System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving input information from a user and initializing a grade, a learning goal, a strong subject, and a weak subject; means for storing the generated user ID and initialization data in a database; means for performing an academic ability analysis of the user and identifying the strong and weak subjects; means for generating exercises and explanations focused on the weak subjects; means for receiving user answers and returning scores and results; means for recording user progress data and generating feedback periodically; and means for presenting a customized curriculum to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's educational environment, many elementary, junior high, and high school students have difficulty finding the right learning methods to efficiently improve their academic abilities. Furthermore, the high cost of individualized instruction makes it difficult for many families to receive ongoing educational support. Furthermore, a uniform learning curriculum does not provide effective learning tailored to each student's academic level or weak subjects, resulting in poor academic performance. There is a need to solve these issues and provide individualized educational support efficiently and at low cost. [Means for solving the problem]

[0005] This invention relates to a system that includes: means for receiving input information from a user and initializing the grade, learning goals, and strong and weak subjects; means for saving the generated user ID and initial setting data in a database; means for analyzing the user's academic ability and identifying areas of strength and weakness; means for generating practice questions and explanations focused on weak areas; means for receiving the user's answers, grading, and returning the results; means for recording the user's progress data and generating regular feedback; and means for presenting a customized curriculum to the user. This system can provide efficient and effective learning support tailored to the user's individual learning needs and reduce educational costs. It can also promote the improvement of users' academic ability and provide equal educational opportunities.

[0006] "Users" refer to students and their parents who use the system to learn.

[0007] "Input information" refers to information such as grade level, learning goals, favorite subjects, and weak subjects that the user provides to the system.

[0008] "Initial settings" refers to setting basic data such as the academic year and learning goals on the system based on information entered by the user.

[0009] "Database" refers to the system's internal storage function for storing and managing user initial setting data, learning progress data, etc.

[0010] "Academic ability analysis" refers to the evaluation process used to identify areas of strength and weakness based on user input and learning history.

[0011] "Practice Problems" refers to individual problem sets created to help users overcome their weaknesses.

[0012] "Explanation" refers to text or multimedia content that provides detailed explanations and solutions to the exercises.

[0013] "Scoring" refers to the process of evaluating a user's answers and determining which answers are correct and which are incorrect.

[0014] "Progress data" refers to data that records the content and results that a user has achieved through daily learning.

[0015] "Feedback" refers to information that suggests areas for improvement and next learning goals based on the user's learning results and progress.

[0016] "Curriculum" refers to a user's learning plan, including assignments and study schedules based on individual learning goals and progress. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, and manages learning progress.

[0039] System configuration

[0040] The system consists of the following main components:

[0041] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0042] 2. Server: Performs database management, generating AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[0043] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[0044] Program processing overview

[0045] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[0046] User registration and initial settings

[0047] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[0048] Academic ability analysis

[0049] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[0050] Creating practice questions

[0051] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[0052] Providing feedback

[0053] The server evaluates the user's progress based on the results of the exercises and generates personalized feedback, which the device displays to the user and suggests the next learning step.

[0054] Creating a customized curriculum

[0055] The server periodically sets tests to evaluate the user's progress. When the user takes the test, the server creates a customized learning curriculum based on the test results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[0056] Specific examples

[0057] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[0058] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and submits the results to the server, which immediately scores them and provides feedback. Furthermore, a regularly updated customized learning curriculum is generated based on User A's learning progress, providing specific suggestions for what to study next.

[0059] In this way, the entire system works in cooperation to fully meet the learning needs of each user and provide efficient and effective learning support.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user enters the required information (user name, password, grade, email address) on the new registration screen and presses the "Register" button.

[0063] Step 2:

[0064] The terminal transmits the input information to the server.

[0065] Step 3:

[0066] The server generates a new user ID based on the received data and saves the initial setting data in the database.

[0067] Step 4:

[0068] The user logs in, enters information on the screen where they can enter their grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[0069] Step 5:

[0070] The terminal transmits the input initial setting information to the server.

[0071] Step 6:

[0072] The server receives the initial setting information, stores it in the user's profile data, and simultaneously prepares to start the academic ability diagnostic test.

[0073] Step 7:

[0074] The user presses the "Start academic ability diagnostic test" button.

[0075] Step 8:

[0076] The terminal transmits a request to start the academic ability diagnostic test to the server.

[0077] Step 9:

[0078] The server generates appropriate academic ability diagnostic questions according to the user's grade level and sends them to the terminal.

[0079] Step 10:

[0080] The terminal displays the questions of the academic ability diagnostic test to the user.

[0081] Step 11:

[0082] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[0083] Step 12:

[0084] The terminal sequentially transmits the user's answers to the server.

[0085] Step 13:

[0086] The server scores the received answers and records whether each question is correct or incorrect.

[0087] Step 14:

[0088] Based on all the responses, the server analyzes the user's strengths and weaknesses and generates a report of the results.

[0089] Step 15:

[0090] The terminal displays the academic ability analysis result report to the user.

[0091] Step 16:

[0092] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[0093] Step 17:

[0094] The terminal displays the generated exercises and explanations to the user.

[0095] Step 18:

[0096] The user completes the exercises and enters their answers.

[0097] Step 19:

[0098] The terminal transmits the user's answer to the server.

[0099] Step 20:

[0100] The server receives the answers, scores them, determines whether they are correct or incorrect, adds explanations, and generates an evaluation result.

[0101] Step 21:

[0102] The terminal displays the evaluation results and explanations to the user.

[0103] Step 22:

[0104] The server records the user's progress data and periodically generates feedback and learning progress reports.

[0105] Step 23:

[0106] The device displays feedback and learning progress reports to the user.

[0107] Step 24:

[0108] The server periodically sets up an academic ability assessment test for the user and notifies the user.

[0109] Step 25:

[0110] The user takes an academic assessment test and enters their answers.

[0111] Step 26:

[0112] The terminal transmits the user's answer to the server.

[0113] Step 27:

[0114] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[0115] Step 28:

[0116] The server generates a curriculum optimized for the user based on the test results.

[0117] Step 29:

[0118] The terminal displays the generated curriculum to the user and suggests the next learning stage.

[0119] The above are the specific processing steps for carrying out the invention. The operations performed by the server, terminal, and user at each step are described in detail.

[0120] Example 1

[0121] 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."

[0122] Conventional learning support systems have had the problem of being difficult to provide effective learning support because they are unable to respond to the academic ability and progress of individual users. Furthermore, they are unable to provide appropriate practice problems to overcome weaknesses in specific areas. Furthermore, they are inadequate in providing customized feedback and creating learning plans based on the user's learning progress, making it difficult to expect improvements in learning efficiency.

[0123] 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.

