System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting training data based on a teaching course and storing the training data in a database; means for providing an interface for a teacher to select a test range; means for generating test questions by a generation AI based on the selected test range; means for outputting the generated test questions in the form of Word files and storing the test questions in cloud storages; means for a teacher to download and modify the test files; and means for uploading the modified test files again and storing the test files in the database.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's educational settings, teachers spend a great deal of time and effort creating tests to measure students' learning proficiency. In particular, with the declining birthrate and aging population, coupled with a teacher shortage, the workload per teacher is increasing, posing a risk of a decline in the quality of education. Furthermore, the tasks involved in creating and managing tests are complicated, and there is a lack of tools to carry them out efficiently. Therefore, the objective of this invention is to provide a system that improves work efficiency in educational settings, reduces the burden on teachers, and enables higher quality education. [Means for solving the problem]

[0005] The present invention is a system that includes a means for collecting learning data based on an educational curriculum and storing it in a database, and a means for providing an interface for teachers to select test topics. It also includes a means for a generation AI to generate test questions based on the selected test topics, and a means for outputting the generated test questions in Word file format and saving them in cloud storage. It also includes a means for teachers to download and modify test files, and a means for re-uploading the modified test files and storing them in the database. This system allows teachers to efficiently create, edit, and manage tests. It also allows questions to be generated using diagrams, making it possible to accommodate a variety of question formats. It also includes a means for storing and managing user accounts and request history for each school in a database, thereby improving operational efficiency and visualizing operations.

[0006] An "educational curriculum" is the learning content and progression plan established for each grade and subject at a particular educational institution.

[0007] "Learning data" refers to information collected based on the educational curriculum, such as teaching materials, textbook contents, curriculum guidelines, and past test questions.

[0008] A "database" is a system that stores data organized in a specific format so that it can be easily searched, accessed, and managed.

[0009] An "interface" is the means by which a user interacts with a system, including both visual and operational elements.

[0010] "Generative AI" is a program that uses artificial intelligence technology to automatically perform specific tasks, and in the present invention, it generates test questions.

[0011] "Test questions" are questions and problems used to assess a student's learning proficiency.

[0012] A "Word file format" is a type of file format generated by word processing software and has the extension ".doc" or ".docx."

[0013] "Cloud storage" is an online storage service that allows you to store and access data over the internet.

[0014] A "user account" is a credential that identifies a specific individual or organization with access to a system.

[0015] "Request history" is a record of requests made by a user to the system and the results of those requests.

[0016] A "pictorial question" is a test question that includes graphics or diagrams to provide visual explanation or information in the question.

[0017] "Revision" refers to the act of changing the test questions or content that were originally generated in order to improve the content or correct errors. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is a system for improving the efficiency of test creation work in educational settings, and provides a series of means for collecting learning data based on an educational curriculum, generating test questions, and managing them. Specific embodiments of the present invention are described below.

[0040] A natural language description of the program's processing

[0041] 1. Building a database of educational content

[0042] server:

[0043] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes the contents of textbooks for each subject and grade, curriculum guidelines, past test questions, etc. This data is organized and managed so that users can easily access it.

[0044] 2. Accepting test generation requests

[0045] Device:

[0046] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[0047] User:

[0048] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[0049] server:

[0050] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[0051] 3. Selecting the test scope

[0052] Device:

[0053] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[0054] User:

[0055] Select the curriculum category, subject, and specific test scope, and submit a test generation request.

[0056] server:

[0057] It receives a test generation request from the user, extracts learning data related to the specified test scope, and provides it as input data to the generation AI.

[0058] 4. Test Generation

[0059] server:

[0060] Based on the specified test scope, the AI ​​generates test questions. The generated questions are output in Word file format. The algorithm is adjusted to create a balanced set of questions.

[0061] 5. Providing and Modifying Tests

[0062] server:

[0063] The generated Word file is saved in cloud storage, and users are provided with a download link through which they can download the test questions.

[0064] Device:

[0065] When teachers download the generated test via the provided link, it is saved to their device as a Word file, where they can review the content and make corrections if necessary.

[0066] User:

[0067] After correcting the test, we ask that you upload it to cloud storage again and store the final version of the data in the database.

[0068] 6. Digital storage of tests

[0069] User:

[0070] The final modified test file is uploaded to cloud storage and stored in the database.

[0071] server:

[0072] Receives uploaded final test files and stores them in a database for future reference and reuse.

[0073] Specific examples

[0074] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in Word file format.

[0075] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0076] In this way, the system of the present invention makes test creation more efficient and significantly reduces the burden on teachers.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[0080] Step 2:

[0081] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[0082] Step 3:

[0083] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[0084] Step 4:

[0085] The user selects the curriculum category and subject, as well as the specific unit and scope from the drop-down menus, and then presses a button to submit a test generation request.

[0086] Step 5:

[0087] The server receives a test generation request from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0088] Step 6:

[0089] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, whether or not to include diagrams, etc. The generation AI automatically generates test questions based on this data.

[0090] Step 7:

[0091] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[0092] Step 8:

[0093] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[0094] Step 9:

[0095] Users can review the downloaded test questions and make corrections as necessary. The questions are saved in Word format, so they can be easily edited using standard document editing software.

[0096] Step 10:

[0097] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0098] Step 11:

[0099] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] Traditionally, test creation was a highly manual process that required a great deal of time and effort from teachers. Furthermore, inadequate database management made it difficult to reuse or efficiently search for past test questions. Furthermore, there was a lack of support for maintaining the balance and quality of the generated test questions. These tasks placed a significant burden on educational settings.

[0103] 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.

[0104] In this invention, the server includes means for collecting learning data and storing it in a database, means for providing an interface for teachers to select test topics, means for a generative AI model to generate test questions based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in remote storage, means for teachers to download and modify test files, means for re-uploading the modified test files and storing them in the database, means for periodically updating the collected data and generated test questions, and means for issuing session IDs to users. This enables more efficient test creation work and efficient data management.

[0105] "Learning data" refers to information collected based on the educational curriculum, such as the contents of textbooks for each subject and each grade, curriculum guidelines, and past test questions.

[0106] A "database" is an information management system that efficiently manages information organized according to specific rules and allows for quick search and updating as needed.

[0107] An "interface" is a window through which a user can interact with a system, such as a screen or input field.

[0108] A "generative AI model" is a program that uses artificial intelligence technology to automatically create test questions based on specified conditions.

[0109] A "document file" is a digital document stored in a format that contains text and images, such as a Word file.

[0110] "Remote storage" is an external data storage service that can be accessed via the Internet.

[0111] A "session ID" is an identifier issued to uniquely identify a user while the user is logged in.

[0112] "Users" are educational personnel who use this system to create and manage test questions.

[0113] The present invention is a system for streamlining test creation work in educational settings, and provides a series of means for collecting learning data based on educational courses, generating test questions, and managing them.

[0114] System hardware and software configuration

[0115] server:

[0116] Hardware: A server with a powerful processor, ample memory, and ample storage.

[0117] Software: Database management systems (e.g., SQL), generative AI models (e.g., GPT-3®), and cloud storage services (e.g., AWS® S3).

[0118] Device:

[0119] Hardware: PCs, tablets, smartphones, etc.

[0120] Software: User interface using a web browser (e.g., GOOGLE CHROME (registered trademark), Mozilla Firefox, etc.).

[0121] User:

[0122] Teachers and other educational professionals.

[0123] Operation flow

[0124] 1. Building a database of educational content:

[0125] The server collects information such as textbook contents for each subject and grade, curriculum guidelines, and past test questions based on the educational curriculum, and stores it in a database. The data is updated regularly to ensure that the latest information is always maintained.

[0126] 2. Accepting test generation requests:

[0127] The terminal provides an interface for teachers to log in, and teachers enter their username and password to authenticate with the server. The server verifies the authentication information and, if successful, issues a session ID. The teacher then moves to the main menu screen and selects the test scope.

[0128] 3. Select the test scope:

[0129] The device provides a menu for selecting the educational curriculum (elementary school, middle school, high school) and subject. Teachers select specific units and areas and submit a test generation request. The server extracts learning data related to the specified test area from the database and provides it to the generative AI model.

[0130] 4. Generate tests:

[0131] The server sends a prompt to the generative AI model to generate test questions. The generative AI model creates balanced test questions based on the specified range and outputs them in a document file format. The generated file is stored in cloud storage.

[0132] 5. Test provision and correction:

[0133] The server provides teachers with a download link for the test file stored in cloud storage. Teachers download the file from the link and check and edit the contents. Once edited, the file is uploaded back to cloud storage and saved in the server's database.

[0134] Specific examples

[0135] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in document file format.

[0136] The generated document file is stored in cloud storage, and teachers download it from the provided link. After checking the content of the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse. In this way, the system of the present invention streamlines test creation work and significantly reduces the burden on teachers.

[0137] Prompt Sentence Examples

[0138] Here are some example prompts to input to a generative AI model:

[0139] "Generate balanced test questions based on the user-specified high school mathematics unit 'Functions and Graphs.' Specifically, include questions on the basic properties of functions, questions requiring graphing, and questions requiring solutions given a range of variables."

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] Building a database of educational content

[0143] server:

[0144] The server collects learning data such as the contents of textbooks for each subject and each grade based on the educational curriculum, curriculum guidelines, and past test questions.

[0145] Input: Textbooks, curriculum guidelines, and past test question data for each subject and grade level.

[0146] After collecting the data, the server organizes the data by category (e.g., subject, grade, unit) and stores it in a database.

[0147] Output: The organized training data is stored in a database.

[0148] Specific behavior:

[0149] 1. The server periodically downloads the latest teaching material data from databases of educational institutions and publishers.

[0150] 2. Analyze the collected data and classify it by subject, grade, and unit.

[0151] 3. Store the classified data in a database and create an index for easy access by users.

[0152] Step 2:

[0153] Accepting test generation requests

[0154] Device:

[0155] The terminal displays a user interface that allows the teacher to enter a username and password.

[0156] Input: Username and password of the user.

[0157] Output: Sends an authentication request to the server.

[0158] User:

[0159] The user enters a username and password in the user interface and presses the "Login" button.

[0160] Enter your username and password.

[0161] server:

[0162] The server checks the received authentication information against the user information in its database.

[0163] If authentication is successful, the server issues a session ID to the user and loads the main menu screen.

[0164] Enter your username and password.

[0165] Output: Authentication result (success / failure) and session ID.

[0166] Specific behavior:

[0167] 1. The teacher accesses the login screen on the device.

[0168] 2. The user enters their username and password and clicks the login button.

[0169] 3. The server checks the username and password against its database and, if they match, issues a session ID.

[0170] 4. The user moves to the main menu screen.

[0171] Step 3:

[0172] Test Scope Selection

[0173] Device:

[0174] The device displays the main menu screen with a menu for selecting the educational curriculum (elementary school, junior high school, high school) and subject.

[0175] Input: Select the curriculum category, subject, and unit.

[0176] Output: A request to send the selected test ranges to the server.

[0177] User:

[0178] The user selects the curriculum category and subject from the drop-down menus, and then selects the appropriate unit or area.

[0179] Once the selection is complete, the user presses the "Request Generation" button.

[0180] Input: Select the curriculum category, subject, and unit.

[0181] server:

[0182] The server receives a test generation request from a user and extracts the specified range information from the database.

[0183] Input: Select the curriculum category, subject, and unit.

[0184] Output: Provide the extracted training data to a generative AI model.

[0185] Specific behavior:

[0186] 1. The teacher accesses the main menu screen on the device.

[0187] 2. Select the curriculum category, subject, and unit from the drop-down menus.

[0188] 3. Press the "Request Generation" button to send a request to the server.

[0189] 4. The server extracts the specified range of training data from the database and provides it to the generative AI model.

[0190] Step 4:

[0191] Test Generation

[0192] server:

[0193] The server sends a prompt to the generative AI model and begins generating test questions.

[0194] Input: Extracted training data, prompt sentence.

[0195] Output: A document file of the generated test questions.

[0196] Specific behavior:

[0197] 1. The server sends a prompt to the generative AI model, such as "Generate balanced test questions based on the 'Functions and Graphs' unit of high school mathematics specified by the user."

[0198] 2. The generative AI model generates test questions based on the input prompt and training data.

[0199] 3. The generated test questions are saved on the server as a document file (e.g., a Word file).

[0200] Step 5:

[0201] Providing and Modifying Tests

[0202] server:

[0203] The server uploads the generated test file to cloud storage and provides a download link to the user.

[0204] Input: The generated test question document file.

[0205] Output: Download link.

[0206] Device:

[0207] The device will download the generated test via the provided link and save it as a document file on the device.

[0208] Input: Download link.

[0209] Output: The downloaded document file.

[0210] User:

[0211] The user opens the document file on the terminal, checks the contents, and corrects the test questions as necessary.

[0212] Re-upload the corrected file to cloud storage.

[0213] Input: The downloaded document file.

[0214] Output: The modified document file.

[0215] Specific behavior:

[0216] 1. The server uploads the generated test file to cloud storage.

[0217] 2. Teachers will download the test file via the provided link and review and correct the content.

[0218] 3. Upload the modified test file back to the cloud storage.

[0219] Step 6:

[0220] Digital storage of tests

[0221] User:

[0222] The user uploads the final modified test file to cloud storage.

[0223] Input: The modified document file.

[0224] Output: The upload request.

[0225] server:

[0226] The server receives the uploaded modified test file and stores it in a database.

[0227] Input: The modified document file.

[0228] Output: The final file stored in the database.

[0229] Specific behavior:

[0230] 1. The teacher uploads the final, revised test file to cloud storage.

[0231] 2. The server receives the uploaded file and stores it in the appropriate folder in the database.

[0232] 3. Add tags (e.g., "High School Math," "Functions and Graphs," "Created September 2023") to saved files to organize them for future search and reuse.

[0233] (Application example 1)

[0234] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] Currently, teachers have to manually create test questions, which requires a great deal of time and effort. At the same time, it is difficult to individually adjust test questions based on each student's learning progress. This makes it difficult to consistently improve the quality of education, and these problems are particularly prevalent in learning centers and cram schools. Furthermore, there are insufficient means for digitally managing and correcting the generated test questions, which increases the workload of educators.

[0236] 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.

[0237] In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in PDF file format and saving them in cloud storage, means for educators to download the test files and modify them on their digital devices, means for re-uploading the modified test files and storing them in the database, means for educators to request the generation of customized test questions based on each student's learning progress, a customization function for adjusting the difficulty and format of the generated test questions, and means for providing a download link for the generated test questions. This allows teachers to easily generate personalized test questions based on each student's learning progress, saving time and effort, and managing and modifying them in digital format.

[0238] An "educational curriculum" is a systematic compilation of learning content and goals that should be taught for each age group or grade level within the educational system.

[0239] "Learning data" is a general term for information collected based on the educational process, such as teaching materials, lesson content, and test questions.

[0240] A "database" is a computer system that stores information and data in a structured manner so that it can be easily accessed, managed, and updated.

[0241] An "interface" is a medium for exchanging information between a user and a computer system, and includes screens, menus, buttons, etc.

[0242] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to automatically generate new test questions.

[0243] "PDF file format" is an abbreviation for Portable Document Format, and is a file format used to store and display documents electronically.

[0244] "Cloud storage" is a service for storing, sharing, and managing files online via the Internet.

[0245] "Digital terminal" is a general term for electronic devices that process information, such as smartphones, tablets, and computers.

[0246] "Customization function" refers to a function that allows users to personalize system and service settings according to their requests and meet their specific needs.

[0247] A "download link" is a URL used to download files on the Internet; by clicking on it you can obtain the desired file.

[0248] MODE FOR CARRYING OUT THE INVENTION

[0249] The present invention provides a system for improving the efficiency of test creation work in educational settings and for supporting individualized learning progress. Specific embodiments of this system are described below.

[0250] This system first collects learning data based on the educational curriculum and stores it in a database. The learning data includes teaching materials and past test questions for each subject and age group. This data is collected and stored on a server.

[0251] Next, an interface is provided for the educator to select the test scope. The interface includes a screen where the educator attempts to log in and a main menu that is displayed after successful authentication. The educator enters a username and password, is authenticated with the server, and moves to the main menu. Here, the educator selects the test scope.

[0252] Based on the selected test scope, the generation AI generates test questions. The test scope information is sent to the server, which then provides the generation AI with relevant learning data based on this information. The generation AI generates test questions using a machine learning algorithm (specifically, GPT-4 (registered trademark)). The generated test questions are saved on the server in PDF file format.

[0253] The generated PDF file is stored in cloud storage, and a download link is provided to the educator. The educator can download the PDF file via this link, review the content on a digital device, and make any necessary corrections. After making corrections, the file can be uploaded back to cloud storage, and the final test file can be stored in the database.

[0254] Furthermore, the system allows educators to request the generation of customized test questions based on each student's learning progress. Educators can provide the AI ​​with prompts to generate personalized test questions according to the student's progress, and adjust the difficulty and format of the test questions.

[0255] Hardware and software used

[0256] Server: AWS or Google Cloud

[0257] Database: MongoDB

[0258] Generative AI model: GPT-4 (OpenAI(R))

[0259] Client side: React Native (mobile apps), React.js (web apps)

[0260] Other tools: User authentication and session management using JSON Web Tokens (JWT), PDF file generation and management using Node.js, cloud storage with AWS S3

[0261] Specific examples

[0262] For example, let's say a mathematics teacher at a learning center wants to create a test on "simultaneous equations" for second-year junior high school students. The teacher logs into the system, selects "simultaneous equations" from the range of junior high school mathematics, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions based on the following prompt:

[0263] Example prompt sentence:

[0264] Based on the following educational data, please generate a test question on simultaneous equations for second-year junior high school students. The test should have the following structure:

[0265] 1. Basic problems (calculation problems)

[0266] 2. Applied questions (word questions)

[0267] 3. Sample answers and explanations for each question

[0268] The generated PDF file is stored in cloud storage, and teachers can download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in its database for future reference and reuse.

[0269] As described above, the system of the present invention improves the efficiency of test creation work in educational settings and significantly reduces the burden on educators.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] Collecting learning data and storing it in a database

[0273] The server collects learning data based on the curriculum and stores it in a database. Specifically, it collects data such as teaching materials and past test questions, and stores them in a structured MongoDB database. This prepares the basic data for use in subsequent test generation processes.

