their emotional state.

[0553] Adjusting the difficulty of test questions

[0554] The device uses an emotion engine to send the user's emotional state to the server. If the user is feeling stressed, the server adjusts the difficulty of the problem to be lowered. For example, it changes the problem to "Find the area of ​​a triangle with a base of 4 cm and a height of 5 cm." Conversely, if the user is confident, it adjusts the difficulty of the problem to be higher. For example, it changes the problem to "Find the area of ​​a triangle with a base of 7 cm and a height of 12 cm."

[0555] Providing test questions

[0556] The server sends the adjusted test questions to the terminal and provides them to the user. The user answers the provided test questions to confirm the effectiveness of their learning. For example, the user can confirm their understanding of the learning content by answering the question, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm."

[0557] Prompt Sentence Examples

[0558] Below is an example of a prompt sentence to input to the generative AI model.

[0559] "Based on what the user has learned, generate a test question on how to find the area of ​​a triangle."

[0560] "Adjust the difficulty of the test questions depending on the user's emotions."

[0561] This maximizes the learning effect of the user and provides an optimal testing environment.

[0562] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0563] Step 1: Enter your learning content

[0564] Users input what they have learned into the system. For example, if a user has learned how to calculate the area of ​​a triangle, they upload that information to the system as a text file. The input text file is sent to the server.

[0565] Step 2: Analyzing learning content and extracting key points

[0566] The server analyzes the input text file. It uses generative AI models such as Google's BERT and OpenAI's GPT-3 to extract key points from the text. Specifically, it uses natural language processing technology to extract the keyword "how to find the area of ​​a triangle." The input is a text file, and the output is the extracted keywords.

[0567] Step 3: Generate test questions

[0568] The server generates test questions based on the extracted key points. It uses a generative AI model to automatically determine the format and content of the questions. For example, it generates a question such as, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The input is the extracted keywords, and the output is the generated test question.

[0569] Step 4: User Emotion Monitoring

[0570] The device monitors the user's emotions in real time. It uses emotion recognition APIs such as Microsoft's Azure Cognitive Services and IBM's Watson to recognize stress and confidence from the user's facial expressions and voice. Specifically, it uses a camera and microphone to capture the user's facial expressions and voice and analyzes their emotional state. The input is the user's facial expression and voice data, and the output is the analyzed emotional state.

[0571] Step 5: Adjust the difficulty of the test questions

[0572] The device uses an emotion engine to send the user's emotional state to the server. If the user is feeling stressed, the server adjusts the difficulty of the questions to be lowered. For example, it changes the question to "Find the area of ​​a triangle with a base of 4 cm and a height of 5 cm." Conversely, if the user is feeling confident, it adjusts the difficulty of the questions to be higher. For example, it changes the question to "Find the area of ​​a triangle with a base of 7 cm and a height of 12 cm." The input is the analyzed emotional state, and the output is the adjusted test questions.

[0573] Step 6: Provide test questions

[0574] The server sends the adjusted test questions to the terminal and provides them to the user. The user answers the provided test questions to confirm the effectiveness of their learning. For example, the user can confirm their understanding of the learning content by answering the question, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The input is the adjusted test questions, and the output is the user's answers.

[0575] (Application example 2)

[0576] Next, a description will be given of Application Example 2 of Form 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."

[0577] While conventional learning systems can create test questions based on the learning content, they lack the ability to adjust the difficulty of the questions according to the user's emotions. This can lead to users feeling stressed or overconfident, which can reduce learning effectiveness. Furthermore, in educational settings, teachers face heavy workloads and staff shortages. To solve these issues, a system that recognizes the user's emotions and provides test questions of an appropriate level of difficulty is needed.

[0578] 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.

[0579] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the difficulty of the test questions. This makes it possible to provide optimal test questions based on the user's emotions, thereby improving learning effectiveness. It also reduces the workload of teachers in educational settings and contributes to solving the problem of staff shortages.

[0580] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[0581] "Textbook content" refers to the content of the teaching materials used for learning in a particular grade or subject.

[0582] "Learning tools" are the methods and tools that learners use to understand and master the curriculum and textbook content.

[0583] "Question creation means" refers to a function or system for automatically generating test questions based on the content learned.

[0584] "Explanation creation means" refers to a function or system for providing explanations for created test questions.

[0585] An "emotion recognition means" is a function or system that detects a user's emotions and provides appropriate feedback or adjustments based on those emotions.

[0586] A "system" is a collection of integrated devices and software in which multiple means and functions work together to achieve a specific purpose.

[0587] The system for implementing this invention comprises the following main components: The server includes a learning means for learning the curriculum guidelines and textbook contents, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the difficulty of the test questions.

[0588] Learning tools

[0589] The server provides an interface for users to study the curriculum and textbook content. This interface can be accessed through a web browser or a smartphone application. Users input their study content and use the learning materials and exercises provided by the system to progress with their studies.

[0590] Question creation method

[0591] The server analyzes the content the user has studied and extracts important points. This extraction is done using natural language processing technology. Based on the extracted important points, test questions are automatically generated using a generative AI model. The generated test questions are set to an appropriate level of difficulty according to the user's learning progress.

[0592] Explanation creation method

[0593] The server automatically creates explanations for the generated test questions. These explanations are written in a detailed and easy-to-understand manner to help users understand the questions. The explanations are created by referencing existing educational materials and expert knowledge bases.

[0594] emotion recognition means

[0595] The server uses sensor devices such as cameras and microphones to recognize the user's emotions. This allows it to analyze the user's emotions from their facial expressions and tone of voice. For emotion recognition, it uses a machine learning model to determine whether the user is feeling stressed or confident. The difficulty of the test questions is adjusted in real time depending on the user's emotions.

[0596] Specific examples

[0597] For example, if a user studies "How to find the area of ​​a triangle," the system operates as follows: When the user inputs their learning content, the server extracts key points and generates test questions related to "How to find the area of ​​a triangle." As the user works on the test questions, the system recognizes their emotions through the camera and microphone, lowering the difficulty of the questions if the user is feeling stressed and raising the difficulty if the user is feeling confident.

[0598] Prompt Sentence Examples

[0599] Below is an example of a prompt sentence to input to the generative AI model.

[0600] "The user has learned how to calculate the area of ​​a triangle. Extract the key points and generate test questions based on them. Also, if the user's emotion is recognized as 'confident,' increase the difficulty of the questions."

[0601] In this way, a system is provided that can maximize the learning effect of users and reduce the workload of teachers in educational settings.

[0602] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0603] Step 1:

[0604] The user inputs the learning content.

[0605] The user inputs the learning content (e.g., "How to calculate the area of ​​a triangle") using the terminal. The input data is sent to the server.

[0606] Step 2:

[0607] The server analyzes the learning content and extracts important points.

[0608] The server analyzes the received learning content using natural language processing techniques. Specifically, it uses libraries such as TextBlob to extract frequently occurring words and phrases from the learning content. This allows it to identify key points. The input is the text data of the learning content, and the output is a list of key points.

[0609] Step 3:

[0610] The server generates test questions based on key points.

[0611] The server inputs the extracted key points into a generative AI model to generate test questions. The generative AI model creates appropriate test questions based on the prompt. The input is a list of key points, and the output is the generated test questions.

[0612] Step 4:

[0613] The server creates explanations for the generated test questions.

[0614] The server automatically generates explanations for the generated test questions, referencing existing educational materials and expert knowledge bases. The input is the generated test questions, and the output is the corresponding explanations.

[0615] Step 5:

[0616] The user works through the test questions.

[0617] The user uses a terminal to answer test questions provided by the server. The user's answers are sent to the server. The input is the user's answers, and the output is the answer data.

[0618] Step 6:

[0619] The server recognizes the user's emotions.

[0620] The server recognizes the user's emotions using sensor devices such as cameras and microphones. It uses a machine learning model to analyze emotions from the user's facial expressions and tone of voice. The input is sensor data, and the output is the user's emotional state.

[0621] Step 7:

[0622] The server adjusts the difficulty of the test questions according to the user's emotions.

[0623] The server adjusts the difficulty of test questions in real time based on the user's recognized emotions. For example, it lowers the difficulty if the user is stressed and raises the difficulty if the user is confident. The input is the user's emotional state, and the output is the adjusted test questions.

[0624] Step 8:

[0625] The server provides feedback to the user.

[0626] The server provides appropriate feedback based on the user's answer and emotional state. The feedback may include explanations and additional learning resources. The input is the user's answer and emotional state, and the output is a feedback message.

[0627] Example 3

[0628] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0629] In the traditional education system, there are often insufficient explanations to help students understand the content, and the learning content and test questions are not adjusted to reflect students' emotions, resulting in poor learning efficiency. Furthermore, the workload of teachers in the field is increasing, and the problem of staff shortages is becoming more serious.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0631] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion analysis means for analyzing the user's emotions and adjusting the difficulty of the learning content and test questions. This allows students to gain a deeper understanding of the learning content and progress efficiently in their studies. It also reduces the workload of teachers and contributes to solving the problem of staff shortages.

[0632] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[0633] "Textbook content" refers to the content of teaching materials created based on curriculum guidelines, and includes the specific information and knowledge that students learn.

[0634] "Learning tools" refers to the methods and tools students use to learn curriculum and textbook content.

[0635] "Question creation means" refers to the methods and tools used to create test questions based on what has been learned.

[0636] "Explanation creation means" refers to methods and tools for creating explanations for the created test questions.

[0637] "Emotion analysis means" refers to a method or tool for analyzing a user's emotions and adjusting the difficulty of the learning content and test questions.

[0638] A "system" refers to a series of processes or devices that are made up of a combination of multiple means.

[0639] "Users" refers to students and educators who use this system.

[0640] The term "server" refers to a central processing unit that manages the processing of the entire system and executes each means.

[0641] MODE FOR CARRYING OUT THE INVENTION

[0642] This invention is an educational system that includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion analysis means for analyzing a user's emotions and adjusting the difficulty of the learning content and test questions.

[0643] Learning tools

[0644] Users use the learning tools to study the curriculum and textbook content. The learning tools provide digital content such as electronic learning materials and online courses. For example, if a user studies a specific mathematics unit, the system will provide learning materials corresponding to that unit.

[0645] Question creation method

[0646] The server creates test questions based on the content that has been learned. The question creation means includes an algorithm that automatically generates test questions corresponding to a specified grade, field, and chapter. For example, if a user studies the field of geometry in mathematics for the second year of junior high school, the server generates test questions based on that content.

[0647] Explanation creation method

[0648] The server generates an explanation for the created test question. The explanation generation means includes an algorithm that provides a detailed explanation of the process and method of solving the question. For example, after a user solves the question "Find the area of ​​a triangle," the server generates the following explanation:

[0649] 1. Determine the base and height of the triangle.

[0650] 2. Multiply the base and height.

[0651] 3. Divide the result by 2.

[0652] This explanation helps the user understand how to answer the question.

[0653] Emotion analysis means

[0654] The device is equipped with an emotion analysis means for analyzing the user's emotions. The emotion analysis means collects the user's facial expressions and voice data and analyzes emotions using a machine learning model. For example, it uses a camera and microphone to record the user's facial expressions and tone of voice and identifies emotions such as stress and joy.

[0655] The device adjusts the learning content and the difficulty of the test questions based on the analysis results. If the user is feeling stressed, the learning content will be changed to easier ones and the difficulty of the test questions will be lowered. Conversely, if the user is feeling happy or excited, the learning content will be changed to more difficult ones and the difficulty of the test questions will be increased.

[0656] Specific examples

[0657] For example, after a user solves the problem "Find the area of ​​a triangle," the server generates the following explanation:

[0658] 1. The base of a triangle is 5cm and the height is 10cm.

[0659] 2. Multiply the base (5 cm) by the height (10 cm) to get 50 square centimeters.

[0660] 3. Divide 50 square centimeters by 2 to get 25 square centimeters.

[0661] 4. Therefore, the area of ​​the triangle is 25 square centimeters.

[0662] Furthermore, if the user feels stressed while studying, the terminal performs the following process.

[0663] 1. The device collects the user's facial expression data and inputs it into the emotion engine.

[0664] 2. The emotion engine recognizes that the user is feeling stressed.

[0665] 3. The device adjusts the learning content to make it easier and at the same time reduces the difficulty of the test questions.

[0666] Prompt Sentence Examples

[0667] An example of a prompt sentence to input to the generative AI model is as follows:

[0668] "If users experience stress while studying, please explain how you will adjust the difficulty of the study content and test questions."

[0669] Using this prompt sentence, the generative AI model explains how to provide the optimal learning and testing environment according to the user's emotions. The flow of the identification process in Example 3 will be explained with reference to FIG. 21.

[0670] Step 1:

[0671] The user uses the learning means to study the curriculum and textbook contents.

[0672] Input: Curriculum guidelines and textbook contents

[0673] Output: Understanding of learning content

[0674] Specific operation: A user browses digital content such as electronic learning materials and online courses to progress through their studies. For example, if a user is studying a specific unit of mathematics, the system will provide learning materials corresponding to that unit.

[0675] Step 2:

[0676] The server creates test questions based on what has been learned.

[0677] Input: Learning content

[0678] Output: Test question

[0679] Specific operation: The server uses an algorithm to automatically generate test questions corresponding to a specified grade, subject, and chapter. For example, if a user studies the geometry subject of eighth-grade mathematics, the server generates test questions based on that content.

[0680] Step 3:

[0681] The user works through the created test questions.

[0682] Input: Test Question

[0683] Output:Answer

[0684] Specific operation: The user solves the test questions generated by the server and inputs the answers. For example, for the question "Find the area of ​​a triangle," the user performs calculations and inputs the answer into the system.

[0685] Step 4:

[0686] The server generates explanations for the created test questions.

[0687] Input: Test questions, user answers

[0688] Output:Explanation

[0689] Specific operation: The server generates an explanation using an algorithm that provides a detailed explanation of the process and method of solving the problem. For example, after a user solves the problem "Find the area of ​​a triangle," the server generates the following explanation:

[0690] 1. Determine the base and height of the triangle.

[0691] 2. Multiply the base and height.

[0692] 3. Divide the result by 2.

[0693] Step 5:

[0694] The terminal uses an emotion analysis means for analyzing the user's emotions.

[0695] Input: User's facial expression data, voice data

[0696] Output: Emotion analysis results

[0697] How it works: The device uses a camera and microphone to record the user's facial expressions and tone of voice, and then uses machine learning models to analyze their emotions. For example, if the user is frowning, it will determine that they are feeling stressed.

[0698] Step 6:

[0699] The terminal adjusts the learning content and the difficulty of the test questions based on the analysis results.

[0700] Input: Sentiment analysis results

[0701] Output: adjusted learning content, adjusted test questions

[0702] Specific operation: If the user feels stressed, the device changes the learning content to easier ones and also lowers the difficulty of the test questions. Conversely, if the user feels happy or excited, the device changes the learning content to more difficult ones and also increases the difficulty of the test questions.