[0124] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness; [means for saving the generated user identification information and initial setting data in a database; [means for conducting a user's academic ability diagnostic test and evaluating academic ability; [means for identifying the user's areas of strength and weakness; [means for using a generative AI model to generate practice questions and explanations focusing on areas of weakness; [means for receiving the user's answers, grading and returning the results; [means for recording the user's progress and generating individual feedback; and [means for presenting a customized study plan to the user.] This enables learning support tailored to each individual user, effectively supporting the user's improvement in academic ability.

[0125] "User identification information" is information generated to uniquely identify each individual user.

[0126] "Initial setting data" refers to data such as grade, learning goals, strong subjects, and weak subjects that are input by the user when registering for the first time.

[0127] A "database" is a system for storing user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[0128] An "academic ability diagnostic test" is a collection of questions used to evaluate a user's current academic ability.

[0129] A "generative AI model" is an artificial intelligence model that generates appropriate practice questions and explanations based on the user's weak areas.

[0130] "Practice questions" are questions that are given with the aim of improving the user's academic ability.

[0131] "Feedback" refers to notifying users of evaluations and areas for improvement based on their learning outcomes and progress.

[0132] A "customized study plan" is a study schedule that is individually created based on the user's academic ability and progress.

[0133] This invention provides a learning support system equipped with a generative AI model. It analyzes the user's academic ability and provides individually optimized learning plans and feedback, thereby achieving efficient and effective learning support.

[0134] System configuration

[0135] The system consists of the following main components:

[0136] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or personal computer.

[0137] 2. Server: Performs database management, processing using generative AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[0138] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, learning curriculum, etc.

[0139] User registration and initial settings

[0140] The process begins when the user enters information such as name, grade, learning goals, and areas of strength and weakness on the new registration screen. The device sends this information to the server, which then generates new user identification information based on the received information. The generated identification information and initial setting data are stored in a database.

[0141] Academic ability analysis

[0142] When a user starts an academic ability diagnostic test, the device sends a request to the server. The server uses a generative AI model to create appropriate academic ability diagnostic questions based on the user's grade level, and then sends them to the device. The user's answers are sent via the device to the server, which automatically scores them and identifies the user's strengths and weaknesses.

[0143] Creating practice questions

[0144] Based on the results of the academic ability assessment, the server uses a generative AI model to generate practice questions that focus on the user's weak areas. The generated questions are sent to the device and presented to the user. The user's answers are sent via the device to the server, which evaluates them and generates feedback.

[0145] Providing feedback

[0146] Based on the results of the exercises the user answers, the server generates personalized feedback, which the device displays to the user and suggests the next steps to take. The feedback includes detailed evaluations and advice, with the aim of deepening the user's understanding.

[0147] Creating a customized curriculum

[0148] The server periodically evaluates the user's progress and sets new tests as needed. Based on the user's test results, a customized learning plan is created using a generative AI model. The generated curriculum is sent to the device and presented to the user.

[0149] Specific use cases

[0150] For example, consider the case where User A, a fifth-grader in elementary school, newly registers with the system. User A enters information such as his name, grade, learning goals, favorite subject (math), and weak subject (Japanese). This information is sent from the terminal to the server, which generates new user identification information and stores it in a database. User A then begins an academic ability diagnostic test, and the server generates appropriate questions and sends them to the terminal. User A's answers are graded by the server, and grammar questions that User A is particularly weak at are extracted.

[0151] The server automatically generates practice questions focusing on weak grammar points and provides them to User A via the terminal. User A answers these questions and submits them to the server again, where the server evaluates the answers and generates feedback, including suggestions for improvement and additional practice questions.

[0152] Examples of prompt statements

[0153] "Please generate grammar exercises for a fifth-grade elementary school student. The user feels that he or she is not good at grammar."

[0154] Based on this prompt, the generative AI model provides appropriate practice questions for User A. This allows the entire system to work together to meet the user's learning needs and provide efficient and effective learning support.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Step 1:

[0157] The user enters the required information (name, grade, learning goals, areas of strength and weakness, etc.) on the new registration screen.

[0158] Input: User's personal and study-related information

[0159] Output: User input data

[0160] Specific behavior: The user enters information into the input form and presses the "Submit" button.

[0161] Step 2:

[0162] The terminal transmits the input user information to the server.

[0163] Input: User-entered data

[0164] Output: Data sent to the server

[0165] Specific operation: The terminal sends the received user input data to the server using the HTTPS protocol.

[0166] Step 3:

[0167] The server generates new user identification information based on the received information and stores the initial setting data in a database.

[0168] Input: Data to send to the server

[0169] Output: User identity and database updates

[0170] Specific operation: The server generates user identification information from the received data and executes an SQL query to store it in a database.

[0171] Step 4:

[0172] The server generates an academic ability diagnostic test, selects appropriate questions based on grade information, and sends them to the terminal.

[0173] Input: User's grade information and initial setting data

[0174] Output: Academic ability diagnostic test

[0175] Specific operation: The server selects appropriate questions from the question bank based on grade information, and if necessary, generates new questions using a generative AI model and sends them to the terminal.

[0176] Step 5:

[0177] The user takes an academic ability diagnostic test and transmits the answers to the server via the terminal.

[0178] Input: Academic ability diagnostic test and user answers

[0179] Output: User answer data

[0180] Specific operation: The user answers the diagnostic test using the terminal and presses the send answer button, which sends the answer data to the server.

[0181] Step 6:

[0182] The server automatically scores the user's answer data and identifies areas of strength and weakness.

[0183] Input: User answer data

[0184] Output: Analysis of strengths and weaknesses

[0185] Specific operation: The server automatically scores the received answer data and analyzes the areas of strength and weakness using a specific algorithm.

[0186] Step 7:

[0187] The server uses a generative AI model to generate practice questions and explanations based on the user's weak areas and sends them to the device.

[0188] Input: Analysis results of strengths and weaknesses

[0189] Output: Exercises and explanations

[0190] Specific operation: The server uses the generative AI model to generate questions that focus on the user's weak areas and sends them to the device.

[0191] Step 8:

[0192] The user answers the exercises and sends the results from the terminal to the server.

[0193] Input: Exercises and user answers

[0194] Output: User answer data

[0195] Specific operation: The user answers the practice questions and sends the results to the server using the send button on the device.

[0196] Step 9:

[0197] The server evaluates the practice question answer data and generates feedback.

[0198] Input: User answer data

[0199] Output: Feedback

[0200] Specific operation: The server evaluates the answer data and uses a generative AI model to create detailed feedback for the user and send it to the device.

[0201] Step 10:

[0202] A server periodically evaluates the user's progress data and generates a customized learning curriculum that is regularly updated.

[0203] Input: User progress data

[0204] Output: Customized learning curriculum

[0205] Specific operation: The server evaluates the user's progress data, uses a generative AI model to generate an individually optimized learning curriculum, and sends it to the device.

[0206] Step 11:

[0207] The terminal displays the customized learning curriculum to the user.