[0274] Step 2:

[0275] User authentication and interface provisioning

[0276] A user attempts to log in to a system using a terminal. They enter a username and password and request authentication from the server. The server checks the authentication information against a database, and if successful, issues session information and provides the user with an interface that displays the main menu. This prepares the user for accessing the system.

[0277] Step 3:

[0278] Test Scope Selection

[0279] The educator uses the device to select the educational curriculum category (e.g., junior high school), subject (e.g., mathematics), and specific unit (e.g., simultaneous equations). The selected information is sent to the server, which uses this information to extract relevant learning data from the database and prepares it as input data for the subsequent generative AI model.

[0280] Step 4:

[0281] Generate test questions

[0282] The server provides training data to a generative AI model (GPT-4) based on the specified test scope and generates test questions. Specifically, it inputs a prompt (e.g., "Based on the educational data below, please generate test questions on simultaneous equations for second-year junior high school students") to the generative AI model and receives the test questions output by the model. The generated questions are converted into PDF file format and temporarily saved on the server.

[0283] Step 5:

[0284] Save test questions and provide download links

[0285] The server saves the generated PDF file in cloud storage (such as AWS S3) and provides a download link to the educator. The user then downloads the PDF file from the provided link using their device and checks and corrects the content of the test questions.

[0286] Step 6:

[0287] Fix the test file and re-upload it

[0288] The educator opens the downloaded PDF file on their device and makes any necessary corrections. Once the corrections are complete, they upload it back to the cloud storage and request the server to save the final test file. The server receives the corrected file and stores it in a database.

[0289] Step 7:

[0290] Request for personalized test question generation

[0291] Educators provide the generative AI model with prompts to generate customized test questions based on each student's learning progress. The server then provides input data to the generative AI based on the prompts to generate personalized test questions.

[0292] Step 8:

[0293] Output and save customized test questions

[0294] The server outputs the personalized test questions as a PDF file and saves it in cloud storage. Educators are provided with a new download link, and users can download the file via their devices, check it, and make corrections. This provides test questions optimized for each student's learning progress.

[0295] 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.

[0296] The present invention is a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. This system combines a series of means for collecting learning data based on educational curriculum, generating test questions, and managing them with an emotion engine that recognizes the user's emotions and provides appropriate tests and feedback. Specific embodiments of the present invention are described below.

[0297] A natural language description of the program's processing

[0298] 1. Building a database of educational content

[0299] server:

[0300] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes textbook content, curriculum guidelines, and past test questions. This data is organized and stored in an easy-to-search format.

[0301] 2. Accepting test generation requests

[0302] Device:

[0303] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[0304] User:

[0305] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[0306] server:

[0307] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[0308] 3. Selecting the test area and checking the emotional state

[0309] Device:

[0310] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[0311] User:

[0312] Users select the curriculum category, subject, and specific test topics from drop-down menus, then press a button to submit a test generation request. The interface also features an emotion engine that analyzes the user's facial expressions and tone of voice to check their emotional state.

[0313] server:

[0314] It receives a test generation request and emotional state from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0315] 4. Test generation and emotion-based adjustment

[0316] server:

[0317] The generation AI is started and input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included are passed in. The AI ​​also adjusts the difficulty and type of test appropriately based on the user's emotional state provided by the emotion engine.

[0318] The generative AI automatically generates test questions based on this data.

[0319] 5. Providing and Modifying Tests

[0320] server:

[0321] The generated test questions are output as Word files and saved to cloud storage. A unique download link for the saved file is generated and notified to the user.

[0322] Device:

[0323] A download link for the test file is displayed to the teacher. The teacher clicks the link to download the Word file and opens it on their device.

[0324] 6. Test correction and emotional feedback

[0325] User:

[0326] Review the downloaded test questions and make any necessary corrections. The questions are saved in Word format, making them easy to edit using standard document editing software. While correcting, the emotion engine analyzes the user's emotions and suggests appropriate feedback and relaxation methods if stress is detected.

[0327] 7. Digital storage of tests

[0328] User:

[0329] The final test file, after corrections are completed, is uploaded to cloud storage again and stored in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0330] server:

[0331] The system receives the uploaded final test file, associates it with the user's account information, and stores it in a database. This allows for the efficient organization and management of each school's test creation history and stored data.

[0332] Specific examples

[0333] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[0334] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0335] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[0336] The processing flow will be explained below.

[0337] Step 1:

[0338] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[0339] Step 2:

[0340] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[0341] Step 3:

[0342] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[0343] Step 4:

[0344] The user selects the curriculum category and subject, as well as the specific unit and scope from drop-down menus, and presses a button to send a test generation request. At this time, the emotion engine analyzes the user's facial expressions and tone of voice to check their emotional state.

[0345] Step 5:

[0346] The server receives the user's test generation request and emotional state information, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0347] Step 6:

[0348] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included.The server also appropriately adjusts the difficulty and type of test based on the user's emotional state using an emotion engine.

[0349] Step 7:

[0350] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[0351] Step 8:

[0352] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[0353] Step 9:

[0354] The system checks the test questions downloaded by the user and makes corrections as necessary. The questions are saved in Word file format, making them easy to edit using common document editing software. While the user is correcting the questions, the emotion engine analyzes their emotions and suggests appropriate feedback and relaxation methods if stress is felt.

[0355] Step 10:

[0356] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0357] Step 11:

[0358] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[0359] Examples:

[0360] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[0361] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0362] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[0363] Example 2

[0364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0365] Traditional test creation tasks require a great deal of time and effort from educators, often causing mental strain. Furthermore, tests are created without taking into account the educator's emotional state, which can increase stress for the educator. Furthermore, there are problems with the inefficient editing and storage of generated tests, making it difficult to reuse past data.

[0366] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to log in by entering authentication information, means for providing an interface for educators to select test topics and for receiving the selected test topics and emotional state, means for analyzing the educator's emotions using an emotion analysis engine and adjusting the test content based on the results, means for generating test questions using a generation AI based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in cloud storage, means for educators to download and modify the test file, means for re-uploading the modified test file and storing it in the database, and means for monitoring the educator's emotions during modification and providing feedback if stress is detected. This makes it possible to improve the efficiency of test creation work, optimize the work environment by taking into account the educator's emotional state, and reduce mental burden.

[0367] "Curriculum" refers to the learning content based on the curriculum guidelines and textbooks established by national and local educational institutions.

[0368] "Learning data" refers to information including the contents of textbooks related to the educational curriculum, curriculum guidelines, and past test questions.

[0369] A "database" refers to a digital system for organizing collected learning data and storing it in an easily searchable format.

[0370] "Interface" refers to the means that provides a screen and input methods for educators to interact with the system.

[0371] An "emotion analysis engine" refers to software that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[0372] "Generative AI" refers to artificial intelligence that automatically generates test questions based on specified parameters.

[0373] "Cloud storage" refers to a service that stores and manages data remotely via the Internet.

[0374] "Document file format" refers to a digital format for storing multi-page documents containing text and images.

[0375] "Educator" refers to a person whose job is to provide education to students.

[0376] "Feedback" refers to the advice and warnings the system provides based on the educator's emotional state.

[0377] This system aims to improve the efficiency of test creation work in educational settings and reduce the mental burden on educators. This system combines a means of collecting learning data based on educational curriculum, generating and managing test questions, and an emotion engine that recognizes educators' emotions and provides appropriate tests and feedback.

[0378] Collecting learning data and storing it in a database

[0379] server:

[0380] The server automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the Internet and books.

[0381] This data is organized by curriculum and stored in an SQL database, which is indexed and has an optimized search function to enable quick data access.

[0382] Educator Certification and Testing Options

[0383] Device:

[0384] A form for teachers to log in is displayed, with fields for entering username and password.

[0385] User:

[0386] Enter your username and password and press the login button.

[0387] server:

[0388] Receives form data and verifies it with user information in the database. If authentication is successful, creates a session and transitions to the main menu screen.

[0389] Selecting test areas and checking emotional state

[0390] Device:

[0391] Provides drop-down menus for selecting curriculum category (elementary, middle, high school), subject, and specific unit or area.

[0392] User:

[0393] Select the curriculum, subject, and unit from the menu and submit a test generation request.

[0394] Device:

[0395] The emotion engine analyzes the user's facial expressions and tone of voice in real time.

[0396] server:

[0397] The system receives the user's selected range and emotional state and extracts relevant learning data from the database.

[0398] Test generation and emotion-based adjustment

[0399] server:

[0400] The extracted training data and test parameters (number of questions, difficulty level, presence or absence of diagrams) are passed as input to the generation AI. Based on the analysis results of the emotion engine, the difficulty level of the test is adjusted appropriately.

[0401] Examples:

[0402] When a teacher wants to create a test for the "Functions and Graphs" unit in high school mathematics, the teacher logs in to the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately. The generated Word file is saved in cloud storage, and the teacher can download it from the provided link.

[0403] Providing and Modifying Tests

[0404] server:

[0405] The generated test questions are saved as Word files and uploaded to cloud storage. A download link is generated from the cloud storage and notified to the user.

[0406] Device:

[0407] Provide instructors with a download link for the test file.

[0408] User:

[0409] Click the download link to download the test questions in Word file format.

[0410] Test correction and emotional feedback

[0411] User:

[0412] Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections.

[0413] During the correction, the emotion engine will again analyze the user's emotions and provide feedback if stress is detected.

[0414] Digital storage of tests

[0415] User:

[0416] Upload the modified test file back to cloud storage.

[0417] server:

[0418] Uploaded files are stored in a database and associated with user account information for future reference and reuse.

[0419] Example prompt sentence:

[0420] "Generate test questions for functions and graphs. The questions should be of medium difficulty and include diagrams. Also, adjust the difficulty level slightly lower if the user is feeling stressed."

[0421] In this way, the system of the present invention can improve the efficiency of test creation work while also taking into account the emotional state of the educator, thereby reducing the mental burden on the educator and providing a better teaching environment.

[0422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] Server: Automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the internet and books. Organizes the extracted data by educational curriculum and stores it in an SQL database.

[0425] Specific operations: Learning data is collected using scraping tools and OCR software and entered into a database, creating a highly searchable database of educational content.

[0426] Input: Textbook PDF file, web page

[0427] Output: Organized training data (SQL database)

[0428] Step 2:

[0429] Terminal: Display a form for teachers to log in, and provide fields for entering a username and password.

[0430] User: Enter your username and password and click the login button.

[0431] Server: Receives the form data and verifies it with the user information in the database. If authentication is successful, creates a session, issues a session ID to the user, and transitions to the main menu screen.

[0432] What it does: It hashes the user information and compares it with the information in the database. If the authentication information matches, it generates a session ID and stores it in a cookie.

[0433] Input: Username, Password

[0434] Output: Session ID

[0435] Step 3:

[0436] Device: Provides drop-down menus for selecting curriculum division (elementary, middle, high school), subject, and specific units or areas.

[0437] User: Selects the curriculum, subject, and unit from the menu and sends a test generation request. The device analyzes the user's facial expressions and tone of voice in real time using an emotion analysis engine.

[0438] Server: Receives the user's selected range and emotional state and extracts relevant learning data from the database.

[0439] What it does: The emotion analysis engine analyzes webcam footage, measures facial muscle movements to infer emotional state, and executes database queries to extract training data relevant to the specified test areas.

[0440] Input: Curriculum classification, subject, unit, emotional state (facial expression analysis)

[0441] Output: Extracted training data, emotional state data

[0442] Step 4:

[0443] Server: The extracted training data and test parameters (number of questions, difficulty level, whether or not diagrams are included) are passed to the generation AI as input. The difficulty level of the test is adjusted appropriately based on the analysis results of the emotion engine.

[0444] Specific behavior: Sends prompts to the generation AI, instructing it to generate questions with a medium level of difficulty for a specific range. Fine-tunes the difficulty setting based on data from the emotion engine.

[0445] Input: training data, test set parameters, emotional state data

[0446] Output: Generated test questions

[0447] Step 5:

[0448] Server: Saves the generated test questions in Word file format and uploads them to cloud storage. Generates a download link from the cloud storage and notifies the user.

[0449] On the device: Provide the teacher with a download link for the test file.

[0450] User: Click on the download link to download the test questions in Word file format.

[0451] Specific behavior: Upload the generated Word file to a cloud storage service (e.g., Amazon S3) and notify the user of the generated link.

[0452] Input: Generated test questions (Word file), cloud storage credentials

[0453] Output: Download link

[0454] Step 6:

[0455] User: Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections. While correcting, the emotion analysis engine analyzes the user's emotions again and displays feedback if stress is detected.

[0456] What it does: While you edit, the emotion analysis engine continuously analyzes your facial expressions and tone of voice, and if stress is detected, a pop-up message will appear.

[0457] Input: Test questions (Word file), real-time emotional state data

[0458] Output: Fixed test questions, feedback messages

[0459] Step 7:

[0460] User: Upload the modified test file back to cloud storage.

[0461] Server: Stores uploaded files in a database and associates them with user account information for future reference and reuse.

[0462] Specific operation: The metadata of uploaded files (creation date and time, subject, unit, etc.) is saved in a database for efficient file management.

[0463] Input: Modified test file (Word file), user account information

[0464] Output: Test files stored in the database

[0465] (Application example 2)

[0466] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0467] Creating tests in educational settings takes a lot of time, placing a heavy burden on teachers. The stress and fatigue felt during the work are also a problem. Similarly, inspection work in factories and other places requires time and effort to manually plan and execute inspections, placing a heavy mental burden on workers. There is a need to improve this situation, increase work efficiency, and reduce the mental burden on workers.

[0468] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for teachers to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in Word file format and saving them in cloud storage, means for recognizing user emotions and adjusting the difficulty and type related to the test topics, means for teachers to download and modify test files, and means for re-uploading the modified test files and storing them in the database. This makes it possible to streamline test creation work and reduce the mental burden on teachers and workers.

[0469] Definitions of important words

[0470] "Curriculum" refers to the learning content and structure of lessons offered at schools and educational institutions, as well as the progress plan for each grade level.

[0471] "Learning data" refers to learning materials, reference materials, past test questions, and information based on curriculum guidelines for students.

[0472] A "database" is a system or mechanism that organizes and stores information so that it can be searched and used as needed.

[0473] "Interface" refers to the screens and input devices used by teachers and users to operate the system, and specifically includes login screens and menu screens.

[0474] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate content such as test questions based on specified conditions.

[0475] "Generating test questions" means creating test questions, including question statements, options, and answers, based on the training data.

[0476] "Cloud storage" refers to an online data storage service accessible via the Internet where you can store and manage data.

[0477] "Recognizing the user's emotions" means determining the user's mental state, such as stress or fatigue, through analysis of the user's facial expressions and tone of voice.

[0478] "Adjusting the difficulty and type of questions related to the test scope" refers to changing the difficulty and type of questions given in consideration of the user's emotional state.

[0479] "Downloading" means importing files or data stored in cloud storage, etc., to your device via the Internet or a network.

[0480] "Uploading" refers to sending and storing data or files from your device via the Internet or a network to an online service such as cloud storage.

[0481] The present invention provides a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. Specific embodiments of the present invention will be described below.

[0482] Hardware and Software Configuration

[0483] 1. Hardware:

[0484] Server: Responsible for database management and running generative AI.

[0485] Device: The device used by the teacher (e.g., PC, tablet, etc.).

[0486] 2. Software:

[0487] Database Management System: A database for storing training data and test files.

[0488] Generative AI: Software that automatically generates test questions using AI models.

[0489] Emotion Recognition Engine: Software that recognizes teachers' emotions and provides feedback.

[0490] Data processing and calculation methods

[0491] The server collects learning data and stores it in a database. Teachers access the interface using their devices and select the test topics. The information on the selected test topics is sent to the server, which then passes it on to the generation AI as input. The generation AI generates test questions and saves the results in cloud storage as a Word file.

[0492] The emotion recognition engine analyzes the teacher's facial expressions and tone of voice through the interface to determine their stress level, and this situational data is sent to the server, which then adjusts the difficulty and type of test questions.

[0493] Specific examples

[0494] For example, consider the case where a worker at a factory is performing a regular inspection and the inspection work plan is automatically generated. The worker wears a smartphone or smart glasses, and an emotion recognition engine monitors the worker's emotional state. When the worker feels stressed, the server automatically adjusts the content and order of the inspection tasks to optimize work efficiency.

[0495] Prompt Sentence Examples

[0496] Here is a specific example of an input prompt sentence for the generative AI model.

[0497] Emotion recognition: "High stress"

[0498] Generate a list of inspection tasks and eliminate low priority tasks.

[0499] This method makes it possible to achieve both overall efficiency and the mental health of workers not only in test creation work but also in a variety of on-site tasks in factories and other places.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Program processing steps

[0502] Step 1:

[0503] The server collects learning data based on the curriculum and stores it in a database. The input data includes textbook content, curriculum guidelines, and past test questions, and the output is to organize and store this data in a database in an easy-to-search format.

[0504] Step 2:

[0505] The user (teacher) accesses the login interface using a terminal and attempts authentication by entering their username and password. The server compares the authentication information with the database, and if authentication is successful, issues a session and transitions to the main menu. The input is the user's authentication information, and the output is session information if successful.

[0506] Step 3:

[0507] The user is directed to an interface for selecting the curriculum category, subject, and test area. The input is the user's selection information, and the output is the selected test area information.

[0508] Step 4:

[0509] The device interface uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to check their emotional state. The input is the user's facial expressions and voice data, and the output is the analyzed emotional state.

[0510] Step 5:

[0511] The server receives a test generation request and emotional state from the user, and extracts training data related to the specified test range from the database. The input is the test generation request and emotional state, and the output is the extracted training data.

[0512] Step 6:

[0513] The server starts the generation AI and passes parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included as input to the generation AI.The server also appropriately adjusts the difficulty and type of test based on the emotional state provided by the emotion engine.The input is the generation parameters and the emotional state, and the output is the generated test questions.

[0514] Step 7:

[0515] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link. The input is the generated test questions, and the output is the save and download link to cloud storage.

[0516] Step 8:

[0517] A user clicks on the download link of the test file on the device and downloads the Word file. The input is the download link, and the output is the test file saved on the device.