[0703] (Application example 3)

[0704] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0705] Conventional educational support systems do not adjust the learning content according to the learner's emotions, which can lead to learners feeling stressed or, conversely, losing interest because the content is too easy. Another issue is that the explanations for test questions are insufficient, making it difficult for learners to understand the process of solving the questions. This reduces the effectiveness of learning and increases the workload of teachers in the classroom.

[0706] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0707] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an emotion analysis means for analyzing the user's emotions, and a difficulty adjustment means for adjusting the difficulty of the learning content and test questions in accordance with the user's emotions. This makes it possible to provide an optimal learning environment and test environment in accordance with the learner's emotions, thereby improving learning effectiveness.

[0708] "Curriculum guidelines" are official guidelines that define the learning content and goals offered by educational institutions.

[0709] "Textbook content" refers to the specific content of learning materials created based on curriculum guidelines.

[0710] "Learning tools" refers to the methods and tools that learners use to study the curriculum and textbook content.

[0711] "Question creation methods" refer to methods and tools for creating test questions based on what has been learned.

[0712] "Means for creating explanations" refers to methods and tools for creating explanations for the test questions that have been created.

[0713] "Emotion analysis means" refers to methods and tools for analyzing user emotions.

[0714] "Difficulty adjustment means" refers to methods and tools for adjusting the difficulty of learning content and test questions according to the user's emotions.

[0715] A "system" refers to a collection of devices and software that have a series of functions that operate in combination with multiple means.

[0716] A system for carrying out this invention is configured as follows: The server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an emotion analysis means for analyzing the user's emotions, and a difficulty adjustment means for adjusting the difficulty of the learning content and test questions in accordance with the user's emotions.

[0717] Program processing explanation

[0718] The server first provides learning tools for studying the curriculum and textbook content, including online learning materials and interactive learning content that users can access using devices such as smartphones and tablets.

[0719] Next, a question creation means is activated to create test questions based on the content learned. This means automatically generates test questions corresponding to the specified grade, field, and chapter. The generated test questions are provided at an appropriate time according to the user's learning progress.

[0720] The explanation creation means for creating explanations for the created test questions automatically generates detailed explanations using a generative AI model. The explanations provide detailed explanations of the process and method of solving the questions, making it easier for users to understand the questions.

[0721] The emotion analysis means uses the smartphone's camera and microphone to analyze the user's emotions from their facial expressions and voice. The analyzed emotion data is used to evaluate how the user feels about the learning content in real time.

[0722] The difficulty level adjustment means adjusts the difficulty of the learning content and test questions based on the data obtained from the emotion analysis means. For example, if the user is feeling stressed, the learning content is adjusted to be easier and the difficulty of the test questions is also lowered. Conversely, if the user is feeling excited or happy, the learning content is adjusted to be more difficult and the difficulty of the test questions is also increased.

[0723] Specific examples

[0724] As a concrete example, consider a case where a user is working on a problem to "find the area of ​​a triangle." If the user is feeling stressed, the system can lower the difficulty of the problem and provide a brief explanation. An example of a prompt to be input to the generative AI model is as follows:

[0725] "Generate an explanation for the problem of finding the area of ​​a triangle. The explanation should be simple enough for users who are stressed."

[0726] By using this prompt sentence to have a generative AI model generate an explanation, it is possible to provide the optimal learning environment for the user.

[0727] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0728] Step 1:

[0729] The server provides learning tools for studying curriculum guidelines and textbook content. Users access online learning materials and interactive learning content using devices such as smartphones and tablets. The input is the user's learning progress data, and the output is the learning content accessed by the user.

[0730] Step 2:

[0731] The server operates a question creation means that creates test questions based on the content learned. Test questions corresponding to the specified grade, field, and chapter are automatically generated. The input is the user's learning progress data and information on the curriculum guidelines, and the output is the generated test questions.

[0732] Step 3:

[0733] The server automatically generates detailed explanations for the created test questions using an explanation creation means. Using a generative AI model, it provides detailed explanations of the problem-solving process and method. The input is the generated test question, and the output is the generated explanation.

[0734] Step 4:

[0735] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice. The emotion analysis means analyzes this data and evaluates the user's emotions. The input is the user's facial and voice data, and the output is the analyzed emotion data.

[0736] Step 5:

[0737] The server operates a difficulty level adjustment means that adjusts the learning content and the difficulty of the test questions based on the emotional data obtained from the emotional analysis means. If the user is feeling stressed, the learning content is adjusted to be easier, and the difficulty of the test questions is also lowered at the same time. Conversely, if the user is feeling excited or happy, the learning content is adjusted to be more difficult, and the difficulty of the test questions is also increased at the same time. The input is the analyzed emotional data, and the output is the adjusted learning content and test questions.

[0738] Step 6:

[0739] The server sends the adjusted learning content and test questions to the user's terminal. The user accesses these contents through the terminal and continues learning. The input is the adjusted learning content and test questions, and the output is the learning content and test questions accessed by the user.

[0740] Step 7:

[0741] After the user works on the test questions, the server generates an explanation using the generative AI model. For example, the explanation is generated using a prompt such as, "Please generate an explanation for the problem of finding the area of ​​a triangle. Please keep the explanation simple and suitable for when the user is feeling stressed." The input is the user's answer data and the prompt, and the output is the generated explanation.

[0742] 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.

[0743] 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> ) 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.

[0744] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0745] 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.

[0746] [Second embodiment]

[0747] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0748] 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.

[0749] 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).

[0750] 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.

[0751] 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.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0759] "Example 1"

[0760] The present invention is a system for use in educational settings. This system has a learning means for studying curriculum guidelines and textbook content. Specifically, the system analyzes the content of each chapter and section of the textbook and stores it in a database. Furthermore, the system extracts content to be studied based on the curriculum guidelines and then studies that content.

[0761] "Example 2"

[0762] Furthermore, the system of the present invention has a question creation means for creating test questions based on the content learned. Specifically, important points are extracted from the content learned and questions are created based on them. For example, if the content learned is "how to calculate the area of ​​a triangle," questions related to that content are created.

[0763] "Example 3"

[0764] The system of the present invention also has an explanation creation means for creating explanations for the created test questions. Specifically, the system explains the process and method of solving the created questions. For example, if the created question is "Find the area of ​​a triangle," the system will explain the process in detail. This helps students understand the questions and answer them.

[0765] The processing flow of each embodiment will be described below.

[0766] "Example 1"

[0767] Step 1: The system learns the curriculum and textbook content. Specifically, it analyzes the content of each chapter and section of the textbook and stores it in a database.

[0768] Step 2: Based on the curriculum guidelines, extract the content to be learned and study it.

[0769] "Example 2"

[0770] Step 1: Create test questions based on what you have learned. Specifically, extract important points from what you have learned and create questions based on them.

[0771] Step 2: For example, if the content learned is "How to find the area of ​​a triangle," create a problem related to that.

[0772] "Example 3"

[0773] Step 1: Create an explanation for the test questions you have created. Specifically, explain the process and method of solving the questions you have created.

[0774] Step 2: For example, if the problem you created is "Find the area of ​​a triangle," explain the solution process in detail. This will help students understand the problem and solve it.

[0775] Example 1

[0776] Next, a description will be given of Example 1 of Form 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."

[0777] In conventional educational systems, there is a lack of efficient ways to study curriculum guidelines and teaching materials, which increases the workload of educators and exacerbates the staff shortage problem.In addition, analysis and extraction of learning content is often done manually, which takes time and effort, making it difficult to provide efficient learning support in educational settings.

[0778] 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.

[0779] In this invention, the server includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content. This reduces the workload of educators, contributes to solving the problem of staff shortages, and enables efficient learning support.

[0780] A "curriculum guideline" is a document that outlines the learning content and educational goals set by an educational institution.

[0781] "Teaching material content" refers to the learning content contained in educational materials such as textbooks and reference books.

[0782] "Learning tools" are methods and tools for learning the curriculum and teaching material content.

[0783] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[0784] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[0785] "Analysis means" refers to methods and tools for analyzing the content of each chapter or section of the teaching material and storing it in a database.

[0786] "Extraction means" refers to methods or tools for extracting content to be learned based on the curriculum guidelines.

[0787] "Providing means" refers to the methods and tools used to provide extracted learning content to users.

[0788] "Educator" refers to occupations such as teachers and lecturers who provide instruction and education in educational settings.

[0789] "Workload" refers to the amount and difficulty of the work that educators perform on a daily basis.

[0790] The "staffing shortage problem" refers to a situation in which there are not enough educators in the educational field.

[0791] The present invention is a system for use in educational settings, which provides a means for efficiently learning curriculum guidelines and teaching material content. A specific embodiment of this system will be described below.

[0792] Generating a Program

[0793] The server generates a program for the system to be used in the educational field. This program includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content.

[0794] Program processing

[0795] The server uses natural language processing (NLP) techniques to analyze the content of each chapter and section of the textbook. Specifically, it uses the Python libraries NLTK and spaCy to analyze the text data. The analyzed data is stored in a database such as MySQL or PostgreSQL.

[0796] The server then extracts the learning content based on the curriculum guidelines. This process uses rule-based algorithms and machine learning models. The extracted content is then provided as a web application for users to study. This web application is built using a front-end framework such as React or Angular.

[0797] Specific examples

[0798] For example, if a user inputs "I would like to study Chapter 3 of the junior high school mathematics textbook," the server performs the following process.

[0799] 1. The server analyzes the content of Chapter 3 of the textbook and stores it in the database.

[0800] 2. The server extracts the content to be learned in Chapter 3 based on the curriculum guidelines.

[0801] 3. The extracted content is provided to the user through a web application.

[0802] Example prompts to input to a generative AI model:

[0803] "Analyze the contents of Chapter 3 of a junior high school mathematics textbook and extract the content that should be studied."

[0804] In this way, the system allows users to efficiently learn the necessary learning content in the educational setting.

[0805] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0806] Step 1:

[0807] Textbook data entry

[0808] The user uploads textbook data to the system. The device sends the PDF or text file of the textbook specified by the user to the server. The input is the textbook data file, and the output is the textbook data sent to the server. Specifically, the user selects the textbook file using the file selection dialog on the device and clicks the upload button.

[0809] Step 2:

[0810] Textbook content analysis

[0811] The server analyzes the received textbook data. Specifically, it uses the Python libraries NLTK and spaCy to analyze the content of each chapter and section of the textbook using natural language processing technology. The input is the textbook data sent to the server, and the output is the analyzed text data. Specifically, the server tokenizes the textbook data and extracts important keywords and phrases.

[0812] Step 3:

[0813] Storage in the database

[0814] The server stores the analyzed textbook content in a database. Specifically, it uses a database management system such as MySQL or PostgreSQL. The input is the analyzed text data, and the output is the data stored in the database. Specifically, the server organizes the data by chapter and section and creates indexes to enable efficient searches.

[0815] Step 4:

[0816] Extraction of learning content based on curriculum guidelines

[0817] The server extracts learning content based on the curriculum guidelines. Specifically, it uses rule-based algorithms and machine learning models to match the content of the textbook with the curriculum guidelines. The input is the textbook data stored in the database and the curriculum guidelines, and the output is the extracted learning content. Specifically, the server extracts relevant textbook sections based on the learning objectives described in the curriculum guidelines.

[0818] Step 5:

[0819] Providing learning content

[0820] The server provides the extracted learning content to the user through a web application. The terminal displays the learning content through the web browser accessed by the user. The input is the extracted learning content, and the output is the learning content provided to the user. Specifically, the server uses front-end frameworks such as React and Angular to provide an interface that the user can operate intuitively.

[0821] (Application example 1)

[0822] Next, a description will be given of Application Example 1 of Form 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."

[0823] In the field of education, the workload of teachers is increasing and staff shortages are becoming a serious problem. There are also issues such as the difficulty of formulating effective learning plans based on curriculum guidelines and managing learning progress. Furthermore, there is a lack of systems that can efficiently analyze the content of teaching materials and propose optimal learning plans for learners. To solve these issues, a system is needed that can efficiently study curriculum guidelines and textbook content, propose learning plans, and manage progress.

[0824] 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.

[0825] In this invention, the server includes a learning means for learning the curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a content analysis means for analyzing the content of the teaching materials and storing the results in a database, a learning plan proposal means for proposing a learning plan based on the curriculum guidelines, and a progress management means for managing learning progress and providing feedback. This reduces the workload of teachers in educational settings, contributes to solving the problem of staff shortages, and enables the creation of effective learning plans and management of learning progress based on the curriculum guidelines.

[0826] A "curriculum guideline" is an official document that outlines the learning content and educational policies established by an educational institution.

[0827] "Textbook content" refers to the content of teaching materials that systematically compile knowledge and information about a specific subject.

[0828] "Learning tools" are methods and tools that allow learners to effectively learn the curriculum and textbook content.

[0829] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[0830] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[0831] "Content analysis means" refers to methods and tools for analyzing the content of teaching materials and storing that information in a database.

[0832] "Study plan suggestion means" refers to methods or tools for proposing optimal study plans to learners based on the curriculum guidelines.

[0833] "Progress management means" are methods and tools for managing learners' learning progress and providing feedback.

[0834] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[0835] "Feedback" means providing evaluation and advice on a learner's learning progress and achievements.

[0836] To put the present invention into practice, it is necessary to build a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system is shown below.

[0837] server

[0838] The server has the following main functions:

[0839] 1. Learning means for curriculum guidelines and textbook contents: The server stores curriculum guidelines and textbook contents in a database and makes them accessible to learners. This includes content analysis means for analyzing the contents of the teaching materials and storing them in a database.

[0840] 2. Question Creation: The server generates test questions based on the content learned. This includes the ability to create test questions for a specified grade, subject, and chapter.

[0841] 3. Explanation creation means: The server generates explanations for the created test questions.

[0842] 4. Means for suggesting learning plans: The server proposes optimal learning plans for learners based on the curriculum guidelines.

[0843] 5. Progress management means: The server manages the learner's learning progress and provides feedback.

[0844] Terminal

[0845] A terminal is a device that a user uses to access a server. Examples include smartphones, tablets, and PCs. A terminal has the following functions:

[0846] 1. Search materials: Users can easily find textbooks and learning materials by scanning barcodes or searching by keyword.

[0847] 2. Display of study plan: The study plan proposed by the server is displayed, and the user can proceed with their studies according to it.

[0848] 3. Progress Management Display: Display learning progress and provide feedback to users.

[0849] User

[0850] The user is a learner or an educator. The user accesses the server using a terminal and performs the following operations:

[0851] 1. Selecting learning materials: The user selects a textbook or learning material and studies its contents.

[0852] 2. Answering test questions: The user answers the test questions generated by the server and checks the results.

[0853] 3. Execution of the study plan: The user proceeds with the study according to the study plan proposed by the server.

[0854] 4. Check progress: Users can check their own learning progress and adjust their learning plan as needed.

[0855] Hardware and software used

[0856] Hardware: smartphones, tablets, PCs, servers

[0857] Software: Python, BarcodeScanner library, requests library, database (e.g., SQLite), AI model (e.g., TensorFlow)

[0858] Data processing and calculation

[0859] The server analyzes the content of the learning materials and stores it in a database. This process includes analyzing the content of the learning materials using an AI model. The server also generates a learning plan based on the curriculum guidelines and proposes it to the user. The server also manages the user's learning progress and provides feedback.