[0208] Input: Customized Learning Curriculum

[0209] Output: Presentation of study schedule

[0210] Specific operation: The terminal displays the received curriculum to the user and indicates the specific content that should be studied next.

[0211] In this way, the entire system cooperates to provide effective learning support that meets the user's learning needs.

[0212] (Application example 1)

[0213] 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."

[0214] Conventional factory worker training systems have made it difficult to provide effective training programs tailored to the skill level of each worker. Standardized training programs cannot adequately reflect the actual abilities and progress of workers, resulting in reduced training efficiency. Customizing training content also requires a significant amount of time and effort, making it difficult to manage progress and provide feedback in real time.

[0215] 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.

[0216] In this invention, the server includes: means for receiving input information from a user and initializing the installation year, goals, strengths and weaknesses; means for saving the generated account ID and initial setting data in a database; means for performing a skill evaluation of the worker and identifying strengths and weaknesses; means for generating training modules and explanations focusing on the weaknesses; means for receiving the worker's answers, scoring, and returning the results; means for recording the worker's progress data and periodically generating feedback; means for presenting a customized training program to the worker; means for generating optimal training content for the worker using a generative AI model; and means for inputting prompts to the generative AI model and outputting the required training content. This enables the provision of an effective training program tailored to the skill level of each worker.

[0217] "User input" is data that operators use to communicate initial setup and individual training needs to the system.

[0218] "Year of installation" refers to the year in which the worker began performing the work.

[0219] "Goal" refers to a specific educational or skill-building goal that a worker seeks to achieve.

[0220] "Area of ​​expertise" refers to an area in which a worker has relatively high skills or knowledge.

[0221] "Weak areas" refer to areas in which a worker has relatively low skills or knowledge.

[0222] An "account ID" is an identifier generated to uniquely identify a worker within the system.

[0223] "Initial setting data" is data that collects setting information provided when an operator starts using the system.

[0224] "Skills assessment" is the process of analyzing a worker's current skill level and identifying their strengths and weaknesses.

[0225] An "educational module" is an educational unit that includes a series of instructional content for acquiring specific skills or knowledge.

[0226] "Explanation" refers to detailed explanatory text and illustrations that allow workers to understand the content contained in the training module.

[0227] An "answer" is a response that a worker submits to an educational module or test.

[0228] "Scoring" is the process of evaluating a worker's answers to determine their accuracy.

[0229] "Results" refers to the evaluation and feedback generated based on the worker's answers.

[0230] "Progress data" is data that records the progress of a worker's education and training.

[0231] "Feedback" refers to advice and evaluation provided to workers regarding their education and training progress.

[0232] A "training program" is a set of educational content customized to improve a worker's skills.

[0233] A "generative AI model" is an artificial intelligence model that is trained to perform a specific task based on large amounts of data.

[0234] A "prompt sentence" is an instruction sentence input to a generative AI model to instruct the worker on how to generate training content.

[0235] This invention relates to a head-mounted display (HMD) application for supporting worker training in factories and a training content generation system that uses a generative AI model. This system provides appropriate training programs according to the skill level of each worker, achieving efficient and effective training.

[0236] System configuration

[0237] The system consists of the following main components:

[0238] 1. User terminal: A head-mounted display (HMD) that allows workers to access the system and receive training content.

[0239] 2. Server: Performs database management, operation of generative AI models, skill evaluation, educational module generation, answer evaluation, and feedback provision.

[0240] 3. Database: Stores worker profile information, skill evaluation results, education history, training programs, etc.

[0241] Specific operation of the system

[0242] User registration and initial settings

[0243] When the user enters the required information (year of installation, goals, areas of strength and weakness) on the new registration screen, the device sends the data to the server. The server generates a new account ID based on the received data and saves the initial setting data in the database.

[0244] Skills Evaluation

[0245] When a user starts a skills assessment test, the device sends the request to the server. The server generates skills assessment questions according to the worker's role and sends them to the device. When the worker solves the questions and submits their answers, the server scores them and identifies the worker's strengths and weaknesses.

[0246] Creating an Educational Module

[0247] Based on the results of the skill assessment, the server generates an educational module and explanations that focus on the worker's weak areas. The terminal receives this and presents it to the worker. The user studies the educational module and sends the answer results from the terminal to the server. The server evaluates the answer and returns the results and feedback.

[0248] Providing feedback

[0249] The server evaluates the worker's progress based on the results of the training module and generates individual feedback, which is displayed to the worker on the terminal and suggests the next training step.

[0250] Customize your training program

[0251] The server periodically sets tests to evaluate the worker's progress. When the user takes the test, the server creates a customized training program based on the results and sends it to the terminal. The terminal then presents the training program to the worker, supporting their daily education.

[0252] Technology used

[0253] This system uses TensorFlow and Keras to build a generative AI model that evaluates worker skills and generates optimal training programs based on large amounts of data. It also uses an SQL database system for database management, processing and analyzing data in real time.

[0254] Specific examples

[0255] For example, when a new worker A is assigned to a factory, he or she is registered in the system. The initial setup involves entering the year of installation, training goals, areas of strength (e.g., machine operation), and areas of weakness (e.g., safety management). The system receives this information and generates an optimal training program based on it.

[0256] After taking the skill assessment test, the system evaluates Worker A's current skill level and generates a training module that focuses on his weaknesses. It then inputs the following prompt sentence into the generative AI model:

[0257] "Please assess the skill level of your workers and suggest appropriate training programs. The dataset is as follows: [example data]"

[0258] Based on this prompt, the most appropriate training content is generated and displayed on the HMD of Worker A. This allows Worker A to receive the training necessary to improve his or her skills in real time.

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

[0260] Step 1:

[0261] The user enters the necessary information (year of establishment, goals, areas of strength, areas of weakness) on the new registration screen. The terminal sends the data to the server.

[0262] Input: Year of establishment, goals, areas of strength and weakness information

[0263] Output: Registration information sent to the server

[0264] Specific operation: The user inputs information using the HMD's user interface and presses the send button.

[0265] Step 2:

[0266] The server generates a new account ID based on the received data and stores the initial setting data in the database.

[0267] Input: Registration information

[0268] Output: Generated account ID and initial setting data

[0269] Specific operation: The server accesses the database, creates a new record, and automatically generates an account ID.

[0270] Step 3:

[0271] When a user starts a skill assessment test, the terminal sends the request to the server.

[0272] Input: Skills Assessment Test Request

[0273] Output: Request sent to the server

[0274] Specific operation: The user presses the evaluation test start button on the HMD.

[0275] Step 4:

[0276] The server generates skill evaluation questions according to the worker's role and sends them to the terminal.

[0277] Input: Role information

[0278] Output: Generated skill assessment questions

[0279] Specific operation: The server uses the generative AI model to generate an appropriate problem set and sends it to the device.

[0280] Step 5:

[0281] The user solves the problem and sends the answer from the terminal to the server.