[0518] Step 9:

[0519] The system checks the test questions downloaded by the user and makes corrections as necessary. During corrections, the emotion engine checks the user's emotional state again and provides appropriate feedback if stress is detected. The input is the corrected test file, and the output is the final test file.

[0520] Step 10:

[0521] The user uploads the final test file to the cloud storage again, and the server receives this file, associates it with the user account information, and stores it in the database. The input is the final test file, and the output is the file stored in the database.

[0522] 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.

[0523] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] 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.

[0525] [Second embodiment]

[0526] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0527] 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.

[0528] 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).

[0529] 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.

[0530] 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.

[0531] 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).

[0532] 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. 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.

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0538] The present invention is a system for improving the efficiency of test creation work in educational settings, and provides a series of means for collecting learning data based on an educational curriculum, generating test questions, and managing them. Specific embodiments of the present invention are described below.

[0539] A natural language description of the program's processing

[0540] 1. Building a database of educational content

[0541] server:

[0542] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes the contents of textbooks for each subject and grade, curriculum guidelines, past test questions, etc. This data is organized and managed so that users can easily access it.

[0543] 2. Accepting test generation requests

[0544] Device:

[0545] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[0546] User:

[0547] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[0548] server:

[0549] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[0550] 3. Selecting the test scope

[0551] Device:

[0552] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[0553] User:

[0554] Select the curriculum category, subject, and specific test scope, and submit a test generation request.

[0555] server:

[0556] It receives a test generation request from the user, extracts learning data related to the specified test scope, and provides it as input data to the generation AI.

[0557] 4. Test Generation

[0558] server:

[0559] Based on the specified test scope, the AI ​​generates test questions. The generated questions are output in Word file format. The algorithm is adjusted to create a balanced set of questions.

[0560] 5. Providing and Modifying Tests

[0561] server:

[0562] The generated Word file is saved in cloud storage, and users are provided with a download link through which they can download the test questions.

[0563] Device:

[0564] When teachers download the generated test via the provided link, it is saved to their device as a Word file, where they can review the content and make corrections if necessary.

[0565] User:

[0566] After correcting the test, we ask that you upload it to cloud storage again and store the final version of the data in the database.

[0567] 6. Digital storage of tests

[0568] User:

[0569] The final modified test file is uploaded to cloud storage and stored in the database.

[0570] server:

[0571] Receives uploaded final test files and stores them in a database for future reference and reuse.

[0572] Specific examples

[0573] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in Word file format.

[0574] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0575] In this way, the system of the present invention makes test creation more efficient and significantly reduces the burden on teachers.

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[0579] Step 2:

[0580] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[0581] Step 3:

[0582] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[0583] Step 4:

[0584] The user selects the curriculum category and subject, as well as the specific unit and scope from the drop-down menus, and then presses a button to submit a test generation request.

[0585] Step 5:

[0586] The server receives a test generation request from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0587] Step 6:

[0588] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, whether or not to include diagrams, etc. The generation AI automatically generates test questions based on this data.

[0589] Step 7:

[0590] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[0591] Step 8:

[0592] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[0593] Step 9:

[0594] Users can review the downloaded test questions and make corrections as necessary. The questions are saved in Word format, so they can be easily edited using standard document editing software.

[0595] Step 10:

[0596] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0597] Step 11:

[0598] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[0599] Example 1

[0600] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0601] Traditionally, test creation was a highly manual process that required a great deal of time and effort from teachers. Furthermore, inadequate database management made it difficult to reuse or efficiently search for past test questions. Furthermore, there was a lack of support for maintaining the balance and quality of the generated test questions. These tasks placed a significant burden on educational settings.

[0602] 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.

[0603] In this invention, the server includes means for collecting learning data and storing it in a database, means for providing an interface for teachers to select test topics, means for a generative AI model to generate test questions based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in remote storage, means for teachers to download and modify test files, means for re-uploading the modified test files and storing them in the database, means for periodically updating the collected data and generated test questions, and means for issuing session IDs to users. This enables more efficient test creation work and efficient data management.

[0604] "Learning data" refers to information collected based on the educational curriculum, such as the contents of textbooks for each subject and each grade, curriculum guidelines, and past test questions.

[0605] A "database" is an information management system that efficiently manages information organized according to specific rules and allows for quick search and updating as needed.

[0606] An "interface" is a window through which a user can interact with a system, such as a screen or input field.

[0607] A "generative AI model" is a program that uses artificial intelligence technology to automatically create test questions based on specified conditions.

[0608] A "document file" is a digital document stored in a format that contains text and images, such as a Word file.

[0609] "Remote storage" is an external data storage service that can be accessed via the Internet.

[0610] A "session ID" is an identifier issued to uniquely identify a user while the user is logged in.

[0611] "Users" are educational personnel who use this system to create and manage test questions.

[0612] The present invention is a system for streamlining test creation work in educational settings, and provides a series of means for collecting learning data based on educational courses, generating test questions, and managing them.

[0613] System hardware and software configuration

[0614] server:

[0615] Hardware: A server with a powerful processor, ample memory, and ample storage.

[0616] Software: Database management systems (e.g., SQL), generative AI models (e.g., GPT-3), cloud storage services (e.g., AWS S3).

[0617] Device:

[0618] Hardware: PCs, tablets, smartphones, etc.

[0619] Software: User interface using a web browser (Google Chrome, Mozilla Firefox, etc.).

[0620] User:

[0621] Teachers and other educational professionals.

[0622] Operation flow

[0623] 1. Building a database of educational content:

[0624] The server collects information such as textbook contents for each subject and grade, curriculum guidelines, and past test questions based on the educational curriculum, and stores it in a database. The data is updated regularly to ensure that the latest information is always maintained.

[0625] 2. Accepting test generation requests:

[0626] The terminal provides an interface for teachers to log in, and teachers enter their username and password to authenticate with the server. The server verifies the authentication information and, if successful, issues a session ID. The teacher then moves to the main menu screen and selects the test scope.

[0627] 3. Select the test scope:

[0628] The device provides a menu for selecting the educational curriculum (elementary school, middle school, high school) and subject. Teachers select specific units and areas and submit a test generation request. The server extracts learning data related to the specified test area from the database and provides it to the generative AI model.

[0629] 4. Generate tests:

[0630] The server sends a prompt to the generative AI model to generate test questions. The generative AI model creates balanced test questions based on the specified range and outputs them in a document file format. The generated file is stored in cloud storage.

[0631] 5. Test provision and correction:

[0632] The server provides teachers with a download link for the test file stored in cloud storage. Teachers download the file from the link and check and edit the contents. Once edited, the file is uploaded back to cloud storage and saved in the server's database.

[0633] Specific examples

[0634] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in document file format.

[0635] The generated document file is stored in cloud storage, and teachers download it from the provided link. After checking the content of the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse. In this way, the system of the present invention streamlines test creation work and significantly reduces the burden on teachers.

[0636] Prompt Sentence Examples

[0637] Here are some example prompts to input to a generative AI model:

[0638] "Generate balanced test questions based on the user-specified high school mathematics unit 'Functions and Graphs.' Specifically, include questions on the basic properties of functions, questions requiring graphing, and questions requiring solutions given a range of variables."

[0639] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0640] Step 1:

[0641] Building a database of educational content

[0642] server:

[0643] The server collects learning data such as the contents of textbooks for each subject and each grade based on the educational curriculum, curriculum guidelines, and past test questions.

[0644] Input: Textbooks, curriculum guidelines, and past test question data for each subject and grade level.

[0645] After collecting the data, the server organizes the data by category (e.g., subject, grade, unit) and stores it in a database.

[0646] Output: The organized training data is stored in a database.

[0647] Specific behavior:

[0648] 1. The server periodically downloads the latest teaching material data from databases of educational institutions and publishers.

[0649] 2. Analyze the collected data and classify it by subject, grade, and unit.

[0650] 3. Store the classified data in a database and create an index for easy access by users.

[0651] Step 2:

[0652] Accepting test generation requests

[0653] Device:

[0654] The terminal displays a user interface that allows the teacher to enter a username and password.

[0655] Input: Username and password of the user.

[0656] Output: Sends an authentication request to the server.

[0657] User:

[0658] The user enters a username and password in the user interface and presses the "Login" button.

[0659] Enter your username and password.

[0660] server:

[0661] The server checks the received authentication information against the user information in its database.

[0662] If authentication is successful, the server issues a session ID to the user and loads the main menu screen.

[0663] Enter your username and password.

[0664] Output: Authentication result (success / failure) and session ID.

[0665] Specific behavior:

[0666] 1. The teacher accesses the login screen on the device.

[0667] 2. The user enters their username and password and clicks the login button.

[0668] 3. The server checks the username and password against its database and, if they match, issues a session ID.

[0669] 4. The user moves to the main menu screen.

[0670] Step 3:

[0671] Test Scope Selection

[0672] Device:

[0673] The device displays the main menu screen with a menu for selecting the educational curriculum (elementary school, junior high school, high school) and subject.

[0674] Input: Select the curriculum category, subject, and unit.

[0675] Output: A request to send the selected test ranges to the server.

[0676] User:

[0677] The user selects the curriculum category and subject from the drop-down menus, and then selects the appropriate unit or area.

[0678] Once the selection is complete, the user presses the "Request Generation" button.

[0679] Input: Select the curriculum category, subject, and unit.

[0680] server:

[0681] The server receives a test generation request from a user and extracts the specified range information from the database.

[0682] Input: Select the curriculum category, subject, and unit.

[0683] Output: Provide the extracted training data to a generative AI model.

[0684] Specific behavior:

[0685] 1. The teacher accesses the main menu screen on the device.

[0686] 2. Select the curriculum category, subject, and unit from the drop-down menus.

[0687] 3. Press the "Request Generation" button to send a request to the server.

[0688] 4. The server extracts the specified range of training data from the database and provides it to the generative AI model.

[0689] Step 4:

[0690] Test Generation

[0691] server:

[0692] The server sends a prompt to the generative AI model and begins generating test questions.

[0693] Input: Extracted training data, prompt sentence.

[0694] Output: A document file of the generated test questions.

[0695] Specific behavior:

[0696] 1. The server sends a prompt to the generative AI model, such as "Generate balanced test questions based on the 'Functions and Graphs' unit of high school mathematics specified by the user."

[0697] 2. The generative AI model generates test questions based on the input prompt and training data.

[0698] 3. The generated test questions are saved on the server as a document file (e.g., a Word file).

[0699] Step 5:

[0700] Providing and Modifying Tests

[0701] server:

[0702] The server uploads the generated test file to cloud storage and provides a download link to the user.

[0703] Input: The generated test question document file.

[0704] Output: Download link.

[0705] Device:

[0706] The device will download the generated test via the provided link and save it as a document file on the device.

[0707] Input: Download link.

[0708] Output: The downloaded document file.

[0709] User:

[0710] The user opens the document file on the terminal, checks the contents, and corrects the test questions as necessary.

[0711] Re-upload the corrected file to cloud storage.

[0712] Input: The downloaded document file.

[0713] Output: The modified document file.

[0714] Specific behavior:

[0715] 1. The server uploads the generated test file to cloud storage.

[0716] 2. Teachers will download the test file via the provided link and review and correct the content.

[0717] 3. Upload the modified test file back to the cloud storage.

[0718] Step 6:

[0719] Digital storage of tests

[0720] User:

[0721] The user uploads the final modified test file to cloud storage.

[0722] Input: The modified document file.

[0723] Output: The upload request.

[0724] server:

[0725] The server receives the uploaded modified test file and stores it in a database.

[0726] Input: The modified document file.

[0727] Output: The final file stored in the database.

[0728] Specific behavior:

[0729] 1. The teacher uploads the final, revised test file to cloud storage.

[0730] 2. The server receives the uploaded file and stores it in the appropriate folder in the database.

[0731] 3. Add tags (e.g., "High School Math," "Functions and Graphs," "Created September 2023") to saved files to organize them for future search and reuse.

[0732] (Application example 1)

[0733] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0734] Currently, teachers have to manually create test questions, which requires a great deal of time and effort. At the same time, it is difficult to individually adjust test questions based on each student's learning progress. This makes it difficult to consistently improve the quality of education, and these problems are particularly prevalent in learning centers and cram schools. Furthermore, there are insufficient means for digitally managing and correcting the generated test questions, which increases the workload of educators.

[0735] 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.

[0736] In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in PDF file format and saving them in cloud storage, means for educators to download the test files and modify them on their digital devices, means for re-uploading the modified test files and storing them in the database, means for educators to request the generation of customized test questions based on each student's learning progress, a customization function for adjusting the difficulty and format of the generated test questions, and means for providing a download link for the generated test questions. This allows teachers to easily generate personalized test questions based on each student's learning progress, saving time and effort, and managing and modifying them in digital format.

[0737] An "educational curriculum" is a systematic compilation of learning content and goals that should be taught for each age group or grade level within the educational system.

[0738] "Learning data" is a general term for information collected based on the educational process, such as teaching materials, lesson content, and test questions.

[0739] A "database" is a computer system that stores information and data in a structured manner so that it can be easily accessed, managed, and updated.

[0740] An "interface" is a medium for exchanging information between a user and a computer system, and includes screens, menus, buttons, etc.

[0741] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to automatically generate new test questions.

[0742] "PDF file format" is an abbreviation for Portable Document Format, and is a file format used to store and display documents electronically.

[0743] "Cloud storage" is a service for storing, sharing, and managing files online via the Internet.

[0744] "Digital terminal" is a general term for electronic devices that process information, such as smartphones, tablets, and computers.

[0745] "Customization function" refers to a function that allows users to personalize system and service settings according to their requests and meet their specific needs.

[0746] A "download link" is a URL used to download files on the Internet; by clicking on it you can obtain the desired file.

[0747] MODE FOR CARRYING OUT THE INVENTION

[0748] The present invention provides a system for improving the efficiency of test creation work in educational settings and for supporting individualized learning progress. Specific embodiments of this system are described below.

[0749] This system first collects learning data based on the educational curriculum and stores it in a database. The learning data includes teaching materials and past test questions for each subject and age group. This data is collected and stored on a server.

[0750] Next, an interface is provided for the educator to select the test scope. The interface includes a screen where the educator attempts to log in and a main menu that is displayed after successful authentication. The educator enters a username and password, is authenticated with the server, and moves to the main menu. Here, the educator selects the test scope.

[0751] Based on the selected test scope, the generation AI generates test questions. The test scope information is sent to the server, which then provides the generation AI with relevant learning data based on this information. The generation AI generates test questions using a machine learning algorithm (specifically, GPT-4). The generated test questions are saved on the server in PDF file format.

[0752] The generated PDF file is stored in cloud storage, and a download link is provided to the educator. The educator can download the PDF file via this link, review the content on a digital device, and make any necessary corrections. After making corrections, the file can be uploaded back to cloud storage, and the final test file can be stored in the database.

[0753] Furthermore, the system allows educators to request the generation of customized test questions based on each student's learning progress. Educators can provide the AI ​​with prompts to generate personalized test questions according to the student's progress, and adjust the difficulty and format of the test questions.

[0754] Hardware and software used

[0755] Server: AWS or Google Cloud

[0756] Database: MongoDB

[0757] Generative AI model: GPT-4 (OpenAI)

[0758] Client side: React Native (mobile apps), React.js (web apps)

[0759] Other tools: User authentication and session management using JSON Web Tokens (JWT), PDF file generation and management using Node.js, cloud storage with AWS S3

[0760] Specific examples

[0761] For example, let's say a mathematics teacher at a learning center wants to create a test on "simultaneous equations" for second-year junior high school students. The teacher logs into the system, selects "simultaneous equations" from the range of junior high school mathematics, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions based on the following prompt:

[0762] Example prompt sentence:

[0763] Based on the following educational data, please generate a test question on simultaneous equations for second-year junior high school students. The test should have the following structure:

[0764] 1. Basic problems (calculation problems)

[0765] 2. Applied questions (word questions)

[0766] 3. Sample answers and explanations for each question

[0767] The generated PDF file is stored in cloud storage, and teachers can download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in its database for future reference and reuse.

[0768] As described above, the system of the present invention improves the efficiency of test creation work in educational settings and significantly reduces the burden on educators.

[0769] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0770] Step 1:

[0771] Collecting learning data and storing it in a database

[0772] The server collects learning data based on the curriculum and stores it in a database. Specifically, it collects data such as teaching materials and past test questions, and stores them in a structured MongoDB database. This prepares the basic data for use in subsequent test generation processes.

[0773] Step 2:

[0774] User authentication and interface provisioning

[0775] A user attempts to log in to a system using a terminal. They enter a username and password and request authentication from the server. The server checks the authentication information against a database, and if successful, issues session information and provides the user with an interface that displays the main menu. This prepares the user for accessing the system.

[0776] Step 3:

[0777] Test Scope Selection

[0778] The educator uses the device to select the educational curriculum category (e.g., junior high school), subject (e.g., mathematics), and specific unit (e.g., simultaneous equations). The selected information is sent to the server, which uses this information to extract relevant learning data from the database and prepares it as input data for the subsequent generative AI model.

[0779] Step 4:

[0780] Generate test questions

[0781] The server provides training data to a generative AI model (GPT-4) based on the specified test scope and generates test questions. Specifically, it inputs a prompt (e.g., "Based on the educational data below, please generate test questions on simultaneous equations for second-year junior high school students") to the generative AI model and receives the test questions output by the model. The generated questions are converted into PDF file format and temporarily saved on the server.

[0782] Step 5:

[0783] Save test questions and provide download links

[0784] The server saves the generated PDF file in cloud storage (such as AWS S3) and provides a download link to the educator. The user then downloads the PDF file from the provided link using their device and checks and corrects the content of the test questions.

[0785] Step 6:

[0786] Fix the test file and re-upload it

[0787] The educator opens the downloaded PDF file on their device and makes any necessary corrections. Once the corrections are complete, they upload it back to the cloud storage and request the server to save the final test file. The server receives the corrected file and stores it in a database.

[0788] Step 7:

[0789] Request for personalized test question generation

[0790] Educators provide the generative AI model with prompts to generate customized test questions based on each student's learning progress. The server then provides input data to the generative AI based on the prompts to generate personalized test questions.

[0791] Step 8:

[0792] Output and save customized test questions

[0793] The server outputs the personalized test questions as a PDF file and saves it in cloud storage. Educators are provided with a new download link, and users can download the file via their devices, check it, and make corrections. This provides test questions optimized for each student's learning progress.