[0860] Specific examples

[0861] When a user scans a barcode to purchase a math textbook, the application will retrieve information about the material and suggest an optimal study plan based on the curriculum guidelines. The application will also include a function to allow students to study according to the study plan and manage their progress within the app.

[0862] Prompt Sentence Examples

[0863] Develop an application that, when a user scans a barcode to purchase a math textbook, retrieves the learning material information and suggests an optimal study plan based on the curriculum guidelines. Include a function to progress according to the study plan and manage progress in the app.

[0864] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0865] Step 1:

[0866] A user uses a terminal to scan a barcode on a textbook.

[0867] Input: Textbook barcode

[0868] Output: Textbook information (title, author, content, etc.)

[0869] Specific operation: The device uses the barcode scanner function to read the barcode of the textbook and sends the information to the server. The server retrieves the textbook information from the database based on the barcode and sends it back to the device.

[0870] Step 2:

[0871] The device displays textbook information.

[0872] Input: Textbook information (title, author, content, etc.)

[0873] Output: Display detailed information about the textbook

[0874] Specific operation: The terminal displays the textbook information received from the server to the user, who can then check detailed information about the textbook.

[0875] Step 3:

[0876] The server analyzes the contents of the textbook and stores them in a database.

[0877] Input: Textbook content

[0878] Output: Parsed textbook content (stored in a database)

[0879] How it works: The server uses an AI model to analyze the content of the textbook and stores the results in a database. The analysis uses natural language processing technology.

[0880] Step 4:

[0881] The server generates a learning plan based on the curriculum guidelines and proposes it to the user.

[0882] Input: Curriculum guidelines, analyzed textbook content, user learning history

[0883] Output: Learning plan

[0884] Specific operation: The server uses an AI model to generate an optimal learning plan based on the curriculum guidelines, the analyzed textbook content, and the user's learning history. The generated learning plan is sent to the device and displayed to the user.

[0885] Step 5:

[0886] The user progresses through the study according to the study plan.

[0887] Input:Study plan

[0888] Output: Learning progress data

[0889] Specific operation: The user studies according to the study plan displayed on the device. The progress of the study is sent from the device to the server, and the server stores the data in a database.

[0890] Step 6:

[0891] The server manages the learning progress and provides feedback.

[0892] Input: Learning progress data

[0893] Output: Feedback

[0894] Specific operation: The server analyzes the learning progress data stored in the database and generates feedback for the user. The feedback is sent to the terminal and displayed to the user.

[0895] Step 7:

[0896] The user reviews the feedback and adjusts the learning plan as needed.

[0897] Input: Feedback

[0898] Output: Revised lesson plan

[0899] Specific operation: The user checks the feedback displayed on the device and modifies the study plan as necessary. The modified study plan is sent from the device to the server, which stores the data in a database.

[0900] Example 2

[0901] Next, a description will be given of Example 2 of Form 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."

[0902] In conventional educational systems, teachers must manually create test questions, which places a heavy burden on the teacher's work. The shortage of teachers is also a serious problem. Furthermore, it is difficult to quickly create appropriate test questions based on the learning content, which can lead to a decline in the quality of education. To solve these issues, a system is needed that automatically generates test questions from the learning content.

[0903] 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.

[0904] In this invention, the server includes an input means for inputting learning content, a receiving means for receiving the input learning content, a prompt generating means for creating a prompt sentence based on the received learning content and inputting it into the generative AI model, a point extracting means for extracting important points from the generative AI model, a question generating means for generating test questions based on the extracted points, and a providing means for providing the generated test questions. This enables the automatic generation of test questions based on the learning content.

[0905] "Learning content" refers to the information and knowledge that a user inputs in order to learn.

[0906] "Input means" refers to a device or interface that allows a user to input learning content into the system.

[0907] The "receiving means" refers to a device or function that receives the learning content transmitted from the input means.

[0908] A "generative AI model" is a model that uses artificial intelligence to perform a specific task, and in this case is used to extract key points from learning content.

[0909] A "prompt generation means" is a device or function that creates prompt sentences to be input into a generative AI model based on received learning content.

[0910] "Point extraction means" refers to a device or function that uses a generative AI model to extract important points from the learning content.

[0911] "Question generation means" refers to a device or function that generates test questions based on the extracted important points.

[0912] "Providing means" refers to a device or function that provides the generated test questions to the user.

[0913] The present invention relates to a system for automatically generating test questions based on learning content. A specific embodiment of this system will be described below.

[0914] System configuration

[0915] This system is mainly composed of the following hardware and software.

[0916] 1. Terminal: The device on which the user inputs learning content. For example, a computer or tablet.

[0917] 2. Server: A central processing unit that receives the training data and generates test questions using the generative AI model. The server has software installed to run the generative AI model (e.g., GPT-4).

[0918] Program processing

[0919] Input and receive learning content

[0920] The user inputs the learning content using the terminal. For example, the learning content is "How to find the area of ​​a triangle." The terminal transmits the input learning content to the server.

[0921] The server receives the learning content sent from the device and stores it as text data. The receiving method uses communication protocols such as HTTP requests and WebSocket.

[0922] Generate prompt statement

[0923] The server creates a prompt sentence to be input to the generative AI model based on the received learning content. For example, it generates a prompt sentence like the following:

[0924] Learning content: How to find the area of ​​a triangle

[0925] Extract the key points.

[0926] This prompt sentence is input into the generative AI model.

[0927] Extracting important points

[0928] The server uses a generative AI model (e.g., GPT-4) to extract key points from the learning content. Based on the input prompt, the generative AI model returns the key point, "The formula for calculating the area of ​​a triangle is base x height ÷ 2."

[0929] Generate test questions

[0930] The server generates test questions based on the extracted key points. For example, it generates questions like the following:

[0931] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0932] Providing test questions

[0933] The server transmits the generated test questions to the terminal and provides them to the user, who can check the generated test questions through the terminal.

[0934] Specific examples

[0935] As a concrete example, the following prompt sentence is input into the generative AI model:

[0936] Learning content: How to find the area of ​​a triangle

[0937] Key Point: The formula for the area of ​​a triangle is base x height / 2.

[0938] Question Creation: Create test questions based on these points.

[0939] An example of a problem that may be generated is as follows:

[0940] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0941] In this way, the server extracts important points from the learning content, generates test questions based on them, and provides them to the user, thereby realizing a system.

[0942] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0943] Step 1:

[0944] The user inputs the learning content.

[0945] Input: The user enters the learning content (e.g., "How to find the area of ​​a triangle") into the input form on the device.

[0946] Specific operation: The user enters "How to find the area of ​​a triangle" into the input form on the terminal and clicks the submit button.

[0947] Output: The device sends the input learning content to the server.

[0948] Step 2:

[0949] The server receives the input learning content.

[0950] Input: The learning content sent from the device (e.g., "How to find the area of ​​a triangle").

[0951] Specific operation: The server receives the HTTP request and saves the learning content as text data.

[0952] Output: Text data of the learning content stored on the server.

[0953] Step 3:

[0954] The server creates and inputs prompt sentences to the generative AI model.

[0955] Input: Text data of learning content stored on the server.

[0956] Specific operation: The server creates a prompt sentence like the following based on what it has learned.

[0957] Learning content: How to find the area of ​​a triangle

[0958] Extract the key points.

[0959] Output: The prompt sentence to be input to the generative AI model.

[0960] Step 4:

[0961] The server extracts key points from the generated AI model.

[0962] Input: The prompt text fed into the generative AI model.

[0963] How it works: A generative AI model (e.g., GPT-4) extracts key points based on the prompt and returns results like this:

[0964] The formula for finding the area of ​​a triangle is base x height ÷ 2.

[0965] Output: Extracted key points.

[0966] Step 5:

[0967] The server generates test questions based on the extracted points.

[0968] Input: Extracted key points (e.g., "The formula for the area of ​​a triangle is base x height divided by 2").

[0969] Specific operation: The server generates test questions based on the key points, such as the following:

[0970] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[0971] Output: The generated test questions.

[0972] Step 6:

[0973] The server provides the generated test questions to the user.

[0974] Input: The generated test questions.

[0975] Specific operation: The server sends the generated test questions to the device.

[0976] Output: The test questions displayed on the user's device.

[0977] (Application example 2)

[0978] Next, a description will be given of Application Example 2 of Form 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."

[0979] In conventional educational systems, test questions based on learning content are created manually, which places a heavy workload on teachers and creates serious staff shortages. Furthermore, the quality and variety of test questions is limited, making it difficult to accurately assess learners' understanding. Furthermore, there is a need for a system that can quickly generate appropriate test questions based on learning content.

[0980] 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.

[0981] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions. This reduces the workload of teachers, solves the problem of staff shortages, and makes it possible to quickly generate high-quality test questions for accurately assessing learners' understanding.

[0982] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[0983] "Textbook content" refers to the content of teaching materials that describe the knowledge and skills that learners should learn in a particular grade or subject.

[0984] "Learning tools" are the methods and tools that learners use to understand and master the curriculum and textbook content.

[0985] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[0986] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[0987] A "generative AI model" is a model that uses artificial intelligence technology to generate new information and content from data.

[0988] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0989] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions.

[0990] Server Roles

[0991] The server plays a central role in automatically generating test questions based on what the learner has learned. Specifically, the server performs the following processes:

[0992] 1. Learning tools: The server stores the curriculum and textbook contents in a database and makes them accessible to learners.

[0993] 2. Question creation method: The server extracts important points based on the content that the learner has studied and generates test questions based on them.

[0994] 3. Explanation creation means: The server automatically creates explanations for the generated test questions and provides them to the learner.

[0995] 4. Generative AI model: The server automatically generates test questions based on the learning content using a generative AI model, which uses an advanced natural language processing model such as OpenAI's GPT-3.

[0996] 5. Prompt sentence generation means: The server generates appropriate prompt sentences for the generative AI model and creates test questions based on them.

[0997] Device Role

[0998] The terminal is a device that allows learners to access the server, check the learning content, and answer test questions. Terminals include smartphones, tablets, and PCs.

[0999] User Roles

[1000] The user uses the system as a learner. The user accesses the server using a terminal, checks the learning content, and solves the generated test questions. The server automatically provides explanations for the test questions the user answers.

[1001] Specific examples

[1002] For example, if the user learns "How to find the area of ​​a triangle," the server generates the following prompt:

[1003] Create test questions based on the following: How to find the area of ​​a triangle

[1004] By inputting this prompt into the generative AI model, the server automatically generates a test question such as, "If the base of a triangle is 5 cm and the height is 10 cm, find its area." The generated test question is provided to the user via their device, and the user can answer it.

[1005] In this way, by having the server, terminal, and user work together, it becomes possible to quickly generate and provide high-quality test questions based on the learning content.

[1006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1007] Step 1:

[1008] The server stores the curriculum and textbook contents in a database. It receives learning material data for users as input and saves it in the database. This creates learning resources that users can access.

[1009] Step 2:

[1010] The user accesses the server using a terminal and selects the content to be studied. The user selects the content they want to study as input, and the selection information is sent to the server. The server provides the user with related learning material data based on the selected content.

[1011] Step 3:

[1012] The server extracts important points based on the content the user has studied. It receives the study content data as input and uses natural language processing technology to extract important points. This provides the information that forms the basis of test questions.

[1013] Step 4:

[1014] The server uses a generative AI model to generate prompt sentences based on the extracted key points. The server receives the extracted key points data as input and generates prompt sentences. The generated prompt sentences are input into the generative AI model.

[1015] Step 5:

[1016] The server inputs a prompt sentence into the generative AI model to automatically generate test questions. The generative AI model receives the prompt sentence as input and generates test questions. The generated test questions are saved on the server.

[1017] Step 6:

[1018] The server automatically generates explanations for the generated test questions. The server receives the generated test questions as input and generates explanations using an explanation generator. The generated explanations are saved together with the test questions.

[1019] Step 7:

[1020] The user accesses and answers the generated test questions using a terminal. The server receives the user's answers and stores the answer data. After the user answers, the server automatically provides explanations.

[1021] Step 8:

[1022] The server analyzes the user's answer results and provides feedback. The server receives the user's answer data as input and analyzes it. Based on the analysis results, feedback is generated for the user and provided via the terminal.

[1023] Example 3

[1024] Next, a description will be given of Example 3 of Form Example 3. 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."

[1025] In the field of education, teachers spend a great deal of time and effort creating test questions based on curriculum guidelines and textbook content and providing explanations for them. Furthermore, as the workload of teachers increases, there is a risk that the quality of education will decline. Furthermore, there is a serious problem of staff shortages, and the introduction of an efficient educational support system is required. To solve these issues, a system is needed that automates the creation of test questions and their explanations, thereby reducing the workload of teachers.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1027] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model. This makes it possible to automate the creation of test questions and their explanations, reducing the workload of teachers and improving the quality of education.

[1028] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[1029] "Textbook content" refers to the content of teaching materials created based on curriculum guidelines, and includes specific information and knowledge that students need to learn.

[1030] "Learning tools" refers to the methods and tools used to learn curriculum and textbook content.

[1031] "Question creation means" refers to the methods and tools used to create test questions based on what has been learned.

[1032] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[1033] A "generative AI model" is a model that uses artificial intelligence technology to generate text and analyze data, and is particularly good at natural language processing.

[1034] A "prompt" is an instruction given to a generative AI model to make it perform a specific task.

[1035] The present invention is a system for reducing the workload of teachers in educational settings and improving the quality of education. This system includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model.

[1036] Hardware and software used

[1037] Hardware: Servers, terminals

[1038] Software: Generative AI models (e.g., GPT-4)

[1039] Specific operation of the system

[1040] 1. The user enters the question

[1041] A user uses the terminal interface to input a test question for which they would like an explanation. For example, the user inputs the question "Find the area of ​​a triangle."

[1042] 2. The device sends the problem to the server

[1043] The terminal receives the questions entered by the user and sends them to the server. Specifically, the terminal uses an HTTP request to send the question data to the server.

[1044] 3. The server sends a prompt to the generative AI model

[1045] Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[1046] The server sends the generated prompt to the generative AI model using an API request.

[1047] 4. Generative AI model generates commentary

[1048] The generative AI model analyzes the prompt received from the server and generates a solution to the problem. For example, it generates an explanation such as, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5 cm and the height is 10 cm, the area is (5 cm 10 cm) / 2 = 25 square centimeters."

[1049] 5. The server sends the commentary to the device.

[1050] The server sends the explanation received from the generative AI model to the device. Specifically, it sends the explanation data to the device using an HTTP response.

[1051] 6. The device displays the explanation to the user

[1052] The terminal displays the explanation received from the server to the user. Specifically, the explanation text is displayed on the terminal screen, allowing the user to understand the process of solving the problem.

[1053] Specific examples

[1054] Input question: "Find the area of ​​a triangle"

[1055] Prompt for generative AI model: "Please explain in detail how you solved the following problem: Find the area of ​​a triangle."

[1056] Generated explanation: "To find the area of ​​a triangle, multiply the base and height and divide by 2. For example, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[1057] In this way, the user can easily understand the process of solving the problem. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1058] Step 1:

[1059] The user enters the problem

[1060] Input: The user uses the terminal interface to enter the test question that requires explanation.