[0282] Input: Worker's response

[0283] Output: The answer sent to the server

[0284] Specific operation: The user solves the problem using the HMD and presses the answer button to submit the result.

[0285] Step 6:

[0286] The server scores the answers and identifies the worker's strengths and weaknesses.

[0287] Input: Answer data

[0288] Output: Identification of strengths and weaknesses

[0289] What happens: The server uses a scoring algorithm to evaluate and identify answers.

[0290] Step 7:

[0291] Based on the results of the skills assessment, the server generates educational modules and explanations that focus on the worker's areas of weakness.

[0292] Input: Results of identifying strengths and weaknesses

[0293] Output: Educational modules and descriptions

[0294] Specific operation: The server inputs a prompt sentence into the generative AI model and generates educational content.

[0295] Step 8:

[0296] The server sends the generated educational module to the terminal, where the user receives it and begins learning.

[0297] Input: Education Module

[0298] Output: Educational module sent to the device

[0299] Specific operation: The server sends educational content to the terminal and it is displayed on the HMD.

[0300] Step 9:

[0301] The user studies the educational module and sends the answers from the terminal to the server.

[0302] Input: Learning results and answers

[0303] Output: Learning results and answers sent to the server

[0304] Specific operation: The user uses the HMD to learn, input and submit the results.

[0305] Step 10:

[0306] The server evaluates the answers and generates results and feedback.

[0307] Input: Learning results and answers

[0308] Output: Evaluation results and feedback

[0309] Specific operation: The server evaluates the answer using an answer evaluation algorithm and generates feedback.

[0310] Step 11:

[0311] The server evaluates the worker's progress based on the results of the training module and generates individual feedback.

[0312] Input: Answer evaluation result

[0313] Output: Individual feedback

[0314] What happens: The server analyzes the progress data and generates feedback.

[0315] Step 12:

[0316] The server creates a customized training program and sends it to the terminal, which presents it to the user.

[0317] Input: Individual feedback

[0318] Output: Customized training program

[0319] Specific operation: The server generates an educational program using the generative AI model and sends it to the device. It is then displayed on the HMD.

[0320] An example of a specific prompt would be, "Please assess the skill level of workers and suggest appropriate training programs. The dataset is as follows: [Example data]," and you can get output results from the generative AI model.

[0321] 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.

[0322] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[0323] System configuration

[0324] The system consists of the following main components:

[0325] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0326] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[0327] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[0328] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[0329] Program processing overview

[0330] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[0331] User registration and initial settings

[0332] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[0333] Academic ability analysis

[0334] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[0335] Creating practice questions

[0336] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[0337] Emotion recognition and feedback provision

[0338] The device sends the user's facial and voice data to the emotion engine, which then uses this data to recognize the user's emotional state. After the user completes the exercise, the emotion data is also analyzed and appropriate feedback is generated. For example, if the user looks tired, the system may respond by displaying an encouraging message.

[0339] Creating a customized curriculum

[0340] The server periodically sets tests to evaluate the user's progress and emotional data. After the user takes the test, the server creates a customized learning curriculum based on the results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[0341] Specific examples

[0342] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[0343] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and sends the answers to the server, which immediately scores them and provides feedback.

[0344] Furthermore, if the system's emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, it will take measures such as displaying encouraging messages and temporarily adjusting the difficulty level. Furthermore, a customized learning curriculum that is regularly updated based on User A's learning progress is generated, and specific content that should be learned next is presented.

[0345] In this way, the entire system works together to fully address the learning needs of each individual user, and by incorporating emotion recognition, it is possible to provide more effective and efficient learning support.

[0346] The processing flow will be explained below.

[0347] Step 1:

[0348] The user enters the required information on the new registration screen and presses the "Register" button.

[0349] Step 2:

[0350] The terminal transmits the input information to the server.

[0351] Step 3:

[0352] The server receives the input information, generates a new user ID, and saves the generated user ID and initial setting data in the database.

[0353] Step 4:

[0354] The user logs in, enters information on the screen for entering grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[0355] Step 5:

[0356] The terminal transmits the input initial setting information to the server.

[0357] Step 6:

[0358] The server receives the initial setting information and stores it in the user's profile data. The server prepares for the academic ability diagnostic test.

[0359] Step 7:

[0360] The user presses the "Start academic ability diagnostic test" button.

[0361] Step 8:

[0362] The terminal sends a request to start the academic ability diagnostic test to the server.

[0363] Step 9:

[0364] The server generates appropriate academic ability diagnostic questions according to the user's grade level and transmits them to the terminal.

[0365] Step 10:

[0366] The terminal displays the questions of the academic ability diagnostic test to the user.

[0367] Step 11:

[0368] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[0369] Step 12:

[0370] The terminal sequentially transmits the user's answers to the server.

[0371] Step 13:

[0372] The server scores the received answers and records whether each question is correct or incorrect.

[0373] Step 14:

[0374] The server analyzes the user's strengths and weaknesses based on all responses and generates a report of the results.

[0375] Step 15:

[0376] The terminal displays the academic ability analysis result report to the user.

[0377] Step 16:

[0378] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[0379] Step 17:

[0380] The terminal displays the generated exercises and explanations to the user.

[0381] Step 18:

[0382] The user completes the exercises and enters the answers.

[0383] Step 19:

[0384] The terminal sends the user's answer to the server.

[0385] Step 20:

[0386] The server receives the answers, scores them, determines whether the answers are correct or incorrect, adds explanations, and generates an evaluation result.

[0387] Step 21:

[0388] The terminal displays the evaluation results and explanations to the user.

[0389] Step 22:

[0390] The device sends the user's facial expressions and voice data to the emotion engine.

[0391] Step 23:

[0392] The server analyzes the user's emotional data using an emotion engine, and generates an encouraging message if the user is feeling stressed.

[0393] Step 24:

[0394] The device displays emotion-based feedback messages to the user.

[0395] Step 25:

[0396] The server records the user's progress data and periodically generates feedback and learning progress reports.

[0397] Step 26:

[0398] The device displays feedback and learning progress reports to the user.

[0399] Step 27:

[0400] The server periodically sets academic ability assessment tests for the user and notifies the user.

[0401] Step 28:

[0402] The user takes the academic assessment test and enters the answers.

[0403] Step 29:

[0404] The terminal sends the user's answer to the server.

[0405] Step 30:

[0406] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[0407] Step 31:

[0408] The server generates a curriculum optimized for the user based on the test results.

[0409] Step 32:

[0410] The device displays the generated curriculum to the user and suggests the next learning step.

[0411] The above are the specific processing steps in a system that combines emotion engines. We have described in detail what operations the server, terminal, and user perform at each step.

[0412] Example 2

[0413] 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."