[0794] 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.

[0795] The present invention is a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. This system combines a series of means for collecting learning data based on educational curriculum, generating test questions, and managing them with an emotion engine that recognizes the user's emotions and provides appropriate tests and feedback. Specific embodiments of the present invention are described below.

[0796] A natural language description of the program's processing

[0797] 1. Building a database of educational content

[0798] server:

[0799] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes textbook content, curriculum guidelines, and past test questions. This data is organized and stored in an easy-to-search format.

[0800] 2. Accepting test generation requests

[0801] Device:

[0802] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[0803] User:

[0804] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[0805] server:

[0806] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[0807] 3. Selecting the test area and checking the emotional state

[0808] Device:

[0809] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[0810] User:

[0811] Users select the curriculum category, subject, and specific test topics from drop-down menus, then press a button to submit a test generation request. The interface also features an emotion engine that analyzes the user's facial expressions and tone of voice to check their emotional state.

[0812] server:

[0813] It receives a test generation request and emotional state from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0814] 4. Test generation and emotion-based adjustment

[0815] server:

[0816] The generation AI is started and input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included are passed in. The AI ​​also adjusts the difficulty and type of test appropriately based on the user's emotional state provided by the emotion engine.

[0817] The generative AI automatically generates test questions based on this data.

[0818] 5. Providing and Modifying Tests

[0819] server:

[0820] The generated test questions are output as Word files and saved to cloud storage. A unique download link for the saved file is generated and notified to the user.

[0821] Device:

[0822] A download link for the test file is displayed to the teacher. The teacher clicks the link to download the Word file and opens it on their device.

[0823] 6. Test correction and emotional feedback

[0824] User:

[0825] Review the downloaded test questions and make any necessary corrections. The questions are saved in Word format, making them easy to edit using standard document editing software. While correcting, the emotion engine analyzes the user's emotions and suggests appropriate feedback and relaxation methods if stress is detected.

[0826] 7. Digital storage of tests

[0827] User:

[0828] The final test file, after corrections are completed, is uploaded to cloud storage again and stored in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0829] server:

[0830] The system receives the uploaded final test file, associates it with the user's account information, and stores it in a database. This allows for the efficient organization and management of each school's test creation history and stored data.

[0831] Specific examples

[0832] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[0833] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0834] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[0835] The processing flow will be explained below.

[0836] Step 1:

[0837] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[0838] Step 2:

[0839] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[0840] Step 3:

[0841] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[0842] Step 4:

[0843] The user selects the curriculum category and subject, as well as the specific unit and scope from drop-down menus, and presses a button to send a test generation request. At this time, the emotion engine analyzes the user's facial expressions and tone of voice to check their emotional state.

[0844] Step 5:

[0845] The server receives the user's test generation request and emotional state information, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[0846] Step 6:

[0847] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included.The server also appropriately adjusts the difficulty and type of test based on the user's emotional state using an emotion engine.

[0848] Step 7:

[0849] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[0850] Step 8:

[0851] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[0852] Step 9:

[0853] The system checks the test questions downloaded by the user and makes corrections as necessary. The questions are saved in Word file format, making them easy to edit using common document editing software. While the user is correcting the questions, the emotion engine analyzes their emotions and suggests appropriate feedback and relaxation methods if stress is felt.

[0854] Step 10:

[0855] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[0856] Step 11:

[0857] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[0858] Examples:

[0859] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[0860] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[0861] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[0862] Example 2

[0863] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0864] Traditional test creation tasks require a great deal of time and effort from educators, often causing mental strain. Furthermore, tests are created without taking into account the educator's emotional state, which can increase stress for the educator. Furthermore, there are problems with the inefficient editing and storage of generated tests, making it difficult to reuse past data.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to log in by entering authentication information, means for providing an interface for educators to select test topics and for receiving the selected test topics and emotional state, means for analyzing the educator's emotions using an emotion analysis engine and adjusting the test content based on the results, means for generating test questions using a generation AI based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in cloud storage, means for educators to download and modify the test file, means for re-uploading the modified test file and storing it in the database, and means for monitoring the educator's emotions during modification and providing feedback if stress is detected. This makes it possible to improve the efficiency of test creation work, optimize the work environment by taking into account the educator's emotional state, and reduce mental burden.

[0866] "Curriculum" refers to the learning content based on the curriculum guidelines and textbooks established by national and local educational institutions.

[0867] "Learning data" refers to information including the contents of textbooks related to the educational curriculum, curriculum guidelines, and past test questions.

[0868] A "database" refers to a digital system for organizing collected learning data and storing it in an easily searchable format.

[0869] "Interface" refers to the means that provides a screen and input methods for educators to interact with the system.

[0870] An "emotion analysis engine" refers to software that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[0871] "Generative AI" refers to artificial intelligence that automatically generates test questions based on specified parameters.

[0872] "Cloud storage" refers to a service that stores and manages data remotely via the Internet.

[0873] "Document file format" refers to a digital format for storing multi-page documents containing text and images.

[0874] "Educator" refers to a person whose job is to provide education to students.

[0875] "Feedback" refers to the advice and warnings the system provides based on the educator's emotional state.

[0876] This system aims to improve the efficiency of test creation work in educational settings and reduce the mental burden on educators. This system combines a means of collecting learning data based on educational curriculum, generating and managing test questions, and an emotion engine that recognizes educators' emotions and provides appropriate tests and feedback.

[0877] Collecting learning data and storing it in a database

[0878] server:

[0879] The server automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the Internet and books.

[0880] This data is organized by curriculum and stored in an SQL database, which is indexed and has an optimized search function to enable quick data access.

[0881] Educator Certification and Testing Options

[0882] Device:

[0883] A form for teachers to log in is displayed, with fields for entering username and password.

[0884] User:

[0885] Enter your username and password and press the login button.

[0886] server:

[0887] Receives form data and verifies it with user information in the database. If authentication is successful, creates a session and transitions to the main menu screen.

[0888] Selecting test areas and checking emotional state

[0889] Device:

[0890] Provides drop-down menus for selecting curriculum category (elementary, middle, high school), subject, and specific unit or area.

[0891] User:

[0892] Select the curriculum, subject, and unit from the menu and submit a test generation request.

[0893] Device:

[0894] The emotion engine analyzes the user's facial expressions and tone of voice in real time.

[0895] server:

[0896] The system receives the user's selected range and emotional state and extracts relevant learning data from the database.

[0897] Test generation and emotion-based adjustment

[0898] server:

[0899] The extracted training data and test parameters (number of questions, difficulty level, presence or absence of diagrams) are passed as input to the generation AI. Based on the analysis results of the emotion engine, the difficulty level of the test is adjusted appropriately.

[0900] Examples:

[0901] When a teacher wants to create a test for the "Functions and Graphs" unit in high school mathematics, the teacher logs in to the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately. The generated Word file is saved in cloud storage, and the teacher can download it from the provided link.

[0902] Providing and Modifying Tests

[0903] server:

[0904] The generated test questions are saved as Word files and uploaded to cloud storage. A download link is generated from the cloud storage and notified to the user.

[0905] Device:

[0906] Provide instructors with a download link for the test file.

[0907] User:

[0908] Click the download link to download the test questions in Word file format.

[0909] Test correction and emotional feedback

[0910] User:

[0911] Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections.

[0912] During the correction, the emotion engine will again analyze the user's emotions and provide feedback if stress is detected.

[0913] Digital storage of tests

[0914] User:

[0915] Upload the modified test file back to cloud storage.

[0916] server:

[0917] Uploaded files are stored in a database and associated with user account information for future reference and reuse.

[0918] Example prompt sentence:

[0919] "Generate test questions for functions and graphs. The questions should be of medium difficulty and include diagrams. Also, adjust the difficulty level slightly lower if the user is feeling stressed."

[0920] In this way, the system of the present invention can improve the efficiency of test creation work while also taking into account the emotional state of the educator, thereby reducing the mental burden on the educator and providing a better teaching environment.

[0921] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0922] Step 1:

[0923] Server: Automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the internet and books. Organizes the extracted data by educational curriculum and stores it in an SQL database.

[0924] Specific operations: Learning data is collected using scraping tools and OCR software and entered into a database, creating a highly searchable database of educational content.

[0925] Input: Textbook PDF file, web page

[0926] Output: Organized training data (SQL database)

[0927] Step 2:

[0928] Terminal: Display a form for teachers to log in, and provide fields for entering a username and password.

[0929] User: Enter your username and password and click the login button.

[0930] Server: Receives the form data and verifies it with the user information in the database. If authentication is successful, creates a session, issues a session ID to the user, and transitions to the main menu screen.

[0931] What it does: It hashes the user information and compares it with the information in the database. If the authentication information matches, it generates a session ID and stores it in a cookie.

[0932] Input: Username, Password

[0933] Output: Session ID

[0934] Step 3:

[0935] Device: Provides drop-down menus for selecting curriculum division (elementary, middle, high school), subject, and specific units or areas.

[0936] User: Selects the curriculum, subject, and unit from the menu and sends a test generation request. The device analyzes the user's facial expressions and tone of voice in real time using an emotion analysis engine.

[0937] Server: Receives the user's selected range and emotional state and extracts relevant learning data from the database.

[0938] What it does: The emotion analysis engine analyzes webcam footage, measures facial muscle movements to infer emotional state, and executes database queries to extract training data relevant to the specified test areas.

[0939] Input: Curriculum classification, subject, unit, emotional state (facial expression analysis)

[0940] Output: Extracted training data, emotional state data

[0941] Step 4:

[0942] Server: The extracted training data and test parameters (number of questions, difficulty level, whether or not diagrams are included) are passed to the generation AI as input. The difficulty level of the test is adjusted appropriately based on the analysis results of the emotion engine.

[0943] Specific behavior: Sends prompts to the generation AI, instructing it to generate questions with a medium level of difficulty for a specific range. Fine-tunes the difficulty setting based on data from the emotion engine.

[0944] Input: training data, test set parameters, emotional state data

[0945] Output: Generated test questions

[0946] Step 5:

[0947] Server: Saves the generated test questions in Word file format and uploads them to cloud storage. Generates a download link from the cloud storage and notifies the user.

[0948] On the device: Provide the teacher with a download link for the test file.

[0949] User: Click on the download link to download the test questions in Word file format.

[0950] Specific behavior: Upload the generated Word file to a cloud storage service (e.g., Amazon S3) and notify the user of the generated link.

[0951] Input: Generated test questions (Word file), cloud storage credentials

[0952] Output: Download link

[0953] Step 6:

[0954] User: Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections. While correcting, the emotion analysis engine analyzes the user's emotions again and displays feedback if stress is detected.

[0955] What it does: While you edit, the emotion analysis engine continuously analyzes your facial expressions and tone of voice, and if stress is detected, a pop-up message will appear.

[0956] Input: Test questions (Word file), real-time emotional state data

[0957] Output: Fixed test questions, feedback messages

[0958] Step 7:

[0959] User: Upload the modified test file back to cloud storage.

[0960] Server: Stores uploaded files in a database and associates them with user account information for future reference and reuse.

[0961] Specific operation: The metadata of uploaded files (creation date and time, subject, unit, etc.) is saved in a database for efficient file management.

[0962] Input: Modified test file (Word file), user account information

[0963] Output: Test files stored in the database

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0966] Creating tests in educational settings takes a lot of time, placing a heavy burden on teachers. The stress and fatigue felt during the work are also a problem. Similarly, inspection work in factories and other places requires time and effort to manually plan and execute inspections, placing a heavy mental burden on workers. There is a need to improve this situation, increase work efficiency, and reduce the mental burden on workers.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for teachers to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in Word file format and saving them in cloud storage, means for recognizing user emotions and adjusting the difficulty and type related to the test topics, means for teachers to download and modify test files, and means for re-uploading the modified test files and storing them in the database. This makes it possible to streamline test creation work and reduce the mental burden on teachers and workers.

[0968] Definitions of important words

[0969] "Curriculum" refers to the learning content and structure of lessons offered at schools and educational institutions, as well as the progress plan for each grade level.

[0970] "Learning data" refers to learning materials, reference materials, past test questions, and information based on curriculum guidelines for students.

[0971] A "database" is a system or mechanism that organizes and stores information so that it can be searched and used as needed.

[0972] "Interface" refers to the screens and input devices used by teachers and users to operate the system, and specifically includes login screens and menu screens.

[0973] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate content such as test questions based on specified conditions.

[0974] "Generating test questions" means creating test questions, including question statements, options, and answers, based on the training data.

[0975] "Cloud storage" refers to an online data storage service accessible via the Internet where you can store and manage data.

[0976] "Recognizing the user's emotions" means determining the user's mental state, such as stress or fatigue, through analysis of the user's facial expressions and tone of voice.

[0977] "Adjusting the difficulty and type of questions related to the test scope" refers to changing the difficulty and type of questions given in consideration of the user's emotional state.

[0978] "Downloading" means importing files or data stored in cloud storage, etc., to your device via the Internet or a network.

[0979] "Uploading" refers to sending and storing data or files from your device via the Internet or a network to an online service such as cloud storage.

[0980] The present invention provides a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. Specific embodiments of the present invention will be described below.

[0981] Hardware and Software Configuration

[0982] 1. Hardware:

[0983] Server: Responsible for database management and running generative AI.

[0984] Device: The device used by the teacher (e.g., PC, tablet, etc.).

[0985] 2. Software:

[0986] Database Management System: A database for storing training data and test files.

[0987] Generative AI: Software that automatically generates test questions using AI models.

[0988] Emotion Recognition Engine: Software that recognizes teachers' emotions and provides feedback.

[0989] Data processing and calculation methods

[0990] The server collects learning data and stores it in a database. Teachers access the interface using their devices and select the test topics. The information on the selected test topics is sent to the server, which then passes it on to the generation AI as input. The generation AI generates test questions and saves the results in cloud storage as a Word file.

[0991] The emotion recognition engine analyzes the teacher's facial expressions and tone of voice through the interface to determine their stress level, and this situational data is sent to the server, which then adjusts the difficulty and type of test questions.

[0992] Specific examples

[0993] For example, consider the case where a worker at a factory is performing a regular inspection and the inspection work plan is automatically generated. The worker wears a smartphone or smart glasses, and an emotion recognition engine monitors the worker's emotional state. When the worker feels stressed, the server automatically adjusts the content and order of the inspection tasks to optimize work efficiency.

[0994] Prompt Sentence Examples

[0995] Here is a specific example of an input prompt sentence for the generative AI model.

[0996] Emotion recognition: "High stress"

[0997] Generate a list of inspection tasks and eliminate low priority tasks.

[0998] This method makes it possible to achieve both overall efficiency and the mental health of workers not only in test creation work but also in a variety of on-site tasks in factories and other places.

[0999] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1000] Program processing steps

[1001] Step 1:

[1002] The server collects learning data based on the curriculum and stores it in a database. The input data includes textbook content, curriculum guidelines, and past test questions, and the output is to organize and store this data in a database in an easy-to-search format.

[1003] Step 2:

[1004] The user (teacher) accesses the login interface using a terminal and attempts authentication by entering their username and password. The server compares the authentication information with the database, and if authentication is successful, issues a session and transitions to the main menu. The input is the user's authentication information, and the output is session information if successful.

[1005] Step 3:

[1006] The user is directed to an interface for selecting the curriculum category, subject, and test area. The input is the user's selection information, and the output is the selected test area information.

[1007] Step 4:

[1008] The device interface uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to check their emotional state. The input is the user's facial expressions and voice data, and the output is the analyzed emotional state.

[1009] Step 5:

[1010] The server receives a test generation request and emotional state from the user, and extracts training data related to the specified test range from the database. The input is the test generation request and emotional state, and the output is the extracted training data.

[1011] Step 6:

[1012] The server starts the generation AI and passes parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included as input to the generation AI.The server also appropriately adjusts the difficulty and type of test based on the emotional state provided by the emotion engine.The input is the generation parameters and the emotional state, and the output is the generated test questions.

[1013] Step 7:

[1014] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link. The input is the generated test questions, and the output is the save and download link to cloud storage.

[1015] Step 8:

[1016] A user clicks on the download link of the test file on the device and downloads the Word file. The input is the download link, and the output is the test file saved on the device.

[1017] Step 9:

[1018] The system checks the test questions downloaded by the user and makes corrections as necessary. During corrections, the emotion engine checks the user's emotional state again and provides appropriate feedback if stress is detected. The input is the corrected test file, and the output is the final test file.

[1019] Step 10:

[1020] The user uploads the final test file to the cloud storage again, and the server receives this file, associates it with the user account information, and stores it in the database. The input is the final test file, and the output is the file stored in the database.

[1021] 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.

[1022] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1023] 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.

[1024] [Third embodiment]

[1025] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1026] 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.

[1027] 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).

[1028] 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.

[1029] 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.

[1030] 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).

[1031] 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. 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1037] The present invention is a system for improving the efficiency of test creation work in educational settings, and provides a series of means for collecting learning data based on an educational curriculum, generating test questions, and managing them. Specific embodiments of the present invention are described below.

[1038] A natural language description of the program's processing

[1039] 1. Building a database of educational content

[1040] server:

[1041] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes the contents of textbooks for each subject and grade, curriculum guidelines, past test questions, etc. This data is organized and managed so that users can easily access it.

[1042] 2. Accepting test generation requests

[1043] Device:

[1044] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[1045] User:

[1046] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[1047] server:

[1048] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[1049] 3. Selecting the test scope

[1050] Device:

[1051] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[1052] User:

[1053] Select the curriculum category, subject, and specific test scope, and submit a test generation request.

[1054] server:

[1055] It receives a test generation request from the user, extracts learning data related to the specified test scope, and provides it as input data to the generation AI.

[1056] 4. Test Generation

[1057] server:

[1058] Based on the specified test scope, the AI ​​generates test questions. The generated questions are output in Word file format. The algorithm is adjusted to create a balanced set of questions.

[1059] 5. Providing and Modifying Tests

[1060] server:

[1061] The generated Word file is saved in cloud storage, and users are provided with a download link through which they can download the test questions.

[1062] Device:

[1063] When teachers download the generated test via the provided link, it is saved to their device as a Word file, where they can review the content and make corrections if necessary.