[1061] Specific action: The user enters "Find the area of ​​a triangle" into the input field of the terminal and clicks the submit button.

[1062] Output: The problem data entered into the terminal.

[1063] Step 2:

[1064] The device sends the problem to the server

[1065] Input: The problem data entered by the user.

[1066] Specific behavior: The device sends the problem data to the server using an HTTP POST request.

[1067] Output: The problem data sent to the server.

[1068] Step 3:

[1069] The server sends a prompt to the generative AI model

[1070] Input: The problem data sent to the server.

[1071] Specific operation: Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[1072] Output: The prompt sent to the generative AI model.

[1073] Step 4:

[1074] Generative AI model generates commentary

[1075] Input: The prompt sent to the generative AI model.

[1076] How it works: The generative AI model analyzes the prompt and generates a solution to the problem. For example, it generates an explanation like, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[1077] Output: The generated narrative data.

[1078] Step 5:

[1079] The server sends the commentary to the device.

[1080] Input: Commentary data received from the generative AI model.

[1081] Specific operation: The server sends explanatory data to the terminal using an HTTP response.

[1082] Output: Commentary data sent to the terminal.

[1083] Step 6:

[1084] The device displays the explanation to the user.

[1085] Input: Description data received from the server.

[1086] Specific operation: The device displays the received explanation on the screen, allowing the user to understand the process of solving the problem.

[1087] Output: Explanatory text displayed on the screen.

[1088] (Application example 3)

[1089] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1090] In traditional educational systems, it is difficult to provide detailed solutions to problems solved by students, and there is a lack of support for students to gain a deeper understanding of the problems. Furthermore, due to the heavy workload of teachers and limited time to provide individual feedback, the quality of education can decline. This poses a challenge, as students are unable to fully realize their learning potential.

[1091] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1092] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing detailed explanations of the answering process based on the created answers. This allows students to be provided with detailed answering processes for the questions they have solved, allowing them to gain a deeper understanding of the questions. It also reduces the workload of teachers and allows them to have more time to provide individual feedback, thereby improving the quality of education.

[1093] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[1094] "Textbook content" refers to the content of learning materials created based on curriculum guidelines.

[1095] "Learning tools" are the methods and tools that students use to learn the curriculum and textbook content.

[1096] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[1097] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[1098] An "answer generation means" is a method or tool for generating an answer to a question.

[1099] An "explanation generating means" is a method or tool for providing a detailed explanation of the solution process based on the generated answer.

[1100] A "system" is a set of devices and programs that function in conjunction with multiple means.

[1101] The system for carrying out this invention comprises a server and a user terminal. The server includes a learning means for learning the curriculum guidelines and textbook contents, a question creation means for creating test questions based on the learned contents, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing a detailed explanation of the answering process based on the created answers.

[1102] Hardware and software used

[1103] Hardware: Servers, smartphones, tablets

[1104] Software: Python, OpenAI API

[1105] Data processing and calculation

[1106] The server receives test questions entered from the user's device and generates answers using a generative AI model. It then provides a detailed explanation of the answering process based on the generated answers. Specifically, the process is carried out as follows:

[1107] 1. Question input: Users input test questions using a smartphone or tablet.

[1108] 2. Answer generation: The server generates an answer to the problem using the OpenAI API. For example, if the problem is "Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm," the answer will be "The area of ​​a triangle is calculated by multiplying the base by the height by 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1109] 3. Explanation Generation: The server provides a detailed explanation of the solution process based on the generated answer. For example, the server might generate an explanation like, "First, let's check the formula for calculating the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying the formula gives 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1110] Examples of concrete examples and prompts

[1111] Specific examples

[1112] Question: "Find the area of ​​a triangle. Its base is 5cm and its height is 10cm."

[1113] Answer: "The area of ​​a triangle is base x height ÷ 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1114] Explanation: First, let's look at the formula for finding the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying the formula we get 5 cm x 10 cm ÷ 2 = 25 square centimeters.

[1115] Prompt Sentence Examples

[1116] Solution generation prompt: "Question: What is the area of ​​a triangle? Its base is 5cm and its height is 10cm. Please generate an answer."

[1117] Explanation-generating prompt: "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Solution: The area of ​​a triangle is base x height ÷ 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters. Please explain your solution in detail."

[1118] This allows students to understand the problem more deeply by providing detailed solutions to the problems they solve, reducing the workload of teachers and freeing up time for individual feedback, thereby improving the quality of education.

[1119] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1120] Step 1:

[1121] The user enters test questions using a smartphone or tablet. The user enters the question text into the application's input form and presses the submit button. The entered question text is sent to the server.

[1122] Input: Test question (e.g., "Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm.")

[1123] Output: The problem statement sent to the server

[1124] Step 2:

[1125] The server calls the generative AI model (OpenAI API) to generate an answer based on the received question. The server sends the question to the generative AI model as a prompt, and the model generates an answer.

[1126] Input: The question sent to the server

[1127] Data processing: Convert the problem statement into a prompt statement (e.g., "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Please generate the answer.")

[1128] Output: The answer returned by the generative AI model (e.g., "The area of ​​a triangle is calculated by multiplying the base by the height and dividing by 2. Therefore, it is 5 cm x 10 cm ÷ 2 = 25 square centimeters.")

[1129] Step 3:

[1130] The server calls the generative AI model again to provide a detailed explanation of the solution process based on the generated answer. The server sends the question and the generated answer as a prompt to the generative AI model, which then generates an explanation.

[1131] Input: The answer returned by the generative AI model

[1132] Data processing: Convert the problem and answer into a prompt (e.g., "Question: Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm. Answer: The area of ​​a triangle is calculated by multiplying the base by the height and dividing by 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters. Please explain in detail how you solved the problem.").

[1133] Output: Explanation returned by the generative AI model (e.g., "First, let's look at the formula for calculating the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying this formula we get 5 cm x 10 cm ÷ 2 = 25 square centimeters.")

[1134] Step 4:

[1135] The server then sends the generated answers and explanations to the user's device, where the user can check the answers and explanations on the screen of their smartphone or tablet.

[1136] Input: Answer and explanation returned by the generative AI model

[1137] Output: Answers and explanations sent to the user's device

[1138] Step 5:

[1139] The user can deepen their understanding of the problem based on the answers and explanations they receive. The user can also use the application's feedback function to send questions or comments about the answers or explanations to the server.

[1140] Input: Answers and explanations displayed on the user's device

[1141] Output: User understanding and feedback

[1142] In this way, the system provides detailed answers and explanations for the questions entered by the user, supporting the user's learning.

[1143] 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.

[1144] "Example 1"

[1145] In one embodiment of the present invention, an emotion engine is incorporated. This emotion engine recognizes the user's emotions and adjusts the learning content based on those emotions. Specifically, if the user is feeling stressed about the learning content, the emotion engine recognizes that stress and adjusts the learning content to be easier. Also, if the user is feeling excited or happy about the learning content, the emotion engine recognizes that excitement or joy and adjusts the learning content to be more difficult. This makes it possible to provide an optimal learning environment that corresponds to the user's emotions.

[1146] "Example 2"

[1147] In another embodiment of the present invention, the emotion engine adjusts the difficulty of the test questions. Specifically, if the user feels stressed about the test questions, the emotion engine recognizes that stress and lowers the difficulty of the test questions. Also, if the user feels confident about the test questions, the emotion engine recognizes that confidence and increases the difficulty of the test questions. This makes it possible to provide an optimal test environment according to the user's emotions.

[1148] "Example 3"

[1149] Furthermore, in another embodiment of the present invention, the emotion engine adjusts both the learning content and the test questions. Specifically, if the user is feeling stressed about the learning content, the emotion engine recognizes that stress and adjusts the learning content to be easier, while simultaneously lowering the difficulty of the test questions. Also, if the user is feeling excited or happy about the learning content, the emotion engine recognizes that excitement or joy and adjusts the learning content to be more difficult, while simultaneously increasing the difficulty of the test questions. This makes it possible to simultaneously provide an optimal learning environment and test environment that corresponds to the user's emotions.

[1150] The processing flow of each embodiment will be described below.

[1151] "Example 1"

[1152] Step 1: The user begins learning.

[1153] Step 2: The emotion engine recognizes the user's emotion.

[1154] Step 3: The emotion engine adapts the learning content based on the emotions it recognizes.

[1155] Step 4: Provide tailored learning content to users.

[1156] "Example 2"

[1157] Step 1: The user starts the test.

[1158] Step 2: The emotion engine recognizes the user's emotion.

[1159] Step 3: Adjust the difficulty of the test questions based on the emotions recognized by the emotion engine.

[1160] Step 4: Provide the adjusted test questions to the user.

[1161] "Example 3"

[1162] Step 1: The user begins learning.

[1163] Step 2: The emotion engine recognizes the user's emotion.

[1164] Step 3: Adjust the learning content and difficulty of test questions based on the emotions recognized by the emotion engine.

[1165] Step 4: Provide users with tailored learning content and test questions.

[1166] Example 1

[1167] Next, a description will be given of Example 1 of Form 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."

[1168] In the conventional education system, it was difficult to provide an optimal learning environment that suited each learner's feelings and level of understanding when learning curriculum guidelines and textbook content. Furthermore, teachers face a heavy workload and serious staff shortages. This leads to issues such as a decline in learners' learning efficiency and a lack of quality education.

[1169] 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.

[1170] In this invention, the server includes a learning means for learning the curriculum guidelines and textbook content, an analysis means for analyzing text data based on the learned content and extracting important keywords and concepts, a storage means for storing the extracted data in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on those emotions. This makes it possible to provide an optimal learning environment according to the emotions and level of understanding of each learner, contributing to reducing the workload of teachers and resolving the problem of staff shortages.

[1171] "Curriculum guidelines" are official guidelines that define the learning content and goals offered by educational institutions.

[1172] "Textbook content" refers to the learning content and information contained in textbooks used in educational institutions.

[1173] "Learning tools" refers to methods and tools for learning curriculum guidelines and textbook content.

[1174] "Analysis methods" refer to methods and tools for analyzing text data based on learned content and extracting important keywords and concepts.

[1175] "Storage means" refers to the methods and tools used to store the extracted data in a database.

[1176] "Extraction means" refers to methods and tools for extracting content to be learned based on the curriculum guidelines.

[1177] "Emotion recognition means" refers to methods or tools for recognizing a user's emotions and adjusting learning content based on those emotions.

[1178] A "database" is a system for systematically organizing and storing information.

[1179] "User" refers to an individual who uses this system to study.

[1180] A "server" refers to a computer system that manages the processing of the entire system and analyzes and stores various data.

[1181] This invention is a system for use in educational settings, and has a learning means for studying curriculum guidelines and textbook contents. Specifically, the system analyzes the contents of each chapter and section of a textbook and stores them in a database. It also extracts the content to be studied based on the curriculum guidelines and then studies it.

[1182] The server uses Python's NLTK library to analyze the content of each chapter and section of textbooks used in educational settings. NLTK is used to tokenize the text and extract important keywords and concepts. For example, when analyzing Chapter 1, "Integers and Fractions," of a junior high school mathematics textbook, the server extracts keywords such as "integer," "fraction," "reduced fraction," and "common fraction." The extracted data is stored in a MySQL database.

[1183] The server also uses the NLTK library to parse the text of the curriculum guidelines and extract the learning content. The text is tokenized and learning objectives and important topics are extracted. For example, when extracting the learning objective of "integers and fractions" from the junior high school mathematics curriculum guidelines, the server extracts learning objectives such as "addition, subtraction, multiplication, and division of integers" and "reduction and reduction of fractions" and stores them in a database.

[1184] The device uses an emotion engine to recognize the user's emotions. This emotion engine uses OpenCV and TensorFlow to analyze the user's facial expressions and voice to recognize emotions. For example, if a user is feeling stressed while learning "integers and fractions," the device will use its camera and microphone to capture the user's facial expressions and voice, perform facial recognition using OpenCV, and analyze the emotion using TensorFlow. The recognized emotion is sent to the server.

[1185] The server adjusts the learning content based on the user's emotions. If the user is feeling stressed, the server retrieves easier learning content from the database and sends it to the device. Conversely, if the user is feeling excited or happy, the server retrieves more difficult learning content from the database and sends it to the device.

[1186] As a concrete example, the following prompt sentence analyzes the contents of Chapter 1, "Integers and Fractions," of a junior high school mathematics textbook and extracts important keywords.

[1187] "Analyze the content of Chapter 1, "Integers and Fractions," in a junior high school mathematics textbook and extract important keywords. Also, extract learning objectives based on the curriculum guidelines and store them in a database. If the user feels stressed while studying, use an emotion engine to adjust the learning content."

[1188] In this way, it becomes possible to provide an optimal learning environment that suits each individual learner's feelings and level of understanding, which contributes to reducing the workload of teachers and resolving the problem of staff shortages.

[1189] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1190] Step 1:

[1191] The server reads PDF files of textbooks used in educational settings. It receives the PDF files of textbooks as input and generates text data as output. Specifically, the server opens the PDF files and extracts the text from each page.

[1192] Step 2:

[1193] The server analyzes the extracted text data. It receives the text data as input and extracts important keywords and concepts as output. Specifically, the server uses Python's NLTK library to tokenize the text and extract frequently occurring words and phrases.

[1194] Step 3:

[1195] The server stores the extracted keywords and concepts in a database. It receives the extracted keywords and concepts as input and saves them in the database as output. Specifically, the server connects to a MySQL database, creates tables for each chapter and section, and inserts data.

[1196] Step 4:

[1197] The server reads the PDF file of the curriculum guidelines. It receives the PDF file of the curriculum guidelines as input and generates text data as output. Specifically, the server opens the PDF file and extracts the text from each page.

[1198] Step 5:

[1199] The server analyzes the text data of the curriculum. It receives the text data as input and extracts learning objectives and important topics as output. Specifically, the server uses the NLTK library to tokenize the text and extract learning objectives and important topics.

[1200] Step 6:

[1201] The server stores the extracted learning objectives and topics in a database. It receives the extracted learning objectives and topics as input and saves them in the database as output. Specifically, the server connects to the database and inserts data into the appropriate tables.

[1202] Step 7:

[1203] The device uses a camera and microphone to capture the user's facial expressions and voice to recognize the user's emotions. It receives the user's facial and voice data as input and generates the captured data as output. Specifically, the device activates the camera and microphone and records the user's facial expressions and voice.

[1204] Step 8:

[1205] The device analyzes the captured data. It receives captured facial and voice data as input and recognizes the user's emotions as output. Specifically, the device uses OpenCV for facial recognition and TensorFlow for emotion analysis.

[1206] Step 9:

[1207] The terminal transmits the recognized emotion data to the server. The terminal receives the recognized emotion data as input and transmits it as output to the server. In specific operations, the terminal transmits the emotion data to the server via a network.

[1208] Step 10:

[1209] The server adjusts the learning content based on the user's emotional data. It receives the emotional data as input and generates adjusted learning content as output. Specifically, the server retrieves appropriate learning content from the database and adjusts the difficulty level according to the user's emotions.