[0414] Conventional learning support systems lack the ability to customize to each user's academic ability and progress, making it difficult to provide effective practice questions for specific areas of weakness. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve motivation to learn or reduce stress. This limits the effectiveness of learning and makes it difficult to provide an optimal learning environment tailored to individual needs.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0416] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness;] [means for storing the generated unique identifier and initial setting data in an information storage device; and] [means for performing an analysis of the user's academic ability and identifying areas of strength and weakness.] This makes it possible [to provide customized feedback and curriculum according to the user's individual learning needs].

[0417] "Information input from the user" refers to information provided by the system user, such as name, grade, learning goals, areas of strength and weakness, etc.

[0418] "Grade" is information that indicates the educational level or learning stage to which the system user belongs.

[0419] "Learning objectives" are the learning goals or objectives that system users want to achieve.

[0420] "Areas of expertise" refers to areas of study or subjects in which the system user has particular strengths.

[0421] "Weak areas" are areas of study or subjects that the system user is weak at.

[0422] "Initial settings" refers to basic settings that the system performs based on information input by the user.

[0423] A "unique identifier" is an ID generated to uniquely identify each user within the system.

[0424] An "information storage device" is a storage device used to store data within a system.

[0425] "Academic performance analysis" is the process by which the system evaluates a user's learning status and identifies their strengths and weaknesses.

[0426] "Practice questions" are a collection of questions provided by the system to improve the user's learning ability.

[0427] "Explanation" refers to supporting materials in the form of written, audio, or video that explain the answers and solutions to the practice problems.

[0428] "Answer" refers to the answer entered by the user to the exercise.

[0429] "Scoring" is the process of evaluating a user's answer and determining whether it is correct or not.

[0430] "Result" is information for providing feedback on the results of the scoring to the user.

[0431] "Progress data" is data that records the user's learning process and progress.

[0432] "Feedback" is reaction information including evaluation and advice regarding the user's learning activities.

[0433] A "learning plan" is a customized curriculum based on a user's learning goals and progress.

[0434] "Emotion data" is data that indicates the emotional state extracted from the user's facial expression and voice.

[0435] The "emotion engine" is a system function that analyzes the user's emotional data and evaluates the results.

[0436] A "generative AI model" is an artificial intelligence model that generates questions, explanations, and feedback that meet the user's needs.

[0437] MODE FOR CARRYING OUT THE INVENTION

[0438] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[0439] System configuration

[0440] The system consists of the following main components:

[0441] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0442] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[0443] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[0444] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[0445] Program processing overview

[0446] User registration and initial settings

[0447] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[0448] Academic ability analysis

[0449] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[0450] Creating practice questions

[0451] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[0452] Emotion recognition and feedback provision

[0453] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[0454] Creating a customized curriculum

[0455] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[0456] This series of processes enables the system to optimally respond to the individual learning needs and emotional state of each user, providing an efficient and effective learning experience.

[0457] Prompt Sentence Examples

[0458] The system performs specific processing by issuing instructions to the generative AI model using prompt sentences. Below are some examples of prompt sentences.

[0459] "Generate language exercises for elementary school students. Focus on grammar."

[0460] "Generate encouraging messages based on the user's emotional data."

[0461] "Create a customized learning curriculum based on the results of your academic ability analysis."

[0462] As a result, the system of the present invention can provide optimal learning support by taking into account the learning needs and emotional state of each individual user.

[0463] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0464] Step 1: User registration and initial setup

[0465] explanation:

[0466] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[0467] input:

[0468] User name, grade, learning goals, strengths and weaknesses

[0469] Data processing:

[0470] The server validates the received data and generates a unique identifier.

[0471] output:

[0472] User ID, initial setting data

[0473] Specific behavior:

[0474] The server receives the user data sent from the terminal, generates a new user ID, and stores it in the information storage device.

[0475] Step 2: Academic performance analysis

[0476] explanation:

[0477] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[0478] input:

[0479] User's grade, test start request, and academic ability assessment answers

[0480] Data processing:

[0481] The server generates assessment questions, receives and grades answers, and identifies areas of strength and weakness.

[0482] output:

[0483] Generated diagnostic questions and analysis of strengths and weaknesses

[0484] Specific behavior:

[0485] The server generates academic ability diagnostic questions and sends them to the terminal. The user enters the answers, and the terminal sends them to the server for grading.

[0486] Step 3: Create an exercise

[0487] explanation:

[0488] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[0489] input:

[0490] Academic ability analysis results, user answers

[0491] Data processing:

[0492] The server generates practice questions based on the results of the academic ability analysis and evaluates the received answers.

[0493] output:

[0494] Generated exercises, evaluated answers, and feedback

[0495] Specific behavior:

[0496] The server generates exercises and explanations and sends them to the device. The user answers them and sends the answers from the device to the server. The server evaluates the answers and provides feedback.

[0497] Step 4: Recognize emotions and provide feedback

[0498] explanation:

[0499] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[0500] input:

[0501] User's facial expression data, voice data

[0502] Data processing:

[0503] The server uses an emotion engine to analyze the facial expression data and voice data to identify an emotional state.

[0504] output:

[0505] Sentiment analysis results and feedback

[0506] Specific behavior:

[0507] The device captures facial and voice data and sends it to a server, which analyzes the user's emotional state and generates appropriate feedback that is sent back to the device.

[0508] Step 5: Create a customized curriculum

[0509] explanation:

[0510] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[0511] input:

[0512] User progress data, emotion data, test results

[0513] Data processing:

[0514] The server evaluates the progress data and emotional data and creates a new curriculum.

[0515] output:

[0516] Customized Curriculum

[0517] Specific behavior:

[0518] The server analyzes the progress data and emotion data, generates a customized curriculum for the user, and sends it to the device, which then displays it to the user.

[0519] Through these processing steps, the system can optimally respond to the individual learning needs and emotional state of the user, providing an efficient and effective learning experience.

[0520] (Application example 2)

[0521] 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."

[0522] Although systems that provide learning support tailored to individual academic ability already exist, there are still insufficient systems that can provide more effective learning support by recognizing the user's emotional state along with their learning progress and responding in real time.Therefore, there is a need to provide more personalized learning support that simultaneously considers the user's individual learning situation and emotional state.

[0523] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0524] In this invention, the server includes: [means for receiving user input information and initializing the grade, learning goals, and strong and weak subjects;] [means for saving the generated user ID and initial setting data in a database;] [means for performing an analysis of the user's academic ability and identifying strong and weak areas;] [means for generating practice questions and explanations focusing on weak areas;] [means for receiving the user's answers, grading, and returning the results;] [means for recording the user's progress data and generating periodic feedback;] [means for presenting a customized curriculum to the user; and] [means for recognizing the user's emotional state, analyzing and recording emotional data, and providing appropriate feedback. This makes it possible to provide study questions tailored to the user's individual academic ability, as well as to provide feedback and adjust the curriculum taking the user's emotional state into consideration.