[1064] User:

[1065] After correcting the test, we ask that you upload it to cloud storage again and store the final version of the data in the database.

[1066] 6. Digital storage of tests

[1067] User:

[1068] The final modified test file is uploaded to cloud storage and stored in the database.

[1069] server:

[1070] Receives uploaded final test files and stores them in a database for future reference and reuse.

[1071] Specific examples

[1072] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in Word file format.

[1073] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1074] In this way, the system of the present invention makes test creation more efficient and significantly reduces the burden on teachers.

[1075] The processing flow will be explained below.

[1076] Step 1:

[1077] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[1078] Step 2:

[1079] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[1080] Step 3:

[1081] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[1082] Step 4:

[1083] The user selects the curriculum category and subject, as well as the specific unit and scope from the drop-down menus, and then presses a button to submit a test generation request.

[1084] Step 5:

[1085] The server receives a test generation request from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1086] Step 6:

[1087] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, whether or not to include diagrams, etc. The generation AI automatically generates test questions based on this data.

[1088] Step 7:

[1089] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[1090] Step 8:

[1091] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[1092] Step 9:

[1093] Users can review the downloaded test questions and make corrections as necessary. The questions are saved in Word format, so they can be easily edited using standard document editing software.

[1094] Step 10:

[1095] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1096] Step 11:

[1097] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[1098] Example 1

[1099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] Traditionally, test creation was a highly manual process that required a great deal of time and effort from teachers. Furthermore, inadequate database management made it difficult to reuse or efficiently search for past test questions. Furthermore, there was a lack of support for maintaining the balance and quality of the generated test questions. These tasks placed a significant burden on educational settings.

[1101] 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.

[1102] In this invention, the server includes means for collecting learning data and storing it in a database, means for providing an interface for teachers to select test topics, means for a generative AI model to generate test questions based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in remote storage, means for teachers to download and modify test files, means for re-uploading the modified test files and storing them in the database, means for periodically updating the collected data and generated test questions, and means for issuing session IDs to users. This enables more efficient test creation work and efficient data management.

[1103] "Learning data" refers to information collected based on the educational curriculum, such as the contents of textbooks for each subject and each grade, curriculum guidelines, and past test questions.

[1104] A "database" is an information management system that efficiently manages information organized according to specific rules and allows for quick search and updating as needed.

[1105] An "interface" is a window through which a user can interact with a system, such as a screen or input field.

[1106] A "generative AI model" is a program that uses artificial intelligence technology to automatically create test questions based on specified conditions.

[1107] A "document file" is a digital document stored in a format that contains text and images, such as a Word file.

[1108] "Remote storage" is an external data storage service that can be accessed via the Internet.

[1109] A "session ID" is an identifier issued to uniquely identify a user while the user is logged in.

[1110] "Users" are educational personnel who use this system to create and manage test questions.

[1111] The present invention is a system for streamlining test creation work in educational settings, and provides a series of means for collecting learning data based on educational courses, generating test questions, and managing them.

[1112] System hardware and software configuration

[1113] server:

[1114] Hardware: A server with a powerful processor, ample memory, and ample storage.

[1115] Software: Database management systems (e.g., SQL), generative AI models (e.g., GPT-3), cloud storage services (e.g., AWS S3).

[1116] Device:

[1117] Hardware: PCs, tablets, smartphones, etc.

[1118] Software: User interface using a web browser (Google Chrome, Mozilla Firefox, etc.).

[1119] User:

[1120] Teachers and other educational professionals.

[1121] Operation flow

[1122] 1. Building a database of educational content:

[1123] The server collects information such as textbook contents for each subject and grade, curriculum guidelines, and past test questions based on the educational curriculum, and stores it in a database. The data is updated regularly to ensure that the latest information is always maintained.

[1124] 2. Accepting test generation requests:

[1125] The terminal provides an interface for teachers to log in, and teachers enter their username and password to authenticate with the server. The server verifies the authentication information and, if successful, issues a session ID. The teacher then moves to the main menu screen and selects the test scope.

[1126] 3. Select the test scope:

[1127] The device provides a menu for selecting the educational curriculum (elementary school, middle school, high school) and subject. Teachers select specific units and areas and submit a test generation request. The server extracts learning data related to the specified test area from the database and provides it to the generative AI model.

[1128] 4. Generate tests:

[1129] The server sends a prompt to the generative AI model to generate test questions. The generative AI model creates balanced test questions based on the specified range and outputs them in a document file format. The generated file is stored in cloud storage.

[1130] 5. Test provision and correction:

[1131] The server provides teachers with a download link for the test file stored in cloud storage. Teachers download the file from the link and check and edit the contents. Once edited, the file is uploaded back to cloud storage and saved in the server's database.

[1132] Specific examples

[1133] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in document file format.

[1134] The generated document file is stored in cloud storage, and teachers download it from the provided link. After checking the content of the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse. In this way, the system of the present invention streamlines test creation work and significantly reduces the burden on teachers.

[1135] Prompt Sentence Examples

[1136] Here are some example prompts to input to a generative AI model:

[1137] "Generate balanced test questions based on the user-specified high school mathematics unit 'Functions and Graphs.' Specifically, include questions on the basic properties of functions, questions requiring graphing, and questions requiring solutions given a range of variables."

[1138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1139] Step 1:

[1140] Building a database of educational content

[1141] server:

[1142] The server collects learning data such as the contents of textbooks for each subject and each grade based on the educational curriculum, curriculum guidelines, and past test questions.

[1143] Input: Textbooks, curriculum guidelines, and past test question data for each subject and grade level.

[1144] After collecting the data, the server organizes the data by category (e.g., subject, grade, unit) and stores it in a database.

[1145] Output: The organized training data is stored in a database.

[1146] Specific behavior:

[1147] 1. The server periodically downloads the latest teaching material data from databases of educational institutions and publishers.

[1148] 2. Analyze the collected data and classify it by subject, grade, and unit.

[1149] 3. Store the classified data in a database and create an index for easy access by users.

[1150] Step 2:

[1151] Accepting test generation requests

[1152] Device:

[1153] The terminal displays a user interface that allows the teacher to enter a username and password.

[1154] Input: Username and password of the user.

[1155] Output: Sends an authentication request to the server.

[1156] User:

[1157] The user enters a username and password in the user interface and presses the "Login" button.

[1158] Enter your username and password.

[1159] server:

[1160] The server checks the received authentication information against the user information in its database.

[1161] If authentication is successful, the server issues a session ID to the user and loads the main menu screen.

[1162] Enter your username and password.

[1163] Output: Authentication result (success / failure) and session ID.

[1164] Specific behavior:

[1165] 1. The teacher accesses the login screen on the device.

[1166] 2. The user enters their username and password and clicks the login button.

[1167] 3. The server checks the username and password against its database and, if they match, issues a session ID.

[1168] 4. The user moves to the main menu screen.

[1169] Step 3:

[1170] Test Scope Selection

[1171] Device:

[1172] The device displays the main menu screen with a menu for selecting the educational curriculum (elementary school, junior high school, high school) and subject.

[1173] Input: Select the curriculum category, subject, and unit.

[1174] Output: A request to send the selected test ranges to the server.

[1175] User:

[1176] The user selects the curriculum category and subject from the drop-down menus, and then selects the appropriate unit or area.

[1177] Once the selection is complete, the user presses the "Request Generation" button.

[1178] Input: Select the curriculum category, subject, and unit.

[1179] server:

[1180] The server receives a test generation request from a user and extracts the specified range information from the database.

[1181] Input: Select the curriculum category, subject, and unit.

[1182] Output: Provide the extracted training data to a generative AI model.

[1183] Specific behavior:

[1184] 1. The teacher accesses the main menu screen on the device.

[1185] 2. Select the curriculum category, subject, and unit from the drop-down menus.

[1186] 3. Press the "Request Generation" button to send a request to the server.

[1187] 4. The server extracts the specified range of training data from the database and provides it to the generative AI model.

[1188] Step 4:

[1189] Test Generation

[1190] server:

[1191] The server sends a prompt to the generative AI model and begins generating test questions.

[1192] Input: Extracted training data, prompt sentence.

[1193] Output: A document file of the generated test questions.

[1194] Specific behavior:

[1195] 1. The server sends a prompt to the generative AI model, such as "Generate balanced test questions based on the 'Functions and Graphs' unit of high school mathematics specified by the user."

[1196] 2. The generative AI model generates test questions based on the input prompt and training data.

[1197] 3. The generated test questions are saved on the server as a document file (e.g., a Word file).

[1198] Step 5:

[1199] Providing and Modifying Tests

[1200] server:

[1201] The server uploads the generated test file to cloud storage and provides a download link to the user.

[1202] Input: The generated test question document file.

[1203] Output: Download link.

[1204] Device:

[1205] The device will download the generated test via the provided link and save it as a document file on the device.

[1206] Input: Download link.

[1207] Output: The downloaded document file.

[1208] User:

[1209] The user opens the document file on the terminal, checks the contents, and corrects the test questions as necessary.

[1210] Re-upload the corrected file to cloud storage.

[1211] Input: The downloaded document file.

[1212] Output: The modified document file.

[1213] Specific behavior:

[1214] 1. The server uploads the generated test file to cloud storage.

[1215] 2. Teachers will download the test file via the provided link and review and correct the content.

[1216] 3. Upload the modified test file back to the cloud storage.

[1217] Step 6:

[1218] Digital storage of tests

[1219] User:

[1220] The user uploads the final modified test file to cloud storage.

[1221] Input: The modified document file.

[1222] Output: The upload request.

[1223] server:

[1224] The server receives the uploaded modified test file and stores it in a database.

[1225] Input: The modified document file.

[1226] Output: The final file stored in the database.

[1227] Specific behavior:

[1228] 1. The teacher uploads the final, revised test file to cloud storage.

[1229] 2. The server receives the uploaded file and stores it in the appropriate folder in the database.

[1230] 3. Add tags (e.g., "High School Math," "Functions and Graphs," "Created September 2023") to saved files to organize them for future search and reuse.

[1231] (Application example 1)

[1232] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1233] Currently, teachers have to manually create test questions, which requires a great deal of time and effort. At the same time, it is difficult to individually adjust test questions based on each student's learning progress. This makes it difficult to consistently improve the quality of education, and these problems are particularly prevalent in learning centers and cram schools. Furthermore, there are insufficient means for digitally managing and correcting the generated test questions, which increases the workload of educators.

[1234] 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.

[1235] In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in PDF file format and saving them in cloud storage, means for educators to download the test files and modify them on their digital devices, means for re-uploading the modified test files and storing them in the database, means for educators to request the generation of customized test questions based on each student's learning progress, a customization function for adjusting the difficulty and format of the generated test questions, and means for providing a download link for the generated test questions. This allows teachers to easily generate personalized test questions based on each student's learning progress, saving time and effort, and managing and modifying them in digital format.

[1236] An "educational curriculum" is a systematic compilation of learning content and goals that should be taught for each age group or grade level within the educational system.

[1237] "Learning data" is a general term for information collected based on the educational process, such as teaching materials, lesson content, and test questions.

[1238] A "database" is a computer system that stores information and data in a structured manner so that it can be easily accessed, managed, and updated.

[1239] An "interface" is a medium for exchanging information between a user and a computer system, and includes screens, menus, buttons, etc.

[1240] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to automatically generate new test questions.

[1241] "PDF file format" is an abbreviation for Portable Document Format, and is a file format used to store and display documents electronically.

[1242] "Cloud storage" is a service for storing, sharing, and managing files online via the Internet.

[1243] "Digital terminal" is a general term for electronic devices that process information, such as smartphones, tablets, and computers.

[1244] "Customization function" refers to a function that allows users to personalize system and service settings according to their requests and meet their specific needs.

[1245] A "download link" is a URL used to download files on the Internet; by clicking on it you can obtain the desired file.

[1246] MODE FOR CARRYING OUT THE INVENTION

[1247] The present invention provides a system for improving the efficiency of test creation work in educational settings and for supporting individualized learning progress. Specific embodiments of this system are described below.

[1248] This system first collects learning data based on the educational curriculum and stores it in a database. The learning data includes teaching materials and past test questions for each subject and age group. This data is collected and stored on a server.

[1249] Next, an interface is provided for the educator to select the test scope. The interface includes a screen where the educator attempts to log in and a main menu that is displayed after successful authentication. The educator enters a username and password, is authenticated with the server, and moves to the main menu. Here, the educator selects the test scope.

[1250] Based on the selected test scope, the generation AI generates test questions. The test scope information is sent to the server, which then provides the generation AI with relevant learning data based on this information. The generation AI generates test questions using a machine learning algorithm (specifically, GPT-4). The generated test questions are saved on the server in PDF file format.

[1251] The generated PDF file is stored in cloud storage, and a download link is provided to the educator. The educator can download the PDF file via this link, review the content on a digital device, and make any necessary corrections. After making corrections, the file can be uploaded back to cloud storage, and the final test file can be stored in the database.

[1252] Furthermore, the system allows educators to request the generation of customized test questions based on each student's learning progress. Educators can provide the AI ​​with prompts to generate personalized test questions according to the student's progress, and adjust the difficulty and format of the test questions.

[1253] Hardware and software used

[1254] Server: AWS or Google Cloud

[1255] Database: MongoDB

[1256] Generative AI model: GPT-4 (OpenAI)

[1257] Client side: React Native (mobile apps), React.js (web apps)

[1258] Other tools: User authentication and session management using JSON Web Tokens (JWT), PDF file generation and management using Node.js, cloud storage with AWS S3

[1259] Specific examples

[1260] For example, let's say a mathematics teacher at a learning center wants to create a test on "simultaneous equations" for second-year junior high school students. The teacher logs into the system, selects "simultaneous equations" from the range of junior high school mathematics, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions based on the following prompt:

[1261] Example prompt sentence:

[1262] Based on the following educational data, please generate a test question on simultaneous equations for second-year junior high school students. The test should have the following structure:

[1263] 1. Basic problems (calculation problems)

[1264] 2. Applied questions (word questions)

[1265] 3. Sample answers and explanations for each question

[1266] The generated PDF file is stored in cloud storage, and teachers can download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in its database for future reference and reuse.

[1267] As described above, the system of the present invention improves the efficiency of test creation work in educational settings and significantly reduces the burden on educators.

[1268] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1269] Step 1:

[1270] Collecting learning data and storing it in a database

[1271] The server collects learning data based on the curriculum and stores it in a database. Specifically, it collects data such as teaching materials and past test questions, and stores them in a structured MongoDB database. This prepares the basic data for use in subsequent test generation processes.

[1272] Step 2:

[1273] User authentication and interface provisioning

[1274] A user attempts to log in to a system using a terminal. They enter a username and password and request authentication from the server. The server checks the authentication information against a database, and if successful, issues session information and provides the user with an interface that displays the main menu. This prepares the user for accessing the system.

[1275] Step 3:

[1276] Test Scope Selection

[1277] The educator uses the device to select the educational curriculum category (e.g., junior high school), subject (e.g., mathematics), and specific unit (e.g., simultaneous equations). The selected information is sent to the server, which uses this information to extract relevant learning data from the database and prepares it as input data for the subsequent generative AI model.

[1278] Step 4:

[1279] Generate test questions

[1280] The server provides training data to a generative AI model (GPT-4) based on the specified test scope and generates test questions. Specifically, it inputs a prompt (e.g., "Based on the educational data below, please generate test questions on simultaneous equations for second-year junior high school students") to the generative AI model and receives the test questions output by the model. The generated questions are converted into PDF file format and temporarily saved on the server.

[1281] Step 5:

[1282] Save test questions and provide download links

[1283] The server saves the generated PDF file in cloud storage (such as AWS S3) and provides a download link to the educator. The user then downloads the PDF file from the provided link using their device and checks and corrects the content of the test questions.

[1284] Step 6:

[1285] Fix the test file and re-upload it

[1286] The educator opens the downloaded PDF file on their device and makes any necessary corrections. Once the corrections are complete, they upload it back to the cloud storage and request the server to save the final test file. The server receives the corrected file and stores it in a database.

[1287] Step 7:

[1288] Request for personalized test question generation

[1289] Educators provide the generative AI model with prompts to generate customized test questions based on each student's learning progress. The server then provides input data to the generative AI based on the prompts to generate personalized test questions.

[1290] Step 8:

[1291] Output and save customized test questions

[1292] The server outputs the personalized test questions as a PDF file and saves it in cloud storage. Educators are provided with a new download link, and users can download the file via their devices, check it, and make corrections. This provides test questions optimized for each student's learning progress.

[1293] 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.

[1294] The present invention is a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. This system combines a series of means for collecting learning data based on educational curriculum, generating test questions, and managing them with an emotion engine that recognizes the user's emotions and provides appropriate tests and feedback. Specific embodiments of the present invention are described below.

[1295] A natural language description of the program's processing

[1296] 1. Building a database of educational content

[1297] server:

[1298] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes textbook content, curriculum guidelines, and past test questions. This data is organized and stored in an easy-to-search format.

[1299] 2. Accepting test generation requests

[1300] Device:

[1301] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[1302] User:

[1303] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[1304] server:

[1305] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[1306] 3. Selecting the test area and checking the emotional state

[1307] Device:

[1308] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[1309] User:

[1310] Users select the curriculum category, subject, and specific test topics from drop-down menus, then press a button to submit a test generation request. The interface also features an emotion engine that analyzes the user's facial expressions and tone of voice to check their emotional state.

[1311] server:

[1312] It receives a test generation request and emotional state from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1313] 4. Test generation and emotion-based adjustment

[1314] server:

[1315] The generation AI is started and input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included are passed in. The AI ​​also adjusts the difficulty and type of test appropriately based on the user's emotional state provided by the emotion engine.

[1316] The generative AI automatically generates test questions based on this data.

[1317] 5. Providing and Modifying Tests

[1318] server:

[1319] The generated test questions are output as Word files and saved to cloud storage. A unique download link for the saved file is generated and notified to the user.

[1320] Device:

[1321] A download link for the test file is displayed to the teacher. The teacher clicks the link to download the Word file and opens it on their device.

[1322] 6. Test correction and emotional feedback

[1323] User:

[1324] Review the downloaded test questions and make any necessary corrections. The questions are saved in Word format, making them easy to edit using standard document editing software. While correcting, the emotion engine analyzes the user's emotions and suggests appropriate feedback and relaxation methods if stress is detected.