[1210] Step 11:

[1211] The server transmits the adjusted learning content to the terminal. It receives the adjusted learning content as input and transmits it as output to the terminal. In specific operation, the server transmits the learning content to the terminal via a network.

[1212] Step 12:

[1213] The terminal presents the adjusted learning content received from the server to the user. The terminal receives the adjusted learning content as input and displays it to the user as output. Specifically, the terminal displays the learning content on the screen, allowing the user to continue learning.

[1214] (Application example 1)

[1215] Next, a description will be given of Application Example 1 of Form 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."

[1216] Conventional educational systems provide uniform learning content without considering the learner's emotions, which can lead to stress and, conversely, to little excitement or joy, resulting in reduced learning effectiveness. Furthermore, teachers in the field face heavy workloads and serious staff shortages. To solve these issues, a system is needed that provides an optimal learning environment that responds to the learner's emotions.

[1217] 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.

[1218] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on the emotions. This provides an optimal learning environment according to the learner's emotions, reduces the workload of teachers in educational settings, and solves the problem of staff shortages.

[1219] "Curriculum guidelines" are official guidelines that define the content and goals that learners should learn at an educational institution.

[1220] "Textbook content" refers to the content of teaching materials that contain the specific knowledge and information that learners should learn.

[1221] "Learning tools" are the methods and tools that learners use to learn curriculum and textbook content.

[1222] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[1223] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[1224] An "emotion recognition means" is a method or tool for recognizing a user's emotions and adjusting the learning content based on those emotions.

[1225] A "database" is a system for systematically organizing and storing information.

[1226] An "educational setting" is a place where learners receive education, such as a school or cram school.

[1227] "Reducing workload" refers to reducing the workload of teachers and staff and improving efficiency.

[1228] The "staffing shortage problem" refers to a situation in which there are not enough teachers and staff members.

[1229] As an embodiment of the present invention, the following system is constructed.

[1230] System Overview

[1231] This system is a learning support system used in educational settings, and includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the learning content based on those emotions.

[1232] Hardware and software used

[1233] Hardware: Camera, microphone, computer

[1234] Software: OpenCV (image processing library), EmotionRecognizer (emotion recognition library), TaskManager (task management library), Database (database management library)

[1235] Program processing explanation

[1236] emotion recognition means

[1237] The server uses a camera and microphone to capture the user's facial expressions and voice. This data is then processed using OpenCV and analyzed by EmotionRecognizer. As a result of the analysis, the user's emotions (e.g., stress, excitement, joy, etc.) are recognized.

[1238] Adjusting learning content

[1239] The server uses TaskManager to adjust the learning content in real time based on the recognized emotions: for example, if the user is stressed, the learning content will be made easier, and conversely, if the user is excited or happy, the learning content will be made more difficult.

[1240] Database Management

[1241] The server stores the recognized emotion data and adjusted learning content in a database, which allows for later analysis of the data and evaluation of learner tendencies and performance.

[1242] Specific examples

[1243] For example, while a user is solving a math problem, their facial expressions and voice are captured through a camera and microphone. If the EmotionRecognizer detects that the user is feeling stressed, the TaskManager lowers the difficulty of the problem and provides easier problems. Conversely, if the user is feeling happy, the TaskManager increases the difficulty and provides more challenging problems.

[1244] Prompt Sentence Examples

[1245] "Design a system that recognizes the emotions of workers and adjusts their work based on those emotions. Emotion recognition requires a camera and microphone, and real-time data processing is required to adjust work. Please also provide the specific program code."

[1246] In this way, it is possible to provide an optimal learning environment that suits the learner's emotions, reduce the workload of teachers in the classroom, and solve the problem of staff shortages.

[1247] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1248] Step 1:

[1249] The server uses a camera and a microphone to capture the user's facial expressions and voice. The input is real-time data from the camera and microphone, and the output is the captured image and voice data. Specifically, the camera captures the user's face and the microphone records the user's voice.

[1250] Step 2:

[1251] The server preprocesses the captured image data using OpenCV. The input is the image data obtained in step 1, and the output is the preprocessed image data. Specifically, it performs processes such as image resizing and noise removal.

[1252] Step 3:

[1253] The server inputs the preprocessed image data into EmotionRecognizer to analyze the user's emotions. The input is the preprocessed image data, and the output is the user's emotions (e.g., stress, excitement, joy, etc.). Specifically, EmotionRecognizer extracts facial features from the image data and classifies the emotions.

[1254] Step 4:

[1255] The server inputs the captured voice data into a voice recognition engine to analyze the user's emotions. The input is the voice data obtained in step 1, and the output is the user's emotions. Specifically, the voice recognition engine extracts emotional features from the voice data and classifies the emotions.

[1256] Step 5:

[1257] The server integrates the emotion data obtained in steps 3 and 4 to determine the final emotion. The input is emotion data obtained from images and audio, and the output is the integrated emotion data. Specifically, it compares both emotion data and selects the matching emotion as the final emotion.

[1258] Step 6:

[1259] The server adjusts the learning content using TaskManager based on the integrated emotional data. The input is the integrated emotional data, and the output is the adjusted learning content. Specifically, if the user feels stressed, the learning content is made easier, and conversely, if the user feels excited or happy, the learning content is made more difficult.

[1260] Step 7:

[1261] The server provides the adjusted learning content to the user. The input is the adjusted learning content, and the output is the learning content displayed to the user. Specifically, the learning content is displayed on the user's device, and the user studies it.

[1262] Step 8:

[1263] The server stores the recognized emotion data and adjusted learning content in a database. The input is emotion data and learning content, and the output is data stored in the database. Specifically, the emotion data and learning content are stored in the database so that they can be analyzed later.

[1264] Example 2

[1265] Next, a description will be given of Example 2 of Form 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."

[1266] In conventional learning systems, test questions based on learning content are often created manually, placing a heavy workload on teachers. Furthermore, it is difficult to provide test questions of an appropriate level of difficulty according to the user's learning progress and emotional state, which means that learning effectiveness is not maximized. Furthermore, there is a serious shortage of personnel in the educational field, and efficient learning support is required.

[1267] 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.

[1268] In this invention, the server includes means for inputting learning content, means for analyzing the input learning content and extracting important points, means for generating test questions based on the extracted important points, means for monitoring the user's emotions, means for adjusting the difficulty of the test questions based on the monitored emotions, and means for providing the adjusted test questions to the user. This makes it possible to automatically generate and provide test questions of an appropriate level of difficulty according to the user's learning progress and emotional state, thereby reducing the workload of teachers and contributing to solving the problem of staff shortages in educational settings.

[1269] "Means for inputting learning content" refers to a device or interface that allows a user to input the learning content into the system.

[1270] "Means for analyzing input learning content and extracting important points" refers to technologies and algorithms for analyzing input learning content and extracting important information and keywords from it.

[1271] The "means for generating test questions based on the extracted important points" refers to a technology or algorithm for automatically generating appropriate test questions based on the extracted important points.

[1272] "Means for monitoring user emotions" refers to devices or technologies for detecting a user's emotional state in real time from their facial expressions, voice, etc.

[1273] "Means for adjusting the difficulty of test questions based on monitored emotions" refers to techniques or algorithms for automatically adjusting the difficulty of test questions depending on the user's emotional state.

[1274] The "means for providing adjusted test questions to a user" refers to a device or interface for presenting adjusted test questions to a user.

[1275] MODE FOR CARRYING OUT THE INVENTION

[1276] The present invention is a system that creates test questions based on learning content and adjusts the difficulty of the questions depending on the emotional state of the user. Specific embodiments of this system will be described below.

[1277] Input of learning content

[1278] Users input what they have learned into the system. For example, if a user has learned how to calculate the area of ​​a triangle, they upload that information to the system as a text file. This input is done using a device such as a PC or tablet.

[1279] Analysis of learning content and extraction of important points

[1280] The server analyzes the input learning content and extracts key points. This process uses natural language processing technology. Specifically, it uses generative AI models such as Google's BERT and OpenAI's GPT-3. This allows it to extract the keyword "how to find the area of ​​a triangle" from the learning content text.

[1281] Generate test questions

[1282] The server generates test questions based on the extracted key points. For example, it generates a question such as, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The server uses a generative AI model to automatically determine the format and content of the questions.

[1283] User Emotion Monitoring

[1284] The device monitors the user's emotions in real time. It uses emotion recognition APIs such as Microsoft's Azure Cognitive Services and IBM's Watson to recognize stress and self-confidence from the user's facial expressions and voice. For example, it uses a camera and microphone to capture the user's facial expressions and voice and analyzes their emotional state.

[1285] Adjusting the difficulty of test questions

[1286] The device uses an emotion engine to send the user's emotional state to the server. If the user is feeling stressed, the server adjusts the difficulty of the problem to be lowered. For example, it changes the problem to "Find the area of ​​a triangle with a base of 4 cm and a height of 5 cm." Conversely, if the user is confident, it adjusts the difficulty of the problem to be higher. For example, it changes the problem to "Find the area of ​​a triangle with a base of 7 cm and a height of 12 cm."

[1287] Providing test questions

[1288] The server sends the adjusted test questions to the terminal and provides them to the user. The user answers the provided test questions to confirm the effectiveness of their learning. For example, the user can confirm their understanding of the learning content by answering the question, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm."

[1289] Prompt Sentence Examples

[1290] Below is an example of a prompt sentence to input to the generative AI model.

[1291] "Based on what the user has learned, generate a test question on how to find the area of ​​a triangle."

[1292] "Adjust the difficulty of the test questions depending on the user's emotions."

[1293] This maximizes the learning effect of the user and provides an optimal testing environment.

[1294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1295] Step 1: Enter your learning content

[1296] Users input what they have learned into the system. For example, if a user has learned how to calculate the area of ​​a triangle, they upload that information to the system as a text file. The input text file is sent to the server.

[1297] Step 2: Analyzing learning content and extracting key points

[1298] The server analyzes the input text file. It uses generative AI models such as Google's BERT and OpenAI's GPT-3 to extract key points from the text. Specifically, it uses natural language processing technology to extract the keyword "how to find the area of ​​a triangle." The input is a text file, and the output is the extracted keywords.

[1299] Step 3: Generate test questions

[1300] The server generates test questions based on the extracted key points. It uses a generative AI model to automatically determine the format and content of the questions. For example, it generates a question such as, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The input is the extracted keywords, and the output is the generated test question.

[1301] Step 4: User Emotion Monitoring

[1302] The device monitors the user's emotions in real time. It uses emotion recognition APIs such as Microsoft's Azure Cognitive Services and IBM's Watson to recognize stress and confidence from the user's facial expressions and voice. Specifically, it uses a camera and microphone to capture the user's facial expressions and voice and analyzes their emotional state. The input is the user's facial expression and voice data, and the output is the analyzed emotional state.

[1303] Step 5: Adjust the difficulty of the test questions

[1304] The device uses an emotion engine to send the user's emotional state to the server. If the user is feeling stressed, the server adjusts the difficulty of the questions to be lowered. For example, it changes the question to "Find the area of ​​a triangle with a base of 4 cm and a height of 5 cm." Conversely, if the user is feeling confident, it adjusts the difficulty of the questions to be higher. For example, it changes the question to "Find the area of ​​a triangle with a base of 7 cm and a height of 12 cm." The input is the analyzed emotional state, and the output is the adjusted test questions.

[1305] Step 6: Provide test questions

[1306] The server sends the adjusted test questions to the terminal and provides them to the user. The user answers the provided test questions to confirm the effectiveness of their learning. For example, the user can confirm their understanding of the learning content by answering the question, "Find the area of ​​a triangle with a base of 5 cm and a height of 10 cm." The input is the adjusted test questions, and the output is the user's answers.

[1307] (Application example 2)

[1308] Next, a description will be given of Application Example 2 of Form 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."

[1309] While conventional learning systems can create test questions based on the learning content, they lack the ability to adjust the difficulty of the questions according to the user's emotions. This can lead to users feeling stressed or overconfident, which can reduce learning effectiveness. Furthermore, in educational settings, teachers face heavy workloads and staff shortages. To solve these issues, a system that recognizes the user's emotions and provides test questions of an appropriate level of difficulty is needed.

[1310] 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.

[1311] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the difficulty of the test questions. This makes it possible to provide optimal test questions based on the user's emotions, thereby improving learning effectiveness. It also reduces the workload of teachers in educational settings and contributes to solving the problem of staff shortages.

[1312] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[1313] "Textbook content" refers to the content of the teaching materials used for learning in a particular grade or subject.

[1314] "Learning tools" are the methods and tools that learners use to understand and master the curriculum and textbook content.

[1315] "Question creation means" refers to a function or system for automatically generating test questions based on the content learned.

[1316] "Explanation creation means" refers to a function or system for providing explanations for created test questions.

[1317] An "emotion recognition means" is a function or system that detects a user's emotions and provides appropriate feedback or adjustments based on those emotions.

[1318] A "system" is a collection of integrated devices and software in which multiple means and functions work together to achieve a specific purpose.

[1319] The system for implementing this invention comprises the following main components: The server includes a learning means for learning the curriculum guidelines and textbook contents, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion recognition means for recognizing the user's emotions and adjusting the difficulty of the test questions.

[1320] Learning tools

[1321] The server provides an interface for users to study the curriculum and textbook content. This interface can be accessed through a web browser or a smartphone application. Users input their study content and use the learning materials and exercises provided by the system to progress with their studies.

[1322] Question creation method

[1323] The server analyzes the content the user has studied and extracts important points. This extraction is done using natural language processing technology. Based on the extracted important points, test questions are automatically generated using a generative AI model. The generated test questions are set to an appropriate level of difficulty according to the user's learning progress.

[1324] Explanation creation method

[1325] The server automatically creates explanations for the generated test questions. These explanations are written in a detailed and easy-to-understand manner to help users understand the questions. The explanations are created by referencing existing educational materials and expert knowledge bases.

[1326] emotion recognition means

[1327] The server uses sensor devices such as cameras and microphones to recognize the user's emotions. This allows it to analyze the user's emotions from their facial expressions and tone of voice. For emotion recognition, it uses a machine learning model to determine whether the user is feeling stressed or confident. The difficulty of the test questions is adjusted in real time depending on the user's emotions.

[1328] Specific examples

[1329] For example, if a user studies "How to find the area of ​​a triangle," the system operates as follows: When the user inputs their learning content, the server extracts key points and generates test questions related to "How to find the area of ​​a triangle." As the user works on the test questions, the system recognizes their emotions through the camera and microphone, lowering the difficulty of the questions if the user is feeling stressed and raising the difficulty if the user is feeling confident.

[1330] Prompt Sentence Examples

[1331] Below is an example of a prompt sentence to input to the generative AI model.

[1332] "The user has learned how to calculate the area of ​​a triangle. Extract the key points and generate test questions based on them. Also, if the user's emotion is recognized as 'confident,' increase the difficulty of the questions."

[1333] In this way, a system is provided that can maximize the learning effect of users and reduce the workload of teachers in educational settings.

[1334] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1335] Step 1:

[1336] The user inputs the learning content.