[0525] "User" refers to the learner or individual receiving education who uses the system.

[0526] "Server" refers to the central computer system that processes and manages user input information, academic achievement data, emotional data, etc.

[0527] "Database" refers to a data repository for storing and managing user profile information, learning history, academic ability analysis results, emotional data, etc.

[0528] A "generative AI model" refers to an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, and so on.

[0529] An "emotion engine" is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[0530] "Initial setting data" refers to basic information such as grade level, learning goals, strong and weak subjects, etc., that a user enters when registering with the system.

[0531] "Academic Analysis" refers to the assessment process used to assess a user's academic ability and identify areas of strength and weakness.

[0532] "Practice Problems and Explanations" refers to information that explains problems and how to solve them, provided for the purpose of improving a user's academic ability.

[0533] "Feedback" refers to the evaluation and advice provided to a user regarding their learning progress and answer results.

[0534] "Customized curriculum" refers to an individualized learning plan that is tailored and optimized based on the user's academic ability and emotional state.

[0535] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, voice, actions, etc.

[0536] "Progress Data" means records and data relating to a User's learning progress.

[0537] The system for implementing this invention comprises a user terminal, a server, a database, a generative AI model, and an emotion engine.

[0538] The user terminal is a device such as a smartphone, tablet, or PC that the user uses to access the system. The server is a central computer system that processes and manages user input information, academic achievement data, emotional data, etc. The database is a data repository that stores and manages user profile information, learning history, academic achievement analysis results, emotional data, etc.

[0539] The generative AI model is an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, etc. The emotion engine is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[0540] Program Processing Overview

[0541] The server receives input from the user and initializes the grade, learning goals, and strong and weak subjects. This initialization data is stored in a database. Next, it diagnoses the user's academic ability and identifies their strong and weak areas. It generates practice questions and explanations that focus on the weak areas, and when the user answers them, it grades the results and provides feedback. Feedback is generated periodically to effectively support the user's academic improvement.

[0542] Furthermore, the server records the user's progress data and presents a customized curriculum based on the progress. The emotion engine analyzes the user's facial and voice data to recognize their emotional state. Based on this, the server can provide appropriate feedback and encouraging messages and adjust the learning curriculum.

[0543] Specific example explanation

[0544] For example, if User A, a fifth-grader, uses this system, he or she will initially enter their grade, learning goals, favorite subject (math), and weak subject (Japanese). The system generates a user ID based on this information and stores the information in a database. Next, it conducts an academic ability assessment, and if it is determined that User A has a weakness in Japanese grammar, for example, appropriate practice questions and explanations will be generated.

[0545] While User A is working on a problem, if the emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, the server generates a prompt sentence like the one below and provides appropriate feedback.

[0546] Example prompt sentence:

[0547] User A's stressed facial expression was detected.

[0548] Please choose the appropriate response from the options below:

[0549] 1. Display encouraging messages

[0550] 2. Slow down your learning pace

[0551] 3. Offer a temporary break

[0552] Based on this prompt, the server provides appropriate feedback to User A and adjusts the learning curriculum to maximize the user's learning effectiveness.

[0553] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0554] Step 1:

[0555] The user enters the initial settings.

[0556] The user inputs initial setting data such as grade, learning goal, strong and weak subjects into the terminal and transmits it to the server.

[0557] Input: Grade, learning goals, strong subjects, weak subjects

[0558] Data processing and calculation: The server generates a user ID based on the received data and saves the initial setting data in the database.

[0559] Output: User ID, initial setting data saved

[0560] Step 2:

[0561] The server runs the academic achievement test.

[0562] When a user starts the academic ability diagnostic test, the server generates a diagnostic test appropriate for the user's grade and sends it to the terminal. The user answers the questions and sends the results back to the server.

[0563] Input: User ID, grade

[0564] Data processing and calculation: Evaluate the user's academic ability and identify areas of strength and weakness.

[0565] Output: Academic achievement evaluation results

[0566] Step 3:

[0567] The server generates individual exercises and explanations.

[0568] Based on the results of the academic ability assessment, the server generates practice questions and explanations that focus on the user's weak areas and sends them to the terminal.

[0569] Input: Academic achievement evaluation results

[0570] Data processing and calculation: Automatically generate practice questions and explanations using a generative AI model.

[0571] Output: Exercises, explanations

[0572] Step 4:

[0573] The user answers the exercises.

[0574] The user answers the exercises presented to them and sends the results to the server via their terminal.

[0575] Input: User's answer

[0576] Data processing and calculation: The server grades the answers, evaluates the results, and generates feedback.

[0577] Output: Marking results, feedback

[0578] Step 5:

[0579] The server tracks the user's progress and provides feedback.

[0580] Once the user has completed the exercises, the server records progress data and provides periodically generated feedback to the user.

[0581] Input: Marking results, progress data

[0582] Data processing and calculation: Feedback is generated from progress data and scoring results and sent to the user.

[0583] Output: Feedback

[0584] Step 6:

[0585] The device uses an emotion engine to recognize the user's emotional state.

[0586] While the user is learning, the device uses a camera and microphone to capture the user's facial expressions and voice, which are then sent to the emotion engine. The server analyzes these and recognizes the user's emotional state.

[0587] Input: facial expression data, voice data

[0588] Data processing and calculation: The emotion engine analyzes the data and identifies the emotional state.

[0589] Output: Emotional state

[0590] Step 7:

[0591] The server adjusts the feedback based on the emotional state.

[0592] Once the user's emotional state is recognized, the server can adjust the feedback and learning curriculum accordingly, for example, sending encouraging messages if the user is feeling stressed.

[0593] Input: Emotional state, feedback

[0594] Data processing and calculation: Adjust existing feedback and curriculum according to emotional states.

[0595] Output: Adjusted feedback and curriculum

[0596] Example prompt sentence:

[0597] User A's stressed facial expression was detected.

[0598] Please choose the appropriate response from the options below:

[0599] 1. Display encouraging messages

[0600] 2. Slow down your learning pace

[0601] 3. Offer a temporary break

[0602] This series of processes enables individual learning support and appropriate feedback based on emotions to be provided to the user.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] [Second embodiment]

[0607] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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).

[0613] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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."

[0619] This invention is a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, and manages learning progress.

[0620] System configuration

[0621] The system consists of the following main components:

[0622] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0623] 2. Server: Performs database management, generating AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[0624] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[0625] Program processing overview

[0626] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[0627] User registration and initial settings

[0628] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[0629] Academic ability analysis

[0630] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[0631] Creating practice questions

[0632] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[0633] Providing feedback

[0634] The server evaluates the user's progress based on the results of the exercises and generates personalized feedback, which the device displays to the user and suggests the next learning step.