[1325] 7. Digital storage of tests

[1326] User:

[1327] The final test file, after corrections are completed, is uploaded to cloud storage again and stored in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1328] server:

[1329] The system receives the uploaded final test file, associates it with the user's account information, and stores it in a database. This allows for the efficient organization and management of each school's test creation history and stored data.

[1330] Specific examples

[1331] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[1332] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1333] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[1334] The processing flow will be explained below.

[1335] Step 1:

[1336] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[1337] Step 2:

[1338] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[1339] Step 3:

[1340] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[1341] Step 4:

[1342] The user selects the curriculum category and subject, as well as the specific unit and scope from drop-down menus, and presses a button to send a test generation request. At this time, the emotion engine analyzes the user's facial expressions and tone of voice to check their emotional state.

[1343] Step 5:

[1344] The server receives the user's test generation request and emotional state information, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1345] Step 6:

[1346] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included.The server also appropriately adjusts the difficulty and type of test based on the user's emotional state using an emotion engine.

[1347] Step 7:

[1348] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[1349] Step 8:

[1350] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[1351] Step 9:

[1352] The system checks the test questions downloaded by the user and makes corrections as necessary. The questions are saved in Word file format, making them easy to edit using common document editing software. While the user is correcting the questions, the emotion engine analyzes their emotions and suggests appropriate feedback and relaxation methods if stress is felt.

[1353] Step 10:

[1354] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1355] Step 11:

[1356] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[1357] Examples:

[1358] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[1359] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1360] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[1361] Example 2

[1362] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1363] Traditional test creation tasks require a great deal of time and effort from educators, often causing mental strain. Furthermore, tests are created without taking into account the educator's emotional state, which can increase stress for the educator. Furthermore, there are problems with the inefficient editing and storage of generated tests, making it difficult to reuse past data.

[1364] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to log in by entering authentication information, means for providing an interface for educators to select test topics and for receiving the selected test topics and emotional state, means for analyzing the educator's emotions using an emotion analysis engine and adjusting the test content based on the results, means for generating test questions using a generation AI based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in cloud storage, means for educators to download and modify the test file, means for re-uploading the modified test file and storing it in the database, and means for monitoring the educator's emotions during modification and providing feedback if stress is detected. This makes it possible to improve the efficiency of test creation work, optimize the work environment by taking into account the educator's emotional state, and reduce mental burden.

[1365] "Curriculum" refers to the learning content based on the curriculum guidelines and textbooks established by national and local educational institutions.

[1366] "Learning data" refers to information including the contents of textbooks related to the educational curriculum, curriculum guidelines, and past test questions.

[1367] A "database" refers to a digital system for organizing collected learning data and storing it in an easily searchable format.

[1368] "Interface" refers to the means that provides a screen and input methods for educators to interact with the system.

[1369] An "emotion analysis engine" refers to software that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[1370] "Generative AI" refers to artificial intelligence that automatically generates test questions based on specified parameters.

[1371] "Cloud storage" refers to a service that stores and manages data remotely via the Internet.

[1372] "Document file format" refers to a digital format for storing multi-page documents containing text and images.

[1373] "Educator" refers to a person whose job is to provide education to students.

[1374] "Feedback" refers to the advice and warnings the system provides based on the educator's emotional state.

[1375] This system aims to improve the efficiency of test creation work in educational settings and reduce the mental burden on educators. This system combines a means of collecting learning data based on educational curriculum, generating and managing test questions, and an emotion engine that recognizes educators' emotions and provides appropriate tests and feedback.

[1376] Collecting learning data and storing it in a database

[1377] server:

[1378] The server automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the Internet and books.

[1379] This data is organized by curriculum and stored in an SQL database, which is indexed and has an optimized search function to enable quick data access.

[1380] Educator Certification and Testing Options

[1381] Device:

[1382] A form for teachers to log in is displayed, with fields for entering username and password.

[1383] User:

[1384] Enter your username and password and press the login button.

[1385] server:

[1386] Receives form data and verifies it with user information in the database. If authentication is successful, creates a session and transitions to the main menu screen.

[1387] Selecting test areas and checking emotional state

[1388] Device:

[1389] Provides drop-down menus for selecting curriculum category (elementary, middle, high school), subject, and specific unit or area.

[1390] User:

[1391] Select the curriculum, subject, and unit from the menu and submit a test generation request.

[1392] Device:

[1393] The emotion engine analyzes the user's facial expressions and tone of voice in real time.

[1394] server:

[1395] The system receives the user's selected range and emotional state and extracts relevant learning data from the database.

[1396] Test generation and emotion-based adjustment

[1397] server:

[1398] The extracted training data and test parameters (number of questions, difficulty level, presence or absence of diagrams) are passed as input to the generation AI. Based on the analysis results of the emotion engine, the difficulty level of the test is adjusted appropriately.

[1399] Examples:

[1400] When a teacher wants to create a test for the "Functions and Graphs" unit in high school mathematics, the teacher logs in to the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately. The generated Word file is saved in cloud storage, and the teacher can download it from the provided link.

[1401] Providing and Modifying Tests

[1402] server:

[1403] The generated test questions are saved as Word files and uploaded to cloud storage. A download link is generated from the cloud storage and notified to the user.

[1404] Device:

[1405] Provide instructors with a download link for the test file.

[1406] User:

[1407] Click the download link to download the test questions in Word file format.

[1408] Test correction and emotional feedback

[1409] User:

[1410] Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections.

[1411] During the correction, the emotion engine will again analyze the user's emotions and provide feedback if stress is detected.

[1412] Digital storage of tests

[1413] User:

[1414] Upload the modified test file back to cloud storage.

[1415] server:

[1416] Uploaded files are stored in a database and associated with user account information for future reference and reuse.

[1417] Example prompt sentence:

[1418] "Generate test questions for functions and graphs. The questions should be of medium difficulty and include diagrams. Also, adjust the difficulty level slightly lower if the user is feeling stressed."

[1419] In this way, the system of the present invention can improve the efficiency of test creation work while also taking into account the emotional state of the educator, thereby reducing the mental burden on the educator and providing a better teaching environment.

[1420] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1421] Step 1:

[1422] Server: Automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the internet and books. Organizes the extracted data by educational curriculum and stores it in an SQL database.

[1423] Specific operations: Learning data is collected using scraping tools and OCR software and entered into a database, creating a highly searchable database of educational content.

[1424] Input: Textbook PDF file, web page

[1425] Output: Organized training data (SQL database)

[1426] Step 2:

[1427] Terminal: Display a form for teachers to log in, and provide fields for entering a username and password.

[1428] User: Enter your username and password and click the login button.

[1429] Server: Receives the form data and verifies it with the user information in the database. If authentication is successful, creates a session, issues a session ID to the user, and transitions to the main menu screen.

[1430] What it does: It hashes the user information and compares it with the information in the database. If the authentication information matches, it generates a session ID and stores it in a cookie.

[1431] Input: Username, Password

[1432] Output: Session ID

[1433] Step 3:

[1434] Device: Provides drop-down menus for selecting curriculum division (elementary, middle, high school), subject, and specific units or areas.

[1435] User: Selects the curriculum, subject, and unit from the menu and sends a test generation request. The device analyzes the user's facial expressions and tone of voice in real time using an emotion analysis engine.

[1436] Server: Receives the user's selected range and emotional state and extracts relevant learning data from the database.

[1437] What it does: The emotion analysis engine analyzes webcam footage, measures facial muscle movements to infer emotional state, and executes database queries to extract training data relevant to the specified test areas.

[1438] Input: Curriculum classification, subject, unit, emotional state (facial expression analysis)

[1439] Output: Extracted training data, emotional state data

[1440] Step 4:

[1441] Server: The extracted training data and test parameters (number of questions, difficulty level, whether or not diagrams are included) are passed to the generation AI as input. The difficulty level of the test is adjusted appropriately based on the analysis results of the emotion engine.

[1442] Specific behavior: Sends prompts to the generation AI, instructing it to generate questions with a medium level of difficulty for a specific range. Fine-tunes the difficulty setting based on data from the emotion engine.

[1443] Input: training data, test set parameters, emotional state data

[1444] Output: Generated test questions

[1445] Step 5:

[1446] Server: Saves the generated test questions in Word file format and uploads them to cloud storage. Generates a download link from the cloud storage and notifies the user.

[1447] On the device: Provide the teacher with a download link for the test file.

[1448] User: Click on the download link to download the test questions in Word file format.

[1449] Specific behavior: Upload the generated Word file to a cloud storage service (e.g., Amazon S3) and notify the user of the generated link.

[1450] Input: Generated test questions (Word file), cloud storage credentials

[1451] Output: Download link

[1452] Step 6:

[1453] User: Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections. While correcting, the emotion analysis engine analyzes the user's emotions again and displays feedback if stress is detected.

[1454] What it does: While you edit, the emotion analysis engine continuously analyzes your facial expressions and tone of voice, and if stress is detected, a pop-up message will appear.

[1455] Input: Test questions (Word file), real-time emotional state data

[1456] Output: Fixed test questions, feedback messages

[1457] Step 7:

[1458] User: Upload the modified test file back to cloud storage.

[1459] Server: Stores uploaded files in a database and associates them with user account information for future reference and reuse.

[1460] Specific operation: The metadata of uploaded files (creation date and time, subject, unit, etc.) is saved in a database for efficient file management.

[1461] Input: Modified test file (Word file), user account information

[1462] Output: Test files stored in the database

[1463] (Application example 2)

[1464] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1465] Creating tests in educational settings takes a lot of time, placing a heavy burden on teachers. The stress and fatigue felt during the work are also a problem. Similarly, inspection work in factories and other places requires time and effort to manually plan and execute inspections, placing a heavy mental burden on workers. There is a need to improve this situation, increase work efficiency, and reduce the mental burden on workers.

[1466] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for teachers to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in Word file format and saving them in cloud storage, means for recognizing user emotions and adjusting the difficulty and type related to the test topics, means for teachers to download and modify test files, and means for re-uploading the modified test files and storing them in the database. This makes it possible to streamline test creation work and reduce the mental burden on teachers and workers.

[1467] Definitions of important words

[1468] "Curriculum" refers to the learning content and structure of lessons offered at schools and educational institutions, as well as the progress plan for each grade level.

[1469] "Learning data" refers to learning materials, reference materials, past test questions, and information based on curriculum guidelines for students.

[1470] A "database" is a system or mechanism that organizes and stores information so that it can be searched and used as needed.

[1471] "Interface" refers to the screens and input devices used by teachers and users to operate the system, and specifically includes login screens and menu screens.

[1472] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate content such as test questions based on specified conditions.

[1473] "Generating test questions" means creating test questions, including question statements, options, and answers, based on the training data.

[1474] "Cloud storage" refers to an online data storage service accessible via the Internet where you can store and manage data.

[1475] "Recognizing the user's emotions" means determining the user's mental state, such as stress or fatigue, through analysis of the user's facial expressions and tone of voice.

[1476] "Adjusting the difficulty and type of questions related to the test scope" refers to changing the difficulty and type of questions given in consideration of the user's emotional state.

[1477] "Downloading" means importing files or data stored in cloud storage, etc., to your device via the Internet or a network.

[1478] "Uploading" refers to sending and storing data or files from your device via the Internet or a network to an online service such as cloud storage.

[1479] The present invention provides a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. Specific embodiments of the present invention will be described below.

[1480] Hardware and Software Configuration

[1481] 1. Hardware:

[1482] Server: Responsible for database management and running generative AI.

[1483] Device: The device used by the teacher (e.g., PC, tablet, etc.).

[1484] 2. Software:

[1485] Database Management System: A database for storing training data and test files.

[1486] Generative AI: Software that automatically generates test questions using AI models.

[1487] Emotion Recognition Engine: Software that recognizes teachers' emotions and provides feedback.

[1488] Data processing and calculation methods

[1489] The server collects learning data and stores it in a database. Teachers access the interface using their devices and select the test topics. The information on the selected test topics is sent to the server, which then passes it on to the generation AI as input. The generation AI generates test questions and saves the results in cloud storage as a Word file.

[1490] The emotion recognition engine analyzes the teacher's facial expressions and tone of voice through the interface to determine their stress level, and this situational data is sent to the server, which then adjusts the difficulty and type of test questions.

[1491] Specific examples

[1492] For example, consider the case where a worker at a factory is performing a regular inspection and the inspection work plan is automatically generated. The worker wears a smartphone or smart glasses, and an emotion recognition engine monitors the worker's emotional state. When the worker feels stressed, the server automatically adjusts the content and order of the inspection tasks to optimize work efficiency.

[1493] Prompt Sentence Examples

[1494] Here is a specific example of an input prompt sentence for the generative AI model.

[1495] Emotion recognition: "High stress"

[1496] Generate a list of inspection tasks and eliminate low priority tasks.

[1497] This method makes it possible to achieve both overall efficiency and the mental health of workers not only in test creation work but also in a variety of on-site tasks in factories and other places.

[1498] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1499] Program processing steps

[1500] Step 1:

[1501] The server collects learning data based on the curriculum and stores it in a database. The input data includes textbook content, curriculum guidelines, and past test questions, and the output is to organize and store this data in a database in an easy-to-search format.

[1502] Step 2:

[1503] The user (teacher) accesses the login interface using a terminal and attempts authentication by entering their username and password. The server compares the authentication information with the database, and if authentication is successful, issues a session and transitions to the main menu. The input is the user's authentication information, and the output is session information if successful.

[1504] Step 3:

[1505] The user is directed to an interface for selecting the curriculum category, subject, and test area. The input is the user's selection information, and the output is the selected test area information.

[1506] Step 4:

[1507] The device interface uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to check their emotional state. The input is the user's facial expressions and voice data, and the output is the analyzed emotional state.

[1508] Step 5:

[1509] The server receives a test generation request and emotional state from the user, and extracts training data related to the specified test range from the database. The input is the test generation request and emotional state, and the output is the extracted training data.

[1510] Step 6:

[1511] The server starts the generation AI and passes parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included as input to the generation AI.The server also appropriately adjusts the difficulty and type of test based on the emotional state provided by the emotion engine.The input is the generation parameters and the emotional state, and the output is the generated test questions.

[1512] Step 7:

[1513] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link. The input is the generated test questions, and the output is the save and download link to cloud storage.

[1514] Step 8:

[1515] A user clicks on the download link of the test file on the device and downloads the Word file. The input is the download link, and the output is the test file saved on the device.

[1516] Step 9:

[1517] The system checks the test questions downloaded by the user and makes corrections as necessary. During corrections, the emotion engine checks the user's emotional state again and provides appropriate feedback if stress is detected. The input is the corrected test file, and the output is the final test file.

[1518] Step 10:

[1519] The user uploads the final test file to the cloud storage again, and the server receives this file, associates it with the user account information, and stores it in the database. The input is the final test file, and the output is the file stored in the database.

[1520] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1521] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1522] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1523] [Fourth embodiment]

[1524] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1525] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1526] 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).

[1527] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1528] 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.

[1529] 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).

[1530] 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. 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.

[1531] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1532] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1533] 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.

[1534] 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.

[1535] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1536] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1537] The present invention is a system for improving the efficiency of test creation work in educational settings, and provides a series of means for collecting learning data based on an educational curriculum, generating test questions, and managing them. Specific embodiments of the present invention are described below.

[1538] A natural language description of the program's processing

[1539] 1. Building a database of educational content

[1540] server:

[1541] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes the contents of textbooks for each subject and grade, curriculum guidelines, past test questions, etc. This data is organized and managed so that users can easily access it.

[1542] 2. Accepting test generation requests

[1543] Device:

[1544] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[1545] User:

[1546] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[1547] server:

[1548] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[1549] 3. Selecting the test scope

[1550] Device:

[1551] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[1552] User:

[1553] Select the curriculum category, subject, and specific test scope, and submit a test generation request.

[1554] server:

[1555] It receives a test generation request from the user, extracts learning data related to the specified test scope, and provides it as input data to the generation AI.

[1556] 4. Test Generation

[1557] server:

[1558] Based on the specified test scope, the AI ​​generates test questions. The generated questions are output in Word file format. The algorithm is adjusted to create a balanced set of questions.

[1559] 5. Providing and Modifying Tests

[1560] server:

[1561] The generated Word file is saved in cloud storage, and users are provided with a download link through which they can download the test questions.

[1562] Device:

[1563] When teachers download the generated test via the provided link, it is saved to their device as a Word file, where they can review the content and make corrections if necessary.

[1564] User:

[1565] After correcting the test, we ask that you upload it to cloud storage again and store the final version of the data in the database.

[1566] 6. Digital storage of tests

[1567] User:

[1568] The final modified test file is uploaded to cloud storage and stored in the database.

[1569] server:

[1570] Receives uploaded final test files and stores them in a database for future reference and reuse.

[1571] Specific examples

[1572] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in Word file format.

[1573] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1574] In this way, the system of the present invention makes test creation more efficient and significantly reduces the burden on teachers.

[1575] The processing flow will be explained below.

[1576] Step 1:

[1577] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[1578] Step 2:

[1579] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[1580] Step 3:

[1581] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[1582] Step 4:

[1583] The user selects the curriculum category and subject, as well as the specific unit and scope from the drop-down menus, and then presses a button to submit a test generation request.

[1584] Step 5:

[1585] The server receives a test generation request from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1586] Step 6:

[1587] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, whether or not to include diagrams, etc. The generation AI automatically generates test questions based on this data.

[1588] Step 7:

[1589] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[1590] Step 8:

[1591] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[1592] Step 9:

[1593] Users can review the downloaded test questions and make corrections as necessary. The questions are saved in Word format, so they can be easily edited using standard document editing software.

[1594] Step 10:

[1595] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1596] Step 11:

[1597] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[1598] Example 1

[1599] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1600] Traditionally, test creation was a highly manual process that required a great deal of time and effort from teachers. Furthermore, inadequate database management made it difficult to reuse or efficiently search for past test questions. Furthermore, there was a lack of support for maintaining the balance and quality of the generated test questions. These tasks placed a significant burden on educational settings.

[1601] 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.