[1337] The user inputs the learning content (e.g., "How to calculate the area of ​​a triangle") using the terminal. The input data is sent to the server.

[1338] Step 2:

[1339] The server analyzes the learning content and extracts important points.

[1340] The server analyzes the received learning content using natural language processing techniques. Specifically, it uses libraries such as TextBlob to extract frequently occurring words and phrases from the learning content. This allows it to identify key points. The input is the text data of the learning content, and the output is a list of key points.

[1341] Step 3:

[1342] The server generates test questions based on key points.

[1343] The server inputs the extracted key points into a generative AI model to generate test questions. The generative AI model creates appropriate test questions based on the prompt. The input is a list of key points, and the output is the generated test questions.

[1344] Step 4:

[1345] The server creates explanations for the generated test questions.

[1346] The server automatically generates explanations for the generated test questions, referencing existing educational materials and expert knowledge bases. The input is the generated test questions, and the output is the corresponding explanations.

[1347] Step 5:

[1348] The user works through the test questions.

[1349] The user uses a terminal to answer test questions provided by the server. The user's answers are sent to the server. The input is the user's answers, and the output is the answer data.

[1350] Step 6:

[1351] The server recognizes the user's emotions.

[1352] The server recognizes the user's emotions using sensor devices such as cameras and microphones. It uses a machine learning model to analyze emotions from the user's facial expressions and tone of voice. The input is sensor data, and the output is the user's emotional state.

[1353] Step 7:

[1354] The server adjusts the difficulty of the test questions according to the user's emotions.

[1355] The server adjusts the difficulty of test questions in real time based on the user's recognized emotions. For example, it lowers the difficulty if the user is stressed and raises the difficulty if the user is confident. The input is the user's emotional state, and the output is the adjusted test questions.

[1356] Step 8:

[1357] The server provides feedback to the user.

[1358] The server provides appropriate feedback based on the user's answer and emotional state. The feedback may include explanations and additional learning resources. The input is the user's answer and emotional state, and the output is a feedback message.

[1359] Example 3

[1360] Next, a description will be given of Example 3 of Form Example 3. 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."

[1361] In the traditional education system, there are often insufficient explanations to help students understand the content, and the learning content and test questions are not adjusted to reflect students' emotions, resulting in poor learning efficiency. Furthermore, the workload of teachers in the field is increasing, and the problem of staff shortages is becoming more serious.

[1362] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1363] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion analysis means for analyzing the user's emotions and adjusting the difficulty of the learning content and test questions. This allows students to gain a deeper understanding of the learning content and progress efficiently in their studies. It also reduces the workload of teachers and contributes to solving the problem of staff shortages.

[1364] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[1365] "Textbook content" refers to the content of teaching materials created based on curriculum guidelines, and includes the specific information and knowledge that students learn.

[1366] "Learning tools" refers to the methods and tools students use to learn curriculum and textbook content.

[1367] "Question creation means" refers to the methods and tools used to create test questions based on what has been learned.

[1368] "Explanation creation means" refers to methods and tools for creating explanations for the created test questions.

[1369] "Emotion analysis means" refers to a method or tool for analyzing a user's emotions and adjusting the difficulty of the learning content and test questions.

[1370] A "system" refers to a series of processes or devices that are made up of a combination of multiple means.

[1371] "Users" refers to students and educators who use this system.

[1372] The term "server" refers to a central processing unit that manages the processing of the entire system and executes each means.

[1373] MODE FOR CARRYING OUT THE INVENTION

[1374] This invention is an educational system that includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, and an emotion analysis means for analyzing a user's emotions and adjusting the difficulty of the learning content and test questions.

[1375] Learning tools

[1376] Users use the learning tools to study the curriculum and textbook content. The learning tools provide digital content such as electronic learning materials and online courses. For example, if a user studies a specific mathematics unit, the system will provide learning materials corresponding to that unit.

[1377] Question creation method

[1378] The server creates test questions based on the content that has been learned. The question creation means includes an algorithm that automatically generates test questions corresponding to a specified grade, field, and chapter. For example, if a user studies the field of geometry in mathematics for the second year of junior high school, the server generates test questions based on that content.

[1379] Explanation creation method

[1380] The server generates an explanation for the created test question. The explanation generation means includes an algorithm that provides a detailed explanation of the process and method of solving the question. For example, after a user solves the question "Find the area of ​​a triangle," the server generates the following explanation:

[1381] 1. Determine the base and height of the triangle.

[1382] 2. Multiply the base and height.

[1383] 3. Divide the result by 2.

[1384] This explanation helps the user understand how to answer the question.

[1385] Emotion analysis means

[1386] The device is equipped with an emotion analysis means for analyzing the user's emotions. The emotion analysis means collects the user's facial expressions and voice data and analyzes emotions using a machine learning model. For example, it uses a camera and microphone to record the user's facial expressions and tone of voice and identifies emotions such as stress and joy.

[1387] The device adjusts the learning content and the difficulty of the test questions based on the analysis results. If the user is feeling stressed, the learning content will be changed to easier ones and the difficulty of the test questions will be lowered. Conversely, if the user is feeling happy or excited, the learning content will be changed to more difficult ones and the difficulty of the test questions will be increased.

[1388] Specific examples

[1389] For example, after a user solves the problem "Find the area of ​​a triangle," the server generates the following explanation:

[1390] 1. The base of a triangle is 5cm and the height is 10cm.

[1391] 2. Multiply the base (5 cm) by the height (10 cm) to get 50 square centimeters.

[1392] 3. Divide 50 square centimeters by 2 to get 25 square centimeters.

[1393] 4. Therefore, the area of ​​the triangle is 25 square centimeters.

[1394] Furthermore, if the user feels stressed while studying, the terminal performs the following process.

[1395] 1. The device collects the user's facial expression data and inputs it into the emotion engine.

[1396] 2. The emotion engine recognizes that the user is feeling stressed.

[1397] 3. The device adjusts the learning content to make it easier and at the same time reduces the difficulty of the test questions.

[1398] Prompt Sentence Examples

[1399] An example of a prompt sentence to input to the generative AI model is as follows:

[1400] "If users experience stress while studying, please explain how you will adjust the difficulty of the study content and test questions."

[1401] Using this prompt sentence, the generative AI model explains how to provide the optimal learning and testing environment according to the user's emotions. The flow of the identification process in Example 3 will be explained with reference to FIG. 21.

[1402] Step 1:

[1403] The user uses the learning means to study the curriculum and textbook contents.

[1404] Input: Curriculum guidelines and textbook contents

[1405] Output: Understanding of learning content

[1406] Specific operation: A user browses digital content such as electronic learning materials and online courses to progress through their studies. For example, if a user is studying a specific unit of mathematics, the system will provide learning materials corresponding to that unit.

[1407] Step 2:

[1408] The server creates test questions based on what has been learned.

[1409] Input: Learning content

[1410] Output: Test question

[1411] Specific operation: The server uses an algorithm to automatically generate test questions corresponding to a specified grade, subject, and chapter. For example, if a user studies the geometry subject of eighth-grade mathematics, the server generates test questions based on that content.

[1412] Step 3:

[1413] The user works through the created test questions.

[1414] Input: Test Question

[1415] Output:Answer

[1416] Specific operation: The user solves the test questions generated by the server and inputs the answers. For example, for the question "Find the area of ​​a triangle," the user performs calculations and inputs the answer into the system.

[1417] Step 4:

[1418] The server generates explanations for the created test questions.

[1419] Input: Test questions, user answers

[1420] Output:Explanation

[1421] Specific operation: The server generates an explanation using an algorithm that provides a detailed explanation of the process and method of solving the problem. For example, after a user solves the problem "Find the area of ​​a triangle," the server generates the following explanation:

[1422] 1. Determine the base and height of the triangle.

[1423] 2. Multiply the base and height.

[1424] 3. Divide the result by 2.

[1425] Step 5:

[1426] The terminal uses an emotion analysis means for analyzing the user's emotions.

[1427] Input: User's facial expression data, voice data

[1428] Output: Emotion analysis results

[1429] How it works: The device uses a camera and microphone to record the user's facial expressions and tone of voice, and then uses machine learning models to analyze their emotions. For example, if the user is frowning, it will determine that they are feeling stressed.

[1430] Step 6:

[1431] The terminal adjusts the learning content and the difficulty of the test questions based on the analysis results.

[1432] Input: Sentiment analysis results

[1433] Output: adjusted learning content, adjusted test questions

[1434] Specific operation: If the user feels stressed, the device changes the learning content to easier ones and also lowers the difficulty of the test questions. Conversely, if the user feels happy or excited, the device changes the learning content to more difficult ones and also increases the difficulty of the test questions.

[1435] (Application example 3)

[1436] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1437] Conventional educational support systems do not adjust the learning content according to the learner's emotions, which can lead to learners feeling stressed or, conversely, losing interest because the content is too easy. Another issue is that the explanations for test questions are insufficient, making it difficult for learners to understand the process of solving the questions. This reduces the effectiveness of learning and increases the workload of teachers in the classroom.

[1438] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1439] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an emotion analysis means for analyzing the user's emotions, and a difficulty adjustment means for adjusting the difficulty of the learning content and test questions in accordance with the user's emotions. This makes it possible to provide an optimal learning environment and test environment in accordance with the learner's emotions, thereby improving learning effectiveness.

[1440] "Curriculum guidelines" are official guidelines that define the learning content and goals offered by educational institutions.

[1441] "Textbook content" refers to the specific content of learning materials created based on curriculum guidelines.

[1442] "Learning tools" refers to the methods and tools that learners use to study the curriculum and textbook content.

[1443] "Question creation methods" refer to methods and tools for creating test questions based on what has been learned.

[1444] "Means for creating explanations" refers to methods and tools for creating explanations for the test questions that have been created.

[1445] "Emotion analysis means" refers to methods and tools for analyzing user emotions.

[1446] "Difficulty adjustment means" refers to methods and tools for adjusting the difficulty of learning content and test questions according to the user's emotions.

[1447] A "system" refers to a collection of devices and software that have a series of functions that operate in combination with multiple means.

[1448] A system for carrying out this invention is configured as follows: The server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an emotion analysis means for analyzing the user's emotions, and a difficulty adjustment means for adjusting the difficulty of the learning content and test questions in accordance with the user's emotions.

[1449] Program processing explanation

[1450] The server first provides learning tools for studying the curriculum and textbook content, including online learning materials and interactive learning content that users can access using devices such as smartphones and tablets.

[1451] Next, a question creation means is activated to create test questions based on the content learned. This means automatically generates test questions corresponding to the specified grade, field, and chapter. The generated test questions are provided at an appropriate time according to the user's learning progress.

[1452] The explanation creation means for creating explanations for the created test questions automatically generates detailed explanations using a generative AI model. The explanations provide detailed explanations of the process and method of solving the questions, making it easier for users to understand the questions.

[1453] The emotion analysis means uses the smartphone's camera and microphone to analyze the user's emotions from their facial expressions and voice. The analyzed emotion data is used to evaluate how the user feels about the learning content in real time.

[1454] The difficulty level adjustment means adjusts the difficulty of the learning content and test questions based on the data obtained from the emotion analysis means. For example, if the user is feeling stressed, the learning content is adjusted to be easier and the difficulty of the test questions is also lowered. Conversely, if the user is feeling excited or happy, the learning content is adjusted to be more difficult and the difficulty of the test questions is also increased.

[1455] Specific examples

[1456] As a concrete example, consider a case where a user is working on a problem to "find the area of ​​a triangle." If the user is feeling stressed, the system can lower the difficulty of the problem and provide a brief explanation. An example of a prompt to be input to the generative AI model is as follows:

[1457] "Generate an explanation for the problem of finding the area of ​​a triangle. The explanation should be simple enough for users who are stressed."

[1458] By using this prompt sentence to have a generative AI model generate an explanation, it is possible to provide the optimal learning environment for the user.

[1459] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1460] Step 1:

[1461] The server provides learning tools for studying curriculum guidelines and textbook content. Users access online learning materials and interactive learning content using devices such as smartphones and tablets. The input is the user's learning progress data, and the output is the learning content accessed by the user.

[1462] Step 2:

[1463] The server operates a question creation means that creates test questions based on the content learned. Test questions corresponding to the specified grade, field, and chapter are automatically generated. The input is the user's learning progress data and information on the curriculum guidelines, and the output is the generated test questions.

[1464] Step 3:

[1465] The server automatically generates detailed explanations for the created test questions using an explanation creation means. Using a generative AI model, it provides detailed explanations of the problem-solving process and method. The input is the generated test question, and the output is the generated explanation.

[1466] Step 4:

[1467] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice. The emotion analysis means analyzes this data and evaluates the user's emotions. The input is the user's facial and voice data, and the output is the analyzed emotion data.

[1468] Step 5:

[1469] The server operates a difficulty level adjustment means that adjusts the learning content and the difficulty of the test questions based on the emotional data obtained from the emotional analysis means. If the user is feeling stressed, the learning content is adjusted to be easier, and the difficulty of the test questions is also lowered at the same time. Conversely, if the user is feeling excited or happy, the learning content is adjusted to be more difficult, and the difficulty of the test questions is also increased at the same time. The input is the analyzed emotional data, and the output is the adjusted learning content and test questions.

[1470] Step 6:

[1471] The server sends the adjusted learning content and test questions to the user's terminal. The user accesses these contents through the terminal and continues learning. The input is the adjusted learning content and test questions, and the output is the learning content and test questions accessed by the user.

[1472] Step 7:

[1473] After the user works on the test questions, the server generates an explanation using the generative AI model. For example, the explanation is generated using a prompt such as, "Please generate an explanation for the problem of finding the area of ​​a triangle. Please keep the explanation simple and suitable for when the user is feeling stressed." The input is the user's answer data and the prompt, and the output is the generated explanation.

[1474] 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.

[1475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1476] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1477] 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.

[1478] [Third embodiment]

[1479] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1480] 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.

[1481] 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).

[1482] 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.

[1483] 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.

[1484] 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).

[1485] 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.

[1486] 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.

[1487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1489] In the 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.

[1490] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1491] "Example 1"

[1492] The present invention is a system for use in educational settings. This system has a learning means for studying curriculum guidelines and textbook content. Specifically, the system analyzes the content of each chapter and section of the textbook and stores it in a database. Furthermore, the system extracts content to be studied based on the curriculum guidelines and then studies that content.

[1493] "Example 2"

[1494] Furthermore, the system of the present invention has a question creation means for creating test questions based on the content learned. Specifically, important points are extracted from the content learned and questions are created based on them. For example, if the content learned is "how to calculate the area of ​​a triangle," questions related to that content are created.

[1495] "Example 3"

[1496] The system of the present invention also has an explanation creation means for creating explanations for the created test questions. Specifically, the system explains the process and method of solving the created questions. For example, if the created question is "Find the area of ​​a triangle," the system will explain the process in detail. This helps students understand the questions and answer them.

[1497] The processing flow of each embodiment will be described below.

[1498] "Example 1"

[1499] Step 1: The system learns the curriculum and textbook content. Specifically, it analyzes the content of each chapter and section of the textbook and stores it in a database.