[0635] Creating a customized curriculum

[0636] The server periodically sets tests to evaluate the user's progress. When the user takes the test, the server creates a customized learning curriculum based on the test results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[0637] Specific examples

[0638] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[0639] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and submits the results to the server, which immediately scores them and provides feedback. Furthermore, a regularly updated customized learning curriculum is generated based on User A's learning progress, providing specific suggestions for what to study next.

[0640] In this way, the entire system works in cooperation to fully meet the learning needs of each user and provide efficient and effective learning support.

[0641] The processing flow will be explained below.

[0642] Step 1:

[0643] The user enters the required information (user name, password, grade, email address) on the new registration screen and presses the "Register" button.

[0644] Step 2:

[0645] The terminal transmits the input information to the server.

[0646] Step 3:

[0647] The server generates a new user ID based on the received data and saves the initial setting data in the database.

[0648] Step 4:

[0649] The user logs in, enters information on the screen where they can enter their grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[0650] Step 5:

[0651] The terminal transmits the input initial setting information to the server.

[0652] Step 6:

[0653] The server receives the initial setting information, stores it in the user's profile data, and simultaneously prepares to start the academic ability diagnostic test.

[0654] Step 7:

[0655] The user presses the "Start academic ability diagnostic test" button.

[0656] Step 8:

[0657] The terminal transmits a request to start the academic ability diagnostic test to the server.

[0658] Step 9:

[0659] The server generates appropriate academic ability diagnostic questions according to the user's grade level and sends them to the terminal.

[0660] Step 10:

[0661] The terminal displays the questions of the academic ability diagnostic test to the user.

[0662] Step 11:

[0663] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[0664] Step 12:

[0665] The terminal sequentially transmits the user's answers to the server.

[0666] Step 13:

[0667] The server scores the received answers and records whether each question is correct or incorrect.

[0668] Step 14:

[0669] Based on all the responses, the server analyzes the user's strengths and weaknesses and generates a report of the results.

[0670] Step 15:

[0671] The terminal displays the academic ability analysis result report to the user.

[0672] Step 16:

[0673] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[0674] Step 17:

[0675] The terminal displays the generated exercises and explanations to the user.

[0676] Step 18:

[0677] The user completes the exercises and enters their answers.

[0678] Step 19:

[0679] The terminal transmits the user's answer to the server.

[0680] Step 20:

[0681] The server receives the answers, scores them, determines whether they are correct or incorrect, adds explanations, and generates an evaluation result.

[0682] Step 21:

[0683] The terminal displays the evaluation results and explanations to the user.

[0684] Step 22:

[0685] The server records the user's progress data and periodically generates feedback and learning progress reports.

[0686] Step 23:

[0687] The device displays feedback and learning progress reports to the user.

[0688] Step 24:

[0689] The server periodically sets up an academic ability assessment test for the user and notifies the user.

[0690] Step 25:

[0691] The user takes an academic assessment test and enters their answers.

[0692] Step 26:

[0693] The terminal transmits the user's answer to the server.

[0694] Step 27:

[0695] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[0696] Step 28:

[0697] The server generates a curriculum optimized for the user based on the test results.

[0698] Step 29:

[0699] The terminal displays the generated curriculum to the user and suggests the next learning stage.

[0700] The above are the specific processing steps for carrying out the invention. The operations performed by the server, terminal, and user at each step are described in detail.

[0701] Example 1

[0702] 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."

[0703] Conventional learning support systems have had the problem of being difficult to provide effective learning support because they are unable to respond to the academic ability and progress of individual users. Furthermore, they are unable to provide appropriate practice problems to overcome weaknesses in specific areas. Furthermore, they are inadequate in providing customized feedback and creating learning plans based on the user's learning progress, making it difficult to expect improvements in learning efficiency.

[0704] 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.

[0705] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness; [means for saving the generated user identification information and initial setting data in a database; [means for conducting a user's academic ability diagnostic test and evaluating academic ability; [means for identifying the user's areas of strength and weakness; [means for using a generative AI model to generate practice questions and explanations focusing on areas of weakness; [means for receiving the user's answers, grading and returning the results; [means for recording the user's progress and generating individual feedback; and [means for presenting a customized study plan to the user.] This enables learning support tailored to each individual user, effectively supporting the user's improvement in academic ability.

[0706] "User identification information" is information generated to uniquely identify each individual user.

[0707] "Initial setting data" refers to data such as grade, learning goals, strong subjects, and weak subjects that are input by the user when registering for the first time.

[0708] A "database" is a system for storing user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[0709] An "academic ability diagnostic test" is a collection of questions used to evaluate a user's current academic ability.

[0710] A "generative AI model" is an artificial intelligence model that generates appropriate practice questions and explanations based on the user's weak areas.

[0711] "Practice questions" are questions that are given with the aim of improving the user's academic ability.

[0712] "Feedback" refers to notifying users of evaluations and areas for improvement based on their learning outcomes and progress.

[0713] A "customized study plan" is a study schedule that is individually created based on the user's academic ability and progress.

[0714] This invention provides a learning support system equipped with a generative AI model. It analyzes the user's academic ability and provides individually optimized learning plans and feedback, thereby achieving efficient and effective learning support.

[0715] System configuration

[0716] The system consists of the following main components:

[0717] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or personal computer.

[0718] 2. Server: Performs database management, processing using generative AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[0719] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, learning curriculum, etc.

[0720] User registration and initial settings

[0721] The process begins when the user enters information such as name, grade, learning goals, and areas of strength and weakness on the new registration screen. The device sends this information to the server, which then generates new user identification information based on the received information. The generated identification information and initial setting data are stored in a database.

[0722] Academic ability analysis

[0723] When a user starts an academic ability diagnostic test, the device sends a request to the server. The server uses a generative AI model to create appropriate academic ability diagnostic questions based on the user's grade level, and then sends them to the device. The user's answers are sent via the device to the server, which automatically scores them and identifies the user's strengths and weaknesses.

[0724] Creating practice questions

[0725] Based on the results of the academic ability assessment, the server uses a generative AI model to generate practice questions that focus on the user's weak areas. The generated questions are sent to the device and presented to the user. The user's answers are sent via the device to the server, which evaluates them and generates feedback.

[0726] Providing feedback

[0727] Based on the results of the exercises the user answers, the server generates personalized feedback, which the device displays to the user and suggests the next steps to take. The feedback includes detailed evaluations and advice, with the aim of deepening the user's understanding.

[0728] Creating a customized curriculum

[0729] The server periodically evaluates the user's progress and sets new tests as needed. Based on the user's test results, a customized learning plan is created using a generative AI model. The generated curriculum is sent to the device and presented to the user.

[0730] Specific use cases

[0731] For example, consider the case where User A, a fifth-grader in elementary school, newly registers with the system. User A enters information such as his name, grade, learning goals, favorite subject (math), and weak subject (Japanese). This information is sent from the terminal to the server, which generates new user identification information and stores it in a database. User A then begins an academic ability diagnostic test, and the server generates appropriate questions and sends them to the terminal. User A's answers are graded by the server, and grammar questions that User A is particularly weak at are extracted.