[1602] In this invention, the server includes means for collecting learning data and storing it in a database, means for providing an interface for teachers to select test topics, means for a generative AI model to generate test questions based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in remote storage, means for teachers to download and modify test files, means for re-uploading the modified test files and storing them in the database, means for periodically updating the collected data and generated test questions, and means for issuing session IDs to users. This enables more efficient test creation work and efficient data management.

[1603] "Learning data" refers to information collected based on the educational curriculum, such as the contents of textbooks for each subject and each grade, curriculum guidelines, and past test questions.

[1604] A "database" is an information management system that efficiently manages information organized according to specific rules and allows for quick search and updating as needed.

[1605] An "interface" is a window through which a user can interact with a system, such as a screen or input field.

[1606] A "generative AI model" is a program that uses artificial intelligence technology to automatically create test questions based on specified conditions.

[1607] A "document file" is a digital document stored in a format that contains text and images, such as a Word file.

[1608] "Remote storage" is an external data storage service that can be accessed via the Internet.

[1609] A "session ID" is an identifier issued to uniquely identify a user while the user is logged in.

[1610] "Users" are educational personnel who use this system to create and manage test questions.

[1611] The present invention is a system for streamlining test creation work in educational settings, and provides a series of means for collecting learning data based on educational courses, generating test questions, and managing them.

[1612] System hardware and software configuration

[1613] server:

[1614] Hardware: A server with a powerful processor, ample memory, and ample storage.

[1615] Software: Database management systems (e.g., SQL), generative AI models (e.g., GPT-3), cloud storage services (e.g., AWS S3).

[1616] Device:

[1617] Hardware: PCs, tablets, smartphones, etc.

[1618] Software: User interface using a web browser (Google Chrome, Mozilla Firefox, etc.).

[1619] User:

[1620] Teachers and other educational professionals.

[1621] Operation flow

[1622] 1. Building a database of educational content:

[1623] The server collects information such as textbook contents for each subject and grade, curriculum guidelines, and past test questions based on the educational curriculum, and stores it in a database. The data is updated regularly to ensure that the latest information is always maintained.

[1624] 2. Accepting test generation requests:

[1625] The terminal provides an interface for teachers to log in, and teachers enter their username and password to authenticate with the server. The server verifies the authentication information and, if successful, issues a session ID. The teacher then moves to the main menu screen and selects the test scope.

[1626] 3. Select the test scope:

[1627] The device provides a menu for selecting the educational curriculum (elementary school, middle school, high school) and subject. Teachers select specific units and areas and submit a test generation request. The server extracts learning data related to the specified test area from the database and provides it to the generative AI model.

[1628] 4. Generate tests:

[1629] The server sends a prompt to the generative AI model to generate test questions. The generative AI model creates balanced test questions based on the specified range and outputs them in a document file format. The generated file is stored in cloud storage.

[1630] 5. Test provision and correction:

[1631] The server provides teachers with a download link for the test file stored in cloud storage. Teachers download the file from the link and check and edit the contents. Once edited, the file is uploaded back to cloud storage and saved in the server's database.

[1632] Specific examples

[1633] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions and generates a balanced test set in document file format.

[1634] The generated document file is stored in cloud storage, and teachers download it from the provided link. After checking the content of the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse. In this way, the system of the present invention streamlines test creation work and significantly reduces the burden on teachers.

[1635] Prompt Sentence Examples

[1636] Here are some example prompts to input to a generative AI model:

[1637] "Generate balanced test questions based on the user-specified high school mathematics unit 'Functions and Graphs.' Specifically, include questions on the basic properties of functions, questions requiring graphing, and questions requiring solutions given a range of variables."

[1638] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1639] Step 1:

[1640] Building a database of educational content

[1641] server:

[1642] The server collects learning data such as the contents of textbooks for each subject and each grade based on the educational curriculum, curriculum guidelines, and past test questions.

[1643] Input: Textbooks, curriculum guidelines, and past test question data for each subject and grade level.

[1644] After collecting the data, the server organizes the data by category (e.g., subject, grade, unit) and stores it in a database.

[1645] Output: The organized training data is stored in a database.

[1646] Specific behavior:

[1647] 1. The server periodically downloads the latest teaching material data from databases of educational institutions and publishers.

[1648] 2. Analyze the collected data and classify it by subject, grade, and unit.

[1649] 3. Store the classified data in a database and create an index for easy access by users.

[1650] Step 2:

[1651] Accepting test generation requests

[1652] Device:

[1653] The terminal displays a user interface that allows the teacher to enter a username and password.

[1654] Input: Username and password of the user.

[1655] Output: Sends an authentication request to the server.

[1656] User:

[1657] The user enters a username and password in the user interface and presses the "Login" button.

[1658] Enter your username and password.

[1659] server:

[1660] The server checks the received authentication information against the user information in its database.

[1661] If authentication is successful, the server issues a session ID to the user and loads the main menu screen.

[1662] Enter your username and password.

[1663] Output: Authentication result (success / failure) and session ID.

[1664] Specific behavior:

[1665] 1. The teacher accesses the login screen on the device.

[1666] 2. The user enters their username and password and clicks the login button.

[1667] 3. The server checks the username and password against its database and, if they match, issues a session ID.

[1668] 4. The user moves to the main menu screen.

[1669] Step 3:

[1670] Test Scope Selection

[1671] Device:

[1672] The device displays the main menu screen with a menu for selecting the educational curriculum (elementary school, junior high school, high school) and subject.

[1673] Input: Select the curriculum category, subject, and unit.

[1674] Output: A request to send the selected test ranges to the server.

[1675] User:

[1676] The user selects the curriculum category and subject from the drop-down menus, and then selects the appropriate unit or area.

[1677] Once the selection is complete, the user presses the "Request Generation" button.

[1678] Input: Select the curriculum category, subject, and unit.

[1679] server:

[1680] The server receives a test generation request from a user and extracts the specified range information from the database.

[1681] Input: Select the curriculum category, subject, and unit.

[1682] Output: Provide the extracted training data to a generative AI model.

[1683] Specific behavior:

[1684] 1. The teacher accesses the main menu screen on the device.

[1685] 2. Select the curriculum category, subject, and unit from the drop-down menus.

[1686] 3. Press the "Request Generation" button to send a request to the server.

[1687] 4. The server extracts the specified range of training data from the database and provides it to the generative AI model.

[1688] Step 4:

[1689] Test Generation

[1690] server:

[1691] The server sends a prompt to the generative AI model and begins generating test questions.

[1692] Input: Extracted training data, prompt sentence.

[1693] Output: A document file of the generated test questions.

[1694] Specific behavior:

[1695] 1. The server sends a prompt to the generative AI model, such as "Generate balanced test questions based on the 'Functions and Graphs' unit of high school mathematics specified by the user."

[1696] 2. The generative AI model generates test questions based on the input prompt and training data.

[1697] 3. The generated test questions are saved on the server as a document file (e.g., a Word file).

[1698] Step 5:

[1699] Providing and Modifying Tests

[1700] server:

[1701] The server uploads the generated test file to cloud storage and provides a download link to the user.

[1702] Input: The generated test question document file.

[1703] Output: Download link.

[1704] Device:

[1705] The device will download the generated test via the provided link and save it as a document file on the device.

[1706] Input: Download link.

[1707] Output: The downloaded document file.

[1708] User:

[1709] The user opens the document file on the terminal, checks the contents, and corrects the test questions as necessary.

[1710] Re-upload the corrected file to cloud storage.

[1711] Input: The downloaded document file.

[1712] Output: The modified document file.

[1713] Specific behavior:

[1714] 1. The server uploads the generated test file to cloud storage.

[1715] 2. Teachers will download the test file via the provided link and review and correct the content.

[1716] 3. Upload the modified test file back to the cloud storage.

[1717] Step 6:

[1718] Digital storage of tests

[1719] User:

[1720] The user uploads the final modified test file to cloud storage.

[1721] Input: The modified document file.

[1722] Output: The upload request.

[1723] server:

[1724] The server receives the uploaded modified test file and stores it in a database.

[1725] Input: The modified document file.

[1726] Output: The final file stored in the database.

[1727] Specific behavior:

[1728] 1. The teacher uploads the final, revised test file to cloud storage.

[1729] 2. The server receives the uploaded file and stores it in the appropriate folder in the database.

[1730] 3. Add tags (e.g., "High School Math," "Functions and Graphs," "Created September 2023") to saved files to organize them for future search and reuse.

[1731] (Application example 1)

[1732] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1733] Currently, teachers have to manually create test questions, which requires a great deal of time and effort. At the same time, it is difficult to individually adjust test questions based on each student's learning progress. This makes it difficult to consistently improve the quality of education, and these problems are particularly prevalent in learning centers and cram schools. Furthermore, there are insufficient means for digitally managing and correcting the generated test questions, which increases the workload of educators.

[1734] 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.

[1735] In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in PDF file format and saving them in cloud storage, means for educators to download the test files and modify them on their digital devices, means for re-uploading the modified test files and storing them in the database, means for educators to request the generation of customized test questions based on each student's learning progress, a customization function for adjusting the difficulty and format of the generated test questions, and means for providing a download link for the generated test questions. This allows teachers to easily generate personalized test questions based on each student's learning progress, saving time and effort, and managing and modifying them in digital format.

[1736] An "educational curriculum" is a systematic compilation of learning content and goals that should be taught for each age group or grade level within the educational system.

[1737] "Learning data" is a general term for information collected based on the educational process, such as teaching materials, lesson content, and test questions.

[1738] A "database" is a computer system that stores information and data in a structured manner so that it can be easily accessed, managed, and updated.

[1739] An "interface" is a medium for exchanging information between a user and a computer system, and includes screens, menus, buttons, etc.

[1740] "Generative AI" is an artificial intelligence system that uses machine learning algorithms to automatically generate new test questions.

[1741] "PDF file format" is an abbreviation for Portable Document Format, and is a file format used to store and display documents electronically.

[1742] "Cloud storage" is a service for storing, sharing, and managing files online via the Internet.

[1743] "Digital terminal" is a general term for electronic devices that process information, such as smartphones, tablets, and computers.

[1744] "Customization function" refers to a function that allows users to personalize system and service settings according to their requests and meet their specific needs.

[1745] A "download link" is a URL used to download files on the Internet; by clicking on it you can obtain the desired file.

[1746] MODE FOR CARRYING OUT THE INVENTION

[1747] The present invention provides a system for improving the efficiency of test creation work in educational settings and for supporting individualized learning progress. Specific embodiments of this system are described below.

[1748] This system first collects learning data based on the educational curriculum and stores it in a database. The learning data includes teaching materials and past test questions for each subject and age group. This data is collected and stored on a server.

[1749] Next, an interface is provided for the educator to select the test scope. The interface includes a screen where the educator attempts to log in and a main menu that is displayed after successful authentication. The educator enters a username and password, is authenticated with the server, and moves to the main menu. Here, the educator selects the test scope.

[1750] Based on the selected test scope, the generation AI generates test questions. The test scope information is sent to the server, which then provides the generation AI with relevant learning data based on this information. The generation AI generates test questions using a machine learning algorithm (specifically, GPT-4). The generated test questions are saved on the server in PDF file format.

[1751] The generated PDF file is stored in cloud storage, and a download link is provided to the educator. The educator can download the PDF file via this link, review the content on a digital device, and make any necessary corrections. After making corrections, the file can be uploaded back to cloud storage, and the final test file can be stored in the database.

[1752] Furthermore, the system allows educators to request the generation of customized test questions based on each student's learning progress. Educators can provide the AI ​​with prompts to generate personalized test questions according to the student's progress, and adjust the difficulty and format of the test questions.

[1753] Hardware and software used

[1754] Server: AWS or Google Cloud

[1755] Database: MongoDB

[1756] Generative AI model: GPT-4 (OpenAI)

[1757] Client side: React Native (mobile apps), React.js (web apps)

[1758] Other tools: User authentication and session management using JSON Web Tokens (JWT), PDF file generation and management using Node.js, cloud storage with AWS S3

[1759] Specific examples

[1760] For example, let's say a mathematics teacher at a learning center wants to create a test on "simultaneous equations" for second-year junior high school students. The teacher logs into the system, selects "simultaneous equations" from the range of junior high school mathematics, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The generation AI then creates appropriate questions based on the following prompt:

[1761] Example prompt sentence:

[1762] Based on the following educational data, please generate a test question on simultaneous equations for second-year junior high school students. The test should have the following structure:

[1763] 1. Basic problems (calculation problems)

[1764] 2. Applied questions (word questions)

[1765] 3. Sample answers and explanations for each question

[1766] The generated PDF file is stored in cloud storage, and teachers can download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in its database for future reference and reuse.

[1767] As described above, the system of the present invention improves the efficiency of test creation work in educational settings and significantly reduces the burden on educators.

[1768] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1769] Step 1:

[1770] Collecting learning data and storing it in a database

[1771] The server collects learning data based on the curriculum and stores it in a database. Specifically, it collects data such as teaching materials and past test questions, and stores them in a structured MongoDB database. This prepares the basic data for use in subsequent test generation processes.

[1772] Step 2:

[1773] User authentication and interface provisioning

[1774] A user attempts to log in to a system using a terminal. They enter a username and password and request authentication from the server. The server checks the authentication information against a database, and if successful, issues session information and provides the user with an interface that displays the main menu. This prepares the user for accessing the system.

[1775] Step 3:

[1776] Test Scope Selection

[1777] The educator uses the device to select the educational curriculum category (e.g., junior high school), subject (e.g., mathematics), and specific unit (e.g., simultaneous equations). The selected information is sent to the server, which uses this information to extract relevant learning data from the database and prepares it as input data for the subsequent generative AI model.

[1778] Step 4:

[1779] Generate test questions

[1780] The server provides training data to a generative AI model (GPT-4) based on the specified test scope and generates test questions. Specifically, it inputs a prompt (e.g., "Based on the educational data below, please generate test questions on simultaneous equations for second-year junior high school students") to the generative AI model and receives the test questions output by the model. The generated questions are converted into PDF file format and temporarily saved on the server.

[1781] Step 5:

[1782] Save test questions and provide download links

[1783] The server saves the generated PDF file in cloud storage (such as AWS S3) and provides a download link to the educator. The user then downloads the PDF file from the provided link using their device and checks and corrects the content of the test questions.

[1784] Step 6:

[1785] Fix the test file and re-upload it

[1786] The educator opens the downloaded PDF file on their device and makes any necessary corrections. Once the corrections are complete, they upload it back to the cloud storage and request the server to save the final test file. The server receives the corrected file and stores it in a database.

[1787] Step 7:

[1788] Request for personalized test question generation

[1789] Educators provide the generative AI model with prompts to generate customized test questions based on each student's learning progress. The server then provides input data to the generative AI based on the prompts to generate personalized test questions.

[1790] Step 8:

[1791] Output and save customized test questions

[1792] The server outputs the personalized test questions as a PDF file and saves it in cloud storage. Educators are provided with a new download link, and users can download the file via their devices, check it, and make corrections. This provides test questions optimized for each student's learning progress.

[1793] 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.

[1794] The present invention is a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. This system combines a series of means for collecting learning data based on educational curriculum, generating test questions, and managing them with an emotion engine that recognizes the user's emotions and provides appropriate tests and feedback. Specific embodiments of the present invention are described below.

[1795] A natural language description of the program's processing

[1796] 1. Building a database of educational content

[1797] server:

[1798] Learning data is collected and stored in a database based on the educational curriculum. The collected data includes textbook content, curriculum guidelines, and past test questions. This data is organized and stored in an easy-to-search format.

[1799] 2. Accepting test generation requests

[1800] Device:

[1801] It provides an interface for teachers to log in. By entering a username and password, authentication is performed on the server, and if authentication is successful, the teacher is taken to the main menu.

[1802] User:

[1803] Enter your username and password to attempt to log in. After successful authentication, you will proceed to a menu where you can select the curriculum category, subject, and test scope.

[1804] server:

[1805] The authentication information is verified against the database, and if successful, a session is issued to the user. Based on the session information, the test scope information selected by the user is saved.

[1806] 3. Selecting the test area and checking the emotional state

[1807] Device:

[1808] It provides an interface for selecting the educational curriculum category (elementary school, junior high school, high school), subject, and specific unit or scope.

[1809] User:

[1810] Users select the curriculum category, subject, and specific test topics from drop-down menus, then press a button to submit a test generation request. The interface also features an emotion engine that analyzes the user's facial expressions and tone of voice to check their emotional state.

[1811] server:

[1812] It receives a test generation request and emotional state from the user, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1813] 4. Test generation and emotion-based adjustment

[1814] server:

[1815] The generation AI is started and input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included are passed in. The AI ​​also adjusts the difficulty and type of test appropriately based on the user's emotional state provided by the emotion engine.

[1816] The generative AI automatically generates test questions based on this data.

[1817] 5. Providing and Modifying Tests

[1818] server:

[1819] The generated test questions are output as Word files and saved to cloud storage. A unique download link for the saved file is generated and notified to the user.

[1820] Device:

[1821] A download link for the test file is displayed to the teacher. The teacher clicks the link to download the Word file and opens it on their device.

[1822] 6. Test correction and emotional feedback

[1823] User:

[1824] Review the downloaded test questions and make any necessary corrections. The questions are saved in Word format, making them easy to edit using standard document editing software. While correcting, the emotion engine analyzes the user's emotions and suggests appropriate feedback and relaxation methods if stress is detected.

[1825] 7. Digital storage of tests

[1826] User:

[1827] The final test file, after corrections are completed, is uploaded to cloud storage again and stored in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1828] server:

[1829] The system receives the uploaded final test file, associates it with the user's account information, and stores it in a database. This allows for the efficient organization and management of each school's test creation history and stored data.

[1830] Specific examples

[1831] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[1832] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1833] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[1834] The processing flow will be explained below.

[1835] Step 1:

[1836] The server collects curriculum-based learning data from multiple data sources and stores it in a database. Specifically, the data, such as textbook content, curriculum guidelines, and past test questions, is organized, tagged, and saved in an easily searchable format.

[1837] Step 2:

[1838] The user accesses the login interface from a terminal and attempts to log in by entering a username and password. If the login information is correct, authentication is successful and a session is issued.

[1839] Step 3:

[1840] The device displays a menu for teachers to select test content, including curriculum categories (elementary, middle, and high school) and subject options.