[1500] Step 2: Based on the curriculum guidelines, extract the content to be learned and study it.

[1501] "Example 2"

[1502] Step 1: Create test questions based on what you have learned. Specifically, extract important points from what you have learned and create questions based on them.

[1503] Step 2: For example, if the content learned is "How to find the area of ​​a triangle," create a problem related to that.

[1504] "Example 3"

[1505] Step 1: Create an explanation for the test questions you have created. Specifically, explain the process and method of solving the questions you have created.

[1506] Step 2: For example, if the problem you created is "Find the area of ​​a triangle," explain the solution process in detail. This will help students understand the problem and solve it.

[1507] Example 1

[1508] Next, a description will be given of Example 1 of Form 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."

[1509] In conventional educational systems, there is a lack of efficient ways to study curriculum guidelines and teaching materials, which increases the workload of educators and exacerbates the staff shortage problem.In addition, analysis and extraction of learning content is often done manually, which takes time and effort, making it difficult to provide efficient learning support in educational settings.

[1510] 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.

[1511] In this invention, the server includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content. This reduces the workload of educators, contributes to solving the problem of staff shortages, and enables efficient learning support.

[1512] A "curriculum guideline" is a document that outlines the learning content and educational goals set by an educational institution.

[1513] "Teaching material content" refers to the learning content contained in educational materials such as textbooks and reference books.

[1514] "Learning tools" are methods and tools for learning the curriculum and teaching material content.

[1515] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[1516] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[1517] "Analysis means" refers to methods and tools for analyzing the content of each chapter or section of the teaching material and storing it in a database.

[1518] "Extraction means" refers to methods or tools for extracting content to be learned based on the curriculum guidelines.

[1519] "Providing means" refers to the methods and tools used to provide extracted learning content to users.

[1520] "Educator" refers to occupations such as teachers and lecturers who provide instruction and education in educational settings.

[1521] "Workload" refers to the amount and difficulty of the work that educators perform on a daily basis.

[1522] The "staffing shortage problem" refers to a situation in which there are not enough educators in the educational field.

[1523] The present invention is a system for use in educational settings, which provides a means for efficiently learning curriculum guidelines and teaching material content. A specific embodiment of this system will be described below.

[1524] Generating a Program

[1525] The server generates a program for the system to be used in the educational field. This program includes a learning means for learning the curriculum guidelines and the contents of the teaching materials, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an analysis means for analyzing the content of each chapter or section of the teaching materials and storing the results in a database, an extraction means for extracting content to be learned based on the curriculum guidelines, and a provision means for providing the extracted learning content.

[1526] Program processing

[1527] The server uses natural language processing (NLP) techniques to analyze the content of each chapter and section of the textbook. Specifically, it uses the Python libraries NLTK and spaCy to analyze the text data. The analyzed data is stored in a database such as MySQL or PostgreSQL.

[1528] The server then extracts the learning content based on the curriculum guidelines. This process uses rule-based algorithms and machine learning models. The extracted content is then provided as a web application for users to study. This web application is built using a front-end framework such as React or Angular.

[1529] Specific examples

[1530] For example, if a user inputs "I would like to study Chapter 3 of the junior high school mathematics textbook," the server performs the following process.

[1531] 1. The server analyzes the content of Chapter 3 of the textbook and stores it in the database.

[1532] 2. The server extracts the content to be learned in Chapter 3 based on the curriculum guidelines.

[1533] 3. The extracted content is provided to the user through a web application.

[1534] Example prompts to input to a generative AI model:

[1535] "Analyze the contents of Chapter 3 of a junior high school mathematics textbook and extract the content that should be studied."

[1536] In this way, the system allows users to efficiently learn the necessary learning content in the educational setting.

[1537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1538] Step 1:

[1539] Textbook data entry

[1540] The user uploads textbook data to the system. The device sends the PDF or text file of the textbook specified by the user to the server. The input is the textbook data file, and the output is the textbook data sent to the server. Specifically, the user selects the textbook file using the file selection dialog on the device and clicks the upload button.

[1541] Step 2:

[1542] Textbook content analysis

[1543] The server analyzes the received textbook data. Specifically, it uses the Python libraries NLTK and spaCy to analyze the content of each chapter and section of the textbook using natural language processing technology. The input is the textbook data sent to the server, and the output is the analyzed text data. Specifically, the server tokenizes the textbook data and extracts important keywords and phrases.

[1544] Step 3:

[1545] Storage in the database

[1546] The server stores the analyzed textbook content in a database. Specifically, it uses a database management system such as MySQL or PostgreSQL. The input is the analyzed text data, and the output is the data stored in the database. Specifically, the server organizes the data by chapter and section and creates indexes to enable efficient searches.

[1547] Step 4:

[1548] Extraction of learning content based on curriculum guidelines

[1549] The server extracts learning content based on the curriculum guidelines. Specifically, it uses rule-based algorithms and machine learning models to match the content of the textbook with the curriculum guidelines. The input is the textbook data stored in the database and the curriculum guidelines, and the output is the extracted learning content. Specifically, the server extracts relevant textbook sections based on the learning objectives described in the curriculum guidelines.

[1550] Step 5:

[1551] Providing learning content

[1552] The server provides the extracted learning content to the user through a web application. The terminal displays the learning content through the web browser accessed by the user. The input is the extracted learning content, and the output is the learning content provided to the user. Specifically, the server uses front-end frameworks such as React and Angular to provide an interface that the user can operate intuitively.

[1553] (Application example 1)

[1554] Next, a description will be given of Application Example 1 of Form 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."

[1555] In the field of education, the workload of teachers is increasing and staff shortages are becoming a serious problem. There are also issues such as the difficulty of formulating effective learning plans based on curriculum guidelines and managing learning progress. Furthermore, there is a lack of systems that can efficiently analyze the content of teaching materials and propose optimal learning plans for learners. To solve these issues, a system is needed that can efficiently study curriculum guidelines and textbook content, propose learning plans, and manage progress.

[1556] 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.

[1557] In this invention, the server includes a learning means for learning the curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a content analysis means for analyzing the content of the teaching materials and storing the results in a database, a learning plan proposal means for proposing a learning plan based on the curriculum guidelines, and a progress management means for managing learning progress and providing feedback. This reduces the workload of teachers in educational settings, contributes to solving the problem of staff shortages, and enables the creation of effective learning plans and management of learning progress based on the curriculum guidelines.

[1558] A "curriculum guideline" is an official document that outlines the learning content and educational policies established by an educational institution.

[1559] "Textbook content" refers to the content of teaching materials that systematically compile knowledge and information about a specific subject.

[1560] "Learning tools" are methods and tools that allow learners to effectively learn the curriculum and textbook content.

[1561] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[1562] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[1563] "Content analysis means" refers to methods and tools for analyzing the content of teaching materials and storing that information in a database.

[1564] "Study plan suggestion means" refers to methods or tools for proposing optimal study plans to learners based on the curriculum guidelines.

[1565] "Progress management means" are methods and tools for managing learners' learning progress and providing feedback.

[1566] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[1567] "Feedback" means providing evaluation and advice on a learner's learning progress and achievements.

[1568] To put the present invention into practice, it is necessary to build a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system is shown below.

[1569] server

[1570] The server has the following main functions:

[1571] 1. Learning means for curriculum guidelines and textbook contents: The server stores curriculum guidelines and textbook contents in a database and makes them accessible to learners. This includes content analysis means for analyzing the contents of the teaching materials and storing them in a database.

[1572] 2. Question Creation: The server generates test questions based on the content learned. This includes the ability to create test questions for a specified grade, subject, and chapter.

[1573] 3. Explanation creation means: The server generates explanations for the created test questions.

[1574] 4. Means for suggesting learning plans: The server proposes optimal learning plans for learners based on the curriculum guidelines.

[1575] 5. Progress management means: The server manages the learner's learning progress and provides feedback.

[1576] Terminal

[1577] A terminal is a device that a user uses to access a server. Examples include smartphones, tablets, and PCs. A terminal has the following functions:

[1578] 1. Search materials: Users can easily find textbooks and learning materials by scanning barcodes or searching by keyword.

[1579] 2. Display of study plan: The study plan proposed by the server is displayed, and the user can proceed with their studies according to it.

[1580] 3. Progress Management Display: Display learning progress and provide feedback to users.

[1581] User

[1582] The user is a learner or an educator. The user accesses the server using a terminal and performs the following operations:

[1583] 1. Selecting learning materials: The user selects a textbook or learning material and studies its contents.

[1584] 2. Answering test questions: The user answers the test questions generated by the server and checks the results.

[1585] 3. Execution of the study plan: The user proceeds with the study according to the study plan proposed by the server.

[1586] 4. Check progress: Users can check their own learning progress and adjust their learning plan as needed.

[1587] Hardware and software used

[1588] Hardware: smartphones, tablets, PCs, servers

[1589] Software: Python, BarcodeScanner library, requests library, database (e.g., SQLite), AI model (e.g., TensorFlow)

[1590] Data processing and calculation

[1591] The server analyzes the content of the learning materials and stores it in a database. This process includes analyzing the content of the learning materials using an AI model. The server also generates a learning plan based on the curriculum guidelines and proposes it to the user. The server also manages the user's learning progress and provides feedback.

[1592] Specific examples

[1593] When a user scans a barcode to purchase a math textbook, the application will retrieve information about the material and suggest an optimal study plan based on the curriculum guidelines. The application will also include a function to allow students to study according to the study plan and manage their progress within the app.

[1594] Prompt Sentence Examples

[1595] Develop an application that, when a user scans a barcode to purchase a math textbook, retrieves the learning material information and suggests an optimal study plan based on the curriculum guidelines. Include a function to progress according to the study plan and manage progress in the app.

[1596] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1597] Step 1:

[1598] A user uses a terminal to scan a barcode on a textbook.

[1599] Input: Textbook barcode

[1600] Output: Textbook information (title, author, content, etc.)

[1601] Specific operation: The device uses the barcode scanner function to read the barcode of the textbook and sends the information to the server. The server retrieves the textbook information from the database based on the barcode and sends it back to the device.

[1602] Step 2:

[1603] The device displays textbook information.

[1604] Input: Textbook information (title, author, content, etc.)

[1605] Output: Display detailed information about the textbook

[1606] Specific operation: The terminal displays the textbook information received from the server to the user, who can then check detailed information about the textbook.

[1607] Step 3:

[1608] The server analyzes the contents of the textbook and stores them in a database.

[1609] Input: Textbook content

[1610] Output: Parsed textbook content (stored in a database)

[1611] How it works: The server uses an AI model to analyze the content of the textbook and stores the results in a database. The analysis uses natural language processing technology.

[1612] Step 4:

[1613] The server generates a learning plan based on the curriculum guidelines and proposes it to the user.

[1614] Input: Curriculum guidelines, analyzed textbook content, user learning history

[1615] Output: Learning plan

[1616] Specific operation: The server uses an AI model to generate an optimal learning plan based on the curriculum guidelines, the analyzed textbook content, and the user's learning history. The generated learning plan is sent to the device and displayed to the user.

[1617] Step 5:

[1618] The user progresses through the study according to the study plan.

[1619] Input:Study plan

[1620] Output: Learning progress data

[1621] Specific operation: The user studies according to the study plan displayed on the device. The progress of the study is sent from the device to the server, and the server stores the data in a database.

[1622] Step 6:

[1623] The server manages the learning progress and provides feedback.

[1624] Input: Learning progress data

[1625] Output: Feedback

[1626] Specific operation: The server analyzes the learning progress data stored in the database and generates feedback for the user. The feedback is sent to the terminal and displayed to the user.

[1627] Step 7:

[1628] The user reviews the feedback and adjusts the learning plan as needed.

[1629] Input: Feedback

[1630] Output: Revised lesson plan

[1631] Specific operation: The user checks the feedback displayed on the device and modifies the study plan as necessary. The modified study plan is sent from the device to the server, which stores the data in a database.

[1632] Example 2

[1633] Next, a description will be given of Example 2 of Form 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."

[1634] In conventional educational systems, teachers must manually create test questions, which places a heavy burden on the teacher's work. The shortage of teachers is also a serious problem. Furthermore, it is difficult to quickly create appropriate test questions based on the learning content, which can lead to a decline in the quality of education. To solve these issues, a system is needed that automatically generates test questions from the learning content.

[1635] 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.

[1636] In this invention, the server includes an input means for inputting learning content, a receiving means for receiving the input learning content, a prompt generating means for creating a prompt sentence based on the received learning content and inputting it into the generative AI model, a point extracting means for extracting important points from the generative AI model, a question generating means for generating test questions based on the extracted points, and a providing means for providing the generated test questions. This enables the automatic generation of test questions based on the learning content.

[1637] "Learning content" refers to the information and knowledge that a user inputs in order to learn.

[1638] "Input means" refers to a device or interface that allows a user to input learning content into the system.

[1639] The "receiving means" refers to a device or function that receives the learning content transmitted from the input means.

[1640] A "generative AI model" is a model that uses artificial intelligence to perform a specific task, and in this case is used to extract key points from learning content.

[1641] A "prompt generation means" is a device or function that creates prompt sentences to be input into a generative AI model based on received learning content.

[1642] "Point extraction means" refers to a device or function that uses a generative AI model to extract important points from the learning content.

[1643] "Question generation means" refers to a device or function that generates test questions based on the extracted important points.

[1644] "Providing means" refers to a device or function that provides the generated test questions to the user.

[1645] The present invention relates to a system for automatically generating test questions based on learning content. A specific embodiment of this system will be described below.

[1646] System configuration

[1647] This system is mainly composed of the following hardware and software.

[1648] 1. Terminal: The device on which the user inputs learning content. For example, a computer or tablet.

[1649] 2. Server: A central processing unit that receives the training data and generates test questions using the generative AI model. The server has software installed to run the generative AI model (e.g., GPT-4).

[1650] Program processing

[1651] Input and receive learning content

[1652] The user inputs the learning content using the terminal. For example, the learning content is "How to find the area of ​​a triangle." The terminal transmits the input learning content to the server.

[1653] The server receives the learning content sent from the device and stores it as text data. The receiving method uses communication protocols such as HTTP requests and WebSocket.

[1654] Generate prompt statement

[1655] The server creates a prompt sentence to be input to the generative AI model based on the received learning content. For example, it generates a prompt sentence like the following:

[1656] Learning content: How to find the area of ​​a triangle

[1657] Extract the key points.

[1658] This prompt sentence is input into the generative AI model.

[1659] Extracting important points

[1660] The server uses a generative AI model (e.g., GPT-4) to extract key points from the learning content. Based on the input prompt, the generative AI model returns the key point, "The formula for calculating the area of ​​a triangle is base x height ÷ 2."

[1661] Generate test questions

[1662] The server generates test questions based on the extracted key points. For example, it generates questions like the following:

[1663] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[1664] Providing test questions

[1665] The server transmits the generated test questions to the terminal and provides them to the user, who can check the generated test questions through the terminal.

[1666] Specific examples

[1667] As a concrete example, the following prompt sentence is input into the generative AI model:

[1668] Learning content: How to find the area of ​​a triangle

[1669] Key Point: The formula for the area of ​​a triangle is base x height / 2.