[1841] Step 4:

[1842] The user selects the curriculum category and subject, as well as the specific unit and scope from drop-down menus, and presses a button to send a test generation request. At this time, the emotion engine analyzes the user's facial expressions and tone of voice to check their emotional state.

[1843] Step 5:

[1844] The server receives the user's test generation request and emotional state information, extracts training data related to the specified test scope from the database, and prepares the extracted data as input data for the generation AI.

[1845] Step 6:

[1846] The server starts the generation AI and passes as input parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included.The server also appropriately adjusts the difficulty and type of test based on the user's emotional state using an emotion engine.

[1847] Step 7:

[1848] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link.

[1849] Step 8:

[1850] The device displays a download link for the test file to the user. The teacher clicks the link to download the Word file and opens it on their device.

[1851] Step 9:

[1852] The system checks the test questions downloaded by the user and makes corrections as necessary. The questions are saved in Word file format, making them easy to edit using common document editing software. While the user is correcting the questions, the emotion engine analyzes their emotions and suggests appropriate feedback and relaxation methods if stress is felt.

[1853] Step 10:

[1854] Once the user has completed the corrections, they upload the final test file back to the cloud storage and store it in the database. The uploaded file is saved in the database in a state that allows for future reference and reuse.

[1855] Step 11:

[1856] The server receives the uploaded final test file and stores it in a database in association with the user account information. This allows for efficient management of each school's test creation history and storage data.

[1857] Examples:

[1858] For example, consider a teacher creating a test for the "Functions and Graphs" unit in high school mathematics. The teacher logs into the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides the relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately.

[1859] The generated Word file is stored in cloud storage, and teachers download it from the provided link. After reviewing the test questions and making any necessary corrections, they upload the final test file back to cloud storage. The server stores this file in a database for future reference and reuse.

[1860] In this way, the system of the present invention can improve the efficiency of test creation work while optimizing the working environment by taking into account the emotional state of the teacher.

[1861] Example 2

[1862] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1863] Traditional test creation tasks require a great deal of time and effort from educators, often causing mental strain. Furthermore, tests are created without taking into account the educator's emotional state, which can increase stress for the educator. Furthermore, there are problems with the inefficient editing and storage of generated tests, making it difficult to reuse past data.

[1864] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for educators to log in by entering authentication information, means for providing an interface for educators to select test topics and for receiving the selected test topics and emotional state, means for analyzing the educator's emotions using an emotion analysis engine and adjusting the test content based on the results, means for generating test questions using a generation AI based on the selected test topics, means for outputting the generated test questions in a document file format and saving them in cloud storage, means for educators to download and modify the test file, means for re-uploading the modified test file and storing it in the database, and means for monitoring the educator's emotions during modification and providing feedback if stress is detected. This makes it possible to improve the efficiency of test creation work, optimize the work environment by taking into account the educator's emotional state, and reduce mental burden.

[1865] "Curriculum" refers to the learning content based on the curriculum guidelines and textbooks established by national and local educational institutions.

[1866] "Learning data" refers to information including the contents of textbooks related to the educational curriculum, curriculum guidelines, and past test questions.

[1867] A "database" refers to a digital system for organizing collected learning data and storing it in an easily searchable format.

[1868] "Interface" refers to the means that provides a screen and input methods for educators to interact with the system.

[1869] An "emotion analysis engine" refers to software that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[1870] "Generative AI" refers to artificial intelligence that automatically generates test questions based on specified parameters.

[1871] "Cloud storage" refers to a service that stores and manages data remotely via the Internet.

[1872] "Document file format" refers to a digital format for storing multi-page documents containing text and images.

[1873] "Educator" refers to a person whose job is to provide education to students.

[1874] "Feedback" refers to the advice and warnings the system provides based on the educator's emotional state.

[1875] This system aims to improve the efficiency of test creation work in educational settings and reduce the mental burden on educators. This system combines a means of collecting learning data based on educational curriculum, generating and managing test questions, and an emotion engine that recognizes educators' emotions and provides appropriate tests and feedback.

[1876] Collecting learning data and storing it in a database

[1877] server:

[1878] The server automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the Internet and books.

[1879] This data is organized by curriculum and stored in an SQL database, which is indexed and has an optimized search function to enable quick data access.

[1880] Educator Certification and Testing Options

[1881] Device:

[1882] A form for teachers to log in is displayed, with fields for entering username and password.

[1883] User:

[1884] Enter your username and password and press the login button.

[1885] server:

[1886] Receives form data and verifies it with user information in the database. If authentication is successful, creates a session and transitions to the main menu screen.

[1887] Selecting test areas and checking emotional state

[1888] Device:

[1889] Provides drop-down menus for selecting curriculum category (elementary, middle, high school), subject, and specific unit or area.

[1890] User:

[1891] Select the curriculum, subject, and unit from the menu and submit a test generation request.

[1892] Device:

[1893] The emotion engine analyzes the user's facial expressions and tone of voice in real time.

[1894] server:

[1895] The system receives the user's selected range and emotional state and extracts relevant learning data from the database.

[1896] Test generation and emotion-based adjustment

[1897] server:

[1898] The extracted training data and test parameters (number of questions, difficulty level, presence or absence of diagrams) are passed as input to the generation AI. Based on the analysis results of the emotion engine, the difficulty level of the test is adjusted appropriately.

[1899] Examples:

[1900] When a teacher wants to create a test for the "Functions and Graphs" unit in high school mathematics, the teacher logs in to the system, selects "Functions and Graphs" from the high school mathematics section, and submits a generation request. Based on this, the server provides relevant data to the generation AI. The emotion engine analyzes the teacher's facial expressions and tone of voice, and if the teacher is feeling stressed, the generation AI automatically adjusts the difficulty of the questions appropriately. The generated Word file is saved in cloud storage, and the teacher can download it from the provided link.

[1901] Providing and Modifying Tests

[1902] server:

[1903] The generated test questions are saved as Word files and uploaded to cloud storage. A download link is generated from the cloud storage and notified to the user.

[1904] Device:

[1905] Provide instructors with a download link for the test file.

[1906] User:

[1907] Click the download link to download the test questions in Word file format.

[1908] Test correction and emotional feedback

[1909] User:

[1910] Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections.

[1911] During the correction, the emotion engine will again analyze the user's emotions and provide feedback if stress is detected.

[1912] Digital storage of tests

[1913] User:

[1914] Upload the modified test file back to cloud storage.

[1915] server:

[1916] Uploaded files are stored in a database and associated with user account information for future reference and reuse.

[1917] Example prompt sentence:

[1918] "Generate test questions for functions and graphs. The questions should be of medium difficulty and include diagrams. Also, adjust the difficulty level slightly lower if the user is feeling stressed."

[1919] In this way, the system of the present invention can improve the efficiency of test creation work while also taking into account the emotional state of the educator, thereby reducing the mental burden on the educator and providing a better teaching environment.

[1920] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1921] Step 1:

[1922] Server: Automatically extracts learning data such as textbook contents, curriculum guidelines, and past test questions from the internet and books. Organizes the extracted data by educational curriculum and stores it in an SQL database.

[1923] Specific operations: Learning data is collected using scraping tools and OCR software and entered into a database, creating a highly searchable database of educational content.

[1924] Input: Textbook PDF file, web page

[1925] Output: Organized training data (SQL database)

[1926] Step 2:

[1927] Terminal: Display a form for teachers to log in, and provide fields for entering a username and password.

[1928] User: Enter your username and password and click the login button.

[1929] Server: Receives the form data and verifies it with the user information in the database. If authentication is successful, creates a session, issues a session ID to the user, and transitions to the main menu screen.

[1930] What it does: It hashes the user information and compares it with the information in the database. If the authentication information matches, it generates a session ID and stores it in a cookie.

[1931] Input: Username, Password

[1932] Output: Session ID

[1933] Step 3:

[1934] Device: Provides drop-down menus for selecting curriculum division (elementary, middle, high school), subject, and specific units or areas.

[1935] User: Selects the curriculum, subject, and unit from the menu and sends a test generation request. The device analyzes the user's facial expressions and tone of voice in real time using an emotion analysis engine.

[1936] Server: Receives the user's selected range and emotional state and extracts relevant learning data from the database.

[1937] What it does: The emotion analysis engine analyzes webcam footage, measures facial muscle movements to infer emotional state, and executes database queries to extract training data relevant to the specified test areas.

[1938] Input: Curriculum classification, subject, unit, emotional state (facial expression analysis)

[1939] Output: Extracted training data, emotional state data

[1940] Step 4:

[1941] Server: The extracted training data and test parameters (number of questions, difficulty level, whether or not diagrams are included) are passed to the generation AI as input. The difficulty level of the test is adjusted appropriately based on the analysis results of the emotion engine.

[1942] Specific behavior: Sends prompts to the generation AI, instructing it to generate questions with a medium level of difficulty for a specific range. Fine-tunes the difficulty setting based on data from the emotion engine.

[1943] Input: training data, test set parameters, emotional state data

[1944] Output: Generated test questions

[1945] Step 5:

[1946] Server: Saves the generated test questions in Word file format and uploads them to cloud storage. Generates a download link from the cloud storage and notifies the user.

[1947] On the device: Provide the teacher with a download link for the test file.

[1948] User: Click on the download link to download the test questions in Word file format.

[1949] Specific behavior: Upload the generated Word file to a cloud storage service (e.g., Amazon S3) and notify the user of the generated link.

[1950] Input: Generated test questions (Word file), cloud storage credentials

[1951] Output: Download link

[1952] Step 6:

[1953] User: Open the downloaded test questions in a document editing software such as Microsoft Word and make any necessary corrections. While correcting, the emotion analysis engine analyzes the user's emotions again and displays feedback if stress is detected.

[1954] What it does: While you edit, the emotion analysis engine continuously analyzes your facial expressions and tone of voice, and if stress is detected, a pop-up message will appear.

[1955] Input: Test questions (Word file), real-time emotional state data

[1956] Output: Fixed test questions, feedback messages

[1957] Step 7:

[1958] User: Upload the modified test file back to cloud storage.

[1959] Server: Stores uploaded files in a database and associates them with user account information for future reference and reuse.

[1960] Specific operation: The metadata of uploaded files (creation date and time, subject, unit, etc.) is saved in a database for efficient file management.

[1961] Input: Modified test file (Word file), user account information

[1962] Output: Test files stored in the database

[1963] (Application example 2)

[1964] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1965] Creating tests in educational settings takes a lot of time, placing a heavy burden on teachers. The stress and fatigue felt during the work are also a problem. Similarly, inspection work in factories and other places requires time and effort to manually plan and execute inspections, placing a heavy mental burden on workers. There is a need to improve this situation, increase work efficiency, and reduce the mental burden on workers.

[1966] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting learning data based on the educational curriculum and storing it in a database, means for providing an interface for teachers to select test topics, means for a generation AI to generate test questions based on the selected test topics, means for outputting the generated test questions in Word file format and saving them in cloud storage, means for recognizing user emotions and adjusting the difficulty and type related to the test topics, means for teachers to download and modify test files, and means for re-uploading the modified test files and storing them in the database. This makes it possible to streamline test creation work and reduce the mental burden on teachers and workers.

[1967] Definitions of important words

[1968] "Curriculum" refers to the learning content and structure of lessons offered at schools and educational institutions, as well as the progress plan for each grade level.

[1969] "Learning data" refers to learning materials, reference materials, past test questions, and information based on curriculum guidelines for students.

[1970] A "database" is a system or mechanism that organizes and stores information so that it can be searched and used as needed.

[1971] "Interface" refers to the screens and input devices used by teachers and users to operate the system, and specifically includes login screens and menu screens.

[1972] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate content such as test questions based on specified conditions.

[1973] "Generating test questions" means creating test questions, including question statements, options, and answers, based on the training data.

[1974] "Cloud storage" refers to an online data storage service accessible via the Internet where you can store and manage data.

[1975] "Recognizing the user's emotions" means determining the user's mental state, such as stress or fatigue, through analysis of the user's facial expressions and tone of voice.

[1976] "Adjusting the difficulty and type of questions related to the test scope" refers to changing the difficulty and type of questions given in consideration of the user's emotional state.

[1977] "Downloading" means importing files or data stored in cloud storage, etc., to your device via the Internet or a network.

[1978] "Uploading" refers to sending and storing data or files from your device via the Internet or a network to an online service such as cloud storage.

[1979] The present invention provides a system for improving the efficiency of test creation work in educational settings and reducing the mental burden on teachers. Specific embodiments of the present invention will be described below.

[1980] Hardware and Software Configuration

[1981] 1. Hardware:

[1982] Server: Responsible for database management and running generative AI.

[1983] Device: The device used by the teacher (e.g., PC, tablet, etc.).

[1984] 2. Software:

[1985] Database Management System: A database for storing training data and test files.

[1986] Generative AI: Software that automatically generates test questions using AI models.

[1987] Emotion Recognition Engine: Software that recognizes teachers' emotions and provides feedback.

[1988] Data processing and calculation methods

[1989] The server collects learning data and stores it in a database. Teachers access the interface using their devices and select the test topics. The information on the selected test topics is sent to the server, which then passes it on to the generation AI as input. The generation AI generates test questions and saves the results in cloud storage as a Word file.

[1990] The emotion recognition engine analyzes the teacher's facial expressions and tone of voice through the interface to determine their stress level, and this situational data is sent to the server, which then adjusts the difficulty and type of test questions.

[1991] Specific examples

[1992] For example, consider the case where a worker at a factory is performing a regular inspection and the inspection work plan is automatically generated. The worker wears a smartphone or smart glasses, and an emotion recognition engine monitors the worker's emotional state. When the worker feels stressed, the server automatically adjusts the content and order of the inspection tasks to optimize work efficiency.

[1993] Prompt Sentence Examples

[1994] Here is a specific example of an input prompt sentence for the generative AI model.

[1995] Emotion recognition: "High stress"

[1996] Generate a list of inspection tasks and eliminate low priority tasks.

[1997] This method makes it possible to achieve both overall efficiency and the mental health of workers not only in test creation work but also in a variety of on-site tasks in factories and other places.

[1998] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1999] Program processing steps

[2000] Step 1:

[2001] The server collects learning data based on the curriculum and stores it in a database. The input data includes textbook content, curriculum guidelines, and past test questions, and the output is to organize and store this data in a database in an easy-to-search format.

[2002] Step 2:

[2003] The user (teacher) accesses the login interface using a terminal and attempts authentication by entering their username and password. The server compares the authentication information with the database, and if authentication is successful, issues a session and transitions to the main menu. The input is the user's authentication information, and the output is session information if successful.

[2004] Step 3:

[2005] The user is directed to an interface for selecting the curriculum category, subject, and test area. The input is the user's selection information, and the output is the selected test area information.

[2006] Step 4:

[2007] The device interface uses an emotion recognition engine to analyze the user's facial expressions and tone of voice to check their emotional state. The input is the user's facial expressions and voice data, and the output is the analyzed emotional state.

[2008] Step 5:

[2009] The server receives a test generation request and emotional state from the user, and extracts training data related to the specified test range from the database. The input is the test generation request and emotional state, and the output is the extracted training data.

[2010] Step 6:

[2011] The server starts the generation AI and passes parameters such as the specified test scope, number of questions, difficulty level, and whether or not diagrams are included as input to the generation AI.The server also appropriately adjusts the difficulty and type of test based on the emotional state provided by the emotion engine.The input is the generation parameters and the emotional state, and the output is the generated test questions.

[2012] Step 7:

[2013] The server outputs the generated test questions in Word file format and saves them in cloud storage. It also generates a unique download link for the saved file and notifies the user of this link. The input is the generated test questions, and the output is the save and download link to cloud storage.

[2014] Step 8:

[2015] A user clicks on the download link of the test file on the device and downloads the Word file. The input is the download link, and the output is the test file saved on the device.

[2016] Step 9:

[2017] The system checks the test questions downloaded by the user and makes corrections as necessary. During corrections, the emotion engine checks the user's emotional state again and provides appropriate feedback if stress is detected. The input is the corrected test file, and the output is the final test file.

[2018] Step 10:

[2019] The user uploads the final test file to the cloud storage again, and the server receives this file, associates it with the user account information, and stores it in the database. The input is the final test file, and the output is the file stored in the database.

[2020] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2021] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2022] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2023] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2024] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2025] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2026] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2027] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2028] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2029] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2030] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2031] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2032] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2033] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2034] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2035] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2036] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2037] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2038] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2039] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2040] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2041] The following is further disclosed regarding the above embodiment.

[2042] (Claim 1)

[2043] a means for collecting and storing curriculum-based learning data in a database;

[2044] a means for providing an interface for teachers to select test areas;

[2045] A means for generating test questions by the generation AI based on the selected test scope;

[2046] A means to output the generated test questions in Word file format and save them in cloud storage,

[2047] A means for teachers to download and modify test files;

[2048] The system includes a means for re-uploading modified test files and storing them in the database.

[2049] (Claim 2)

[2050] 10. The system of claim 1, wherein the system is capable of generating questions using diagrams.

[2051] (Claim 3)

[2052] 2. The system according to claim 1, further comprising means for storing and managing user accounts and request histories for each school in a database.

[2053] "Example 1"

[2054] (Claim 1)

[2055] a means for collecting and storing training data in a database;

[2056] a means for providing an interface for teachers to select test areas;

[2057] A means for the generative AI model to generate test questions based on the selected test scope;

[2058] A means for outputting the generated test questions in a document file format and storing them in a remote storage;

[2059] A means for teachers to download and modify test files;

[2060] A means to re-upload the modified test file and store it in the database;

[2061] A means of periodically updating the collected data and generated test questions;

[2062] A system that includes a means for issuing a session ID to a user.

[2063] (Claim 2)

[2064] 2. The system according to claim 1, wherein the system is capable of generating problems using diagrams.

[2065] (Claim 3)

[2066] 2. The system according to claim 1, further comprising me...

Claims

1. a means for collecting and storing curriculum-based learning data in a database; a means for providing an interface for teachers to select test areas; A means for generating test questions by the generation AI based on the selected test scope; A means to output the generated test questions in Word file format and save them in cloud storage, A means for teachers to download and modify test files; The system includes a means for re-uploading modified test files and storing them in the database.

2. The system of claim 1, wherein the system allows for diagram-based problem generation.

3. 2. The system according to claim 1, further comprising means for storing and managing user accounts and request histories for each school in a database.

Images