[1670] Question Creation: Create test questions based on these points.

[1671] An example of a problem that may be generated is as follows:

[1672] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[1673] In this way, the server extracts important points from the learning content, generates test questions based on them, and provides them to the user, thereby realizing a system.

[1674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1675] Step 1:

[1676] The user inputs the learning content.

[1677] Input: The user enters the learning content (e.g., "How to find the area of ​​a triangle") into the input form on the device.

[1678] Specific operation: The user enters "How to find the area of ​​a triangle" into the input form on the terminal and clicks the submit button.

[1679] Output: The device sends the input learning content to the server.

[1680] Step 2:

[1681] The server receives the input learning content.

[1682] Input: The learning content sent from the device (e.g., "How to find the area of ​​a triangle").

[1683] Specific operation: The server receives the HTTP request and saves the learning content as text data.

[1684] Output: Text data of the learning content stored on the server.

[1685] Step 3:

[1686] The server creates and inputs prompt sentences to the generative AI model.

[1687] Input: Text data of learning content stored on the server.

[1688] Specific operation: The server creates a prompt sentence like the following based on what it has learned.

[1689] Learning content: How to find the area of ​​a triangle

[1690] Extract the key points.

[1691] Output: The prompt sentence to be input to the generative AI model.

[1692] Step 4:

[1693] The server extracts key points from the generated AI model.

[1694] Input: The prompt text fed into the generative AI model.

[1695] How it works: A generative AI model (e.g., GPT-4) extracts key points based on the prompt and returns results like this:

[1696] The formula for finding the area of ​​a triangle is base x height ÷ 2.

[1697] Output: Extracted key points.

[1698] Step 5:

[1699] The server generates test questions based on the extracted points.

[1700] Input: Extracted key points (e.g., "The formula for the area of ​​a triangle is base x height divided by 2").

[1701] Specific operation: The server generates test questions based on the key points, such as the following:

[1702] Problem: Using the formula for finding the area of ​​a triangle, find the area of ​​a triangle with a base of 5cm and a height of 10cm.

[1703] Output: The generated test questions.

[1704] Step 6:

[1705] The server provides the generated test questions to the user.

[1706] Input: The generated test questions.

[1707] Specific operation: The server sends the generated test questions to the device.

[1708] Output: The test questions displayed on the user's device.

[1709] (Application example 2)

[1710] Next, a description will be given of Application Example 2 of Form 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."

[1711] In conventional educational systems, test questions based on learning content are created manually, which places a heavy workload on teachers and creates serious staff shortages. Furthermore, the quality and variety of test questions is limited, making it difficult to accurately assess learners' understanding. Furthermore, there is a need for a system that can quickly generate appropriate test questions based on learning content.

[1712] 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.

[1713] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions. This reduces the workload of teachers, solves the problem of staff shortages, and makes it possible to quickly generate high-quality test questions for accurately assessing learners' understanding.

[1714] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[1715] "Textbook content" refers to the content of teaching materials that describe the knowledge and skills that learners should learn in a particular grade or subject.

[1716] "Learning tools" are the methods and tools that learners use to understand and master the curriculum and textbook content.

[1717] "Question creation means" refers to methods or tools for generating test questions based on what has been learned.

[1718] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[1719] A "generative AI model" is a model that uses artificial intelligence technology to generate new information and content from data.

[1720] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1721] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, a means for automatically generating test questions based on the learned content using a generative AI model, and a means for generating prompt sentences to create test questions.

[1722] Server Roles

[1723] The server plays a central role in automatically generating test questions based on what the learner has learned. Specifically, the server performs the following processes:

[1724] 1. Learning tools: The server stores the curriculum and textbook contents in a database and makes them accessible to learners.

[1725] 2. Question creation method: The server extracts important points based on the content that the learner has studied and generates test questions based on them.

[1726] 3. Explanation creation means: The server automatically creates explanations for the generated test questions and provides them to the learner.

[1727] 4. Generative AI model: The server automatically generates test questions based on the learning content using a generative AI model, which uses an advanced natural language processing model such as OpenAI's GPT-3.

[1728] 5. Prompt sentence generation means: The server generates appropriate prompt sentences for the generative AI model and creates test questions based on them.

[1729] Device Role

[1730] The terminal is a device that allows learners to access the server, check the learning content, and answer test questions. Terminals include smartphones, tablets, and PCs.

[1731] User Roles

[1732] The user uses the system as a learner. The user accesses the server using a terminal, checks the learning content, and solves the generated test questions. The server automatically provides explanations for the test questions the user answers.

[1733] Specific examples

[1734] For example, if the user learns "How to find the area of ​​a triangle," the server generates the following prompt:

[1735] Create test questions based on the following: How to find the area of ​​a triangle

[1736] By inputting this prompt into the generative AI model, the server automatically generates a test question such as, "If the base of a triangle is 5 cm and the height is 10 cm, find its area." The generated test question is provided to the user via their device, and the user can answer it.

[1737] In this way, by having the server, terminal, and user work together, it becomes possible to quickly generate and provide high-quality test questions based on the learning content.

[1738] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1739] Step 1:

[1740] The server stores the curriculum and textbook contents in a database. It receives learning material data for users as input and saves it in the database. This creates learning resources that users can access.

[1741] Step 2:

[1742] The user accesses the server using a terminal and selects the content to be studied. The user selects the content they want to study as input, and the selection information is sent to the server. The server provides the user with related learning material data based on the selected content.

[1743] Step 3:

[1744] The server extracts important points based on the content the user has studied. It receives the study content data as input and uses natural language processing technology to extract important points. This provides the information that forms the basis of test questions.

[1745] Step 4:

[1746] The server uses a generative AI model to generate prompt sentences based on the extracted key points. The server receives the extracted key points data as input and generates prompt sentences. The generated prompt sentences are input into the generative AI model.

[1747] Step 5:

[1748] The server inputs a prompt sentence into the generative AI model to automatically generate test questions. The generative AI model receives the prompt sentence as input and generates test questions. The generated test questions are saved on the server.

[1749] Step 6:

[1750] The server automatically generates explanations for the generated test questions. The server receives the generated test questions as input and generates explanations using an explanation generator. The generated explanations are saved together with the test questions.

[1751] Step 7:

[1752] The user accesses and answers the generated test questions using a terminal. The server receives the user's answers and stores the answer data. After the user answers, the server automatically provides explanations.

[1753] Step 8:

[1754] The server analyzes the user's answer results and provides feedback. The server receives the user's answer data as input and analyzes it. Based on the analysis results, feedback is generated for the user and provided via the terminal.

[1755] Example 3

[1756] Next, a third embodiment of the third embodiment will be described. 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."

[1757] In the field of education, teachers spend a great deal of time and effort creating test questions based on curriculum guidelines and textbook content and providing explanations for them. Furthermore, as the workload of teachers increases, there is a risk that the quality of education will decline. Furthermore, there is a serious problem of staff shortages, and the introduction of an efficient educational support system is required. To solve these issues, a system is needed that automates the creation of test questions and their explanations, thereby reducing the workload of teachers.

[1758] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1759] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model. This makes it possible to automate the creation of test questions and their explanations, reducing the workload of teachers and improving the quality of education.

[1760] "Course of study" is an official guideline that defines the educational content and learning objectives provided by an educational institution.

[1761] "Textbook content" refers to the content of teaching materials created based on curriculum guidelines, and includes specific information and knowledge that students need to learn.

[1762] "Learning tools" refers to the methods and tools used to learn curriculum and textbook content.

[1763] "Question creation means" refers to the methods and tools used to create test questions based on what has been learned.

[1764] "Explanation creation means" refers to a method or tool for generating explanations for the created test questions.

[1765] A "generative AI model" is a model that uses artificial intelligence technology to generate text and analyze data, and is particularly good at natural language processing.

[1766] A "prompt" is an instruction given to a generative AI model to make it perform a specific task.

[1767] The present invention is a system for reducing the workload of teachers in educational settings and improving the quality of education. This system includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, and an explanation creation means for creating explanations for the created test questions using a generative AI model.

[1768] Hardware and software used

[1769] Hardware: Servers, terminals

[1770] Software: Generative AI models (e.g., GPT-4)

[1771] Specific operation of the system

[1772] 1. The user enters the question

[1773] A user uses the terminal interface to input a test question for which they would like an explanation. For example, the user inputs the question "Find the area of ​​a triangle."

[1774] 2. The device sends the problem to the server

[1775] The terminal receives the questions entered by the user and sends them to the server. Specifically, the terminal uses an HTTP request to send the question data to the server.

[1776] 3. The server sends a prompt to the generative AI model

[1777] Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[1778] The server sends the generated prompt to the generative AI model using an API request.

[1779] 4. Generative AI model generates commentary

[1780] The generative AI model analyzes the prompt received from the server and generates a solution to the problem. For example, it generates an explanation such as, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5 cm and the height is 10 cm, the area is (5 cm 10 cm) / 2 = 25 square centimeters."

[1781] 5. The server sends the commentary to the device.

[1782] The server sends the explanation received from the generative AI model to the device. Specifically, it sends the explanation data to the device using an HTTP response.

[1783] 6. The device displays the explanation to the user

[1784] The terminal displays the explanation received from the server to the user. Specifically, the explanation text is displayed on the terminal screen, allowing the user to understand the process of solving the problem.

[1785] Specific examples

[1786] Input question: "Find the area of ​​a triangle"

[1787] Prompt for generative AI model: "Please explain in detail how you solved the following problem: Find the area of ​​a triangle."

[1788] Generated explanation: "To find the area of ​​a triangle, multiply the base and height and divide by 2. For example, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[1789] In this way, the user can easily understand the process of solving the problem. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1790] Step 1:

[1791] The user enters the problem

[1792] Input: The user uses the terminal interface to enter the test question that requires explanation.

[1793] Specific action: The user enters "Find the area of ​​a triangle" into the input field of the terminal and clicks the submit button.

[1794] Output: The problem data entered into the terminal.

[1795] Step 2:

[1796] The device sends the problem to the server

[1797] Input: The problem data entered by the user.

[1798] Specific behavior: The device sends the problem data to the server using an HTTP POST request.

[1799] Output: The problem data sent to the server.

[1800] Step 3:

[1801] The server sends a prompt to the generative AI model

[1802] Input: The problem data sent to the server.

[1803] Specific operation: Based on the problem received by the server, a prompt is created to be sent to the generative AI model. For example, a prompt such as "Please explain in detail the process of solving the following problem: Calculate the area of ​​a triangle" is generated.

[1804] Output: The prompt sent to the generative AI model.

[1805] Step 4:

[1806] Generative AI model generates commentary

[1807] Input: The prompt sent to the generative AI model.

[1808] How it works: The generative AI model analyzes the prompt and generates a solution to the problem. For example, it generates an explanation like, "To find the area of ​​a triangle, multiply the base and height and divide by 2. Specifically, if the base is 5cm and the height is 10cm, the area is (5cm 10cm) / 2 = 25 square centimeters."

[1809] Output: The generated narrative data.

[1810] Step 5:

[1811] The server sends the commentary to the device.

[1812] Input: Commentary data received from the generative AI model.

[1813] Specific operation: The server sends explanatory data to the terminal using an HTTP response.

[1814] Output: Commentary data sent to the terminal.

[1815] Step 6:

[1816] The device displays the explanation to the user.

[1817] Input: Description data received from the server.

[1818] Specific operation: The device displays the received explanation on the screen, allowing the user to understand the process of solving the problem.

[1819] Output: Explanatory text displayed on the screen.

[1820] (Application example 3)

[1821] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1822] In traditional educational systems, it is difficult to provide detailed solutions to problems solved by students, and there is a lack of support for students to gain a deeper understanding of the problems. Furthermore, due to the heavy workload of teachers and limited time to provide individual feedback, the quality of education can decline. This poses a challenge, as students are unable to fully realize their learning potential.

[1823] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1824] In this invention, the server includes a learning means for learning curriculum guidelines and textbook content, a question creation means for creating test questions based on the learned content, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing detailed explanations of the answering process based on the created answers. This allows students to be provided with detailed answering processes for the questions they have solved, allowing them to gain a deeper understanding of the questions. It also reduces the workload of teachers and allows them to have more time to provide individual feedback, thereby improving the quality of education.

[1825] "Curriculum guidelines" are official guidelines that define the learning content and educational goals offered by educational institutions.

[1826] "Textbook content" refers to the content of learning materials created based on curriculum guidelines.

[1827] "Learning tools" are the methods and tools that students use to learn the curriculum and textbook content.

[1828] "Question creation means" refers to methods and tools for creating test questions based on what has been learned.

[1829] "Explanation creation means" refers to a method or tool for creating explanations for the created test questions.

[1830] An "answer generation means" is a method or tool for generating an answer to a question.

[1831] An "explanation generating means" is a method or tool for providing a detailed explanation of the solution process based on the generated answer.

[1832] A "system" is a set of devices and programs that function in conjunction with multiple means.

[1833] The system for carrying out this invention comprises a server and a user terminal. The server includes a learning means for learning the curriculum guidelines and textbook contents, a question creation means for creating test questions based on the learned contents, an explanation creation means for creating explanations for the created test questions, an answer creation means for creating answers to the questions, and an explanation creation means for providing a detailed explanation of the answering process based on the created answers.

[1834] Hardware and software used

[1835] Hardware: Servers, smartphones, tablets

[1836] Software: Python, OpenAI API

[1837] Data processing and calculation

[1838] The server receives test questions entered from the user's device and generates answers using a generative AI model. It then provides a detailed explanation of the answering process based on the generated answers. Specifically, the process is carried out as follows:

[1839] 1. Question input: Users input test questions using a smartphone or tablet.

[1840] 2. Answer generation: The server generates an answer to the problem using the OpenAI API. For example, if the problem is "Find the area of ​​a triangle. The base is 5 cm and the height is 10 cm," the answer will be "The area of ​​a triangle is calculated by multiplying the base by the height by 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1841] 3. Explanation Generation: The server provides a detailed explanation of the solution process based on the generated answer. For example, the server might generate an explanation like, "First, let's check the formula for calculating the area of ​​a triangle. The formula is base x height ÷ 2. In this problem, the base is 5 cm and the height is 10 cm, so applying the formula gives 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1842] Examples of concrete examples and prompts

[1843] Specific examples

[1844] Question: "Find the area of ​​a triangle. Its base is 5cm and its height is 10cm."

[1845] Answer: "The area of ​​a triangle is base x height ÷ 2. Therefore, 5 cm x 10 cm ÷ 2 = 25 square centimeters."

[1846] Explanation: First, let's look at the for...

Claims

1. A means for analyzing the learning contents input by a user and extracting important points; A means for generating test questions using a generative AI model based on a prompt sentence including the extracted important points; means for monitoring the user's emotions in response to the test questions; a means for adjusting the difficulty of the test questions based on the monitored emotions; and means for providing tailored test questions to said user; A system including:

2. a means for generating explanations for the generated test questions; means for providing said commentary to said user; The system of claim 1 further comprising:

3. a means for adjusting the difficulty of the learning content based on the monitored emotions; and The system of claim 1 further comprising:

Images