[0732] The server automatically generates practice questions focusing on weak grammar points and provides them to User A via the terminal. User A answers these questions and submits them to the server again, where the server evaluates the answers and generates feedback, including suggestions for improvement and additional practice questions.

[0733] Examples of prompt statements

[0734] "Please generate grammar exercises for a fifth-grade elementary school student. The user feels that he or she is not good at grammar."

[0735] Based on this prompt, the generative AI model provides appropriate practice questions for User A. This allows the entire system to work together to meet the user's learning needs and provide efficient and effective learning support.

[0736] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0737] Step 1:

[0738] The user enters the required information (name, grade, learning goals, areas of strength and weakness, etc.) on the new registration screen.

[0739] Input: User's personal and study-related information

[0740] Output: User input data

[0741] Specific behavior: The user enters information into the input form and presses the "Submit" button.

[0742] Step 2:

[0743] The terminal transmits the input user information to the server.

[0744] Input: User-entered data

[0745] Output: Data sent to the server

[0746] Specific operation: The terminal sends the received user input data to the server using the HTTPS protocol.

[0747] Step 3:

[0748] The server generates new user identification information based on the received information and stores the initial setting data in a database.

[0749] Input: Data to send to the server

[0750] Output: User identity and database updates

[0751] Specific operation: The server generates user identification information from the received data and executes an SQL query to store it in a database.

[0752] Step 4:

[0753] The server generates an academic ability diagnostic test, selects appropriate questions based on grade information, and sends them to the terminal.

[0754] Input: User's grade information and initial setting data

[0755] Output: Academic ability diagnostic test

[0756] Specific operation: The server selects appropriate questions from the question bank based on grade information, and if necessary, generates new questions using a generative AI model and sends them to the terminal.

[0757] Step 5:

[0758] The user takes an academic ability diagnostic test and transmits the answers to the server via the terminal.

[0759] Input: Academic ability diagnostic test and user answers

[0760] Output: User answer data

[0761] Specific operation: The user answers the diagnostic test using the terminal and presses the send answer button, which sends the answer data to the server.

[0762] Step 6:

[0763] The server automatically scores the user's answer data and identifies areas of strength and weakness.

[0764] Input: User answer data

[0765] Output: Analysis of strengths and weaknesses

[0766] Specific operation: The server automatically scores the received answer data and analyzes the areas of strength and weakness using a specific algorithm.

[0767] Step 7:

[0768] The server uses a generative AI model to generate practice questions and explanations based on the user's weak areas and sends them to the device.

[0769] Input: Analysis results of strengths and weaknesses

[0770] Output: Exercises and explanations

[0771] Specific operation: The server uses the generative AI model to generate questions that focus on the user's weak areas and sends them to the device.

[0772] Step 8:

[0773] The user answers the exercises and sends the results from the terminal to the server.

[0774] Input: Exercises and user answers

[0775] Output: User answer data

[0776] Specific operation: The user answers the practice questions and sends the results to the server using the send button on the device.

[0777] Step 9:

[0778] The server evaluates the practice question answer data and generates feedback.

[0779] Input: User answer data

[0780] Output: Feedback

[0781] Specific operation: The server evaluates the answer data and uses a generative AI model to create detailed feedback for the user and send it to the device.

[0782] Step 10:

[0783] A server periodically evaluates the user's progress data and generates a customized learning curriculum that is regularly updated.

[0784] Input: User progress data

[0785] Output: Customized learning curriculum

[0786] Specific operation: The server evaluates the user's progress data, uses a generative AI model to generate an individually optimized learning curriculum, and sends it to the device.

[0787] Step 11:

[0788] The terminal displays the customized learning curriculum to the user.

[0789] Input: Customized Learning Curriculum

[0790] Output: Presentation of study schedule

[0791] Specific operation: The terminal displays the received curriculum to the user and indicates the specific content that should be studied next.

[0792] In this way, the entire system cooperates to provide effective learning support that meets the user's learning needs.

[0793] (Application example 1)

[0794] 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."

[0795] Conventional factory worker training systems have made it difficult to provide effective training programs tailored to the skill level of each worker. Standardized training programs cannot adequately reflect the actual abilities and progress of workers, resulting in reduced training efficiency. Customizing training content also requires a significant amount of time and effort, making it difficult to manage progress and provide feedback in real time.

[0796] 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.

[0797] In this invention, the server includes: means for receiving input information from a user and initializing the installation year, goals, strengths and weaknesses; means for saving the generated account ID and initial setting data in a database; means for performing a skill evaluation of the worker and identifying strengths and weaknesses; means for generating training modules and explanations focusing on the weaknesses; means for receiving the worker's answers, scoring, and returning the results; means for recording the worker's progress data and periodically generating feedback; means for presenting a customized training program to the worker; means for generating optimal training content for the worker using a generative AI model; and means for inputting prompts to the generative AI model and outputting the required training content. This enables the provision of an effective training program tailored to the skill level of each worker.

[0798] "User input" is data that operators use to communicate initial setup and individual training needs to the system.

[0799] "Year of installation" refers to the year in which the worker began performing the work.

[0800] "Goal" refers to a specific educational or skill-building goal that a worker seeks to achieve.

[0801] "Area of ​​expertise" refers to an area in which a worker has relatively high skills or knowledge.

[0802] "Weak areas" refer to areas in which a worker has relatively low skills or knowledge.

[0803] An "account ID" is an identifier generated to uniquely identify a worker within the system.

[0804] "Initial setting data" is data that collects setting information provided when an operator starts using the system.

[0805] "Skills assessment" is the process of analyzing a worker's current skill level and identifying their strengths and weaknesses.

[0806] An "educational module" is an educational unit that includes a series of instructional content for acquiring specific skills or knowledge.

[0807] "Explanation" refers to detailed explanatory text and illustrations that allow workers to understand the content contained in the training module.

[0808] An "answer" is a response that a worker submits to an educational module or test.

[0809] "Scoring" is the process of evaluating a worker's answers to determine their accuracy.

[0810] "Results" refers to the evaluation and feedback generated based on the worker's answers.

[0811] "Progress data" is data that records the progress of a worker's education and training.

[0812] "Feedback" refers to advice and evaluation provided to workers regarding their education and training progress.

[0813] A "training program" is a set of educational content customized to improve a worker's skills.

[0814] A "generative AI model" is an artificial intelligence model that is trained to perform a specific task based on large amounts of data.

[0815] A "prompt sentence" is an instruction sentence input to a generative AI model to instruct the worker on how to generate training content.

[0816] This invention relates to a head-mounted display (HMD) application for supporting worker training in factories and a training content generation system that uses a generative AI model. This system provides appropriate training programs according to the skill level of each worker, achieving efficient and effective training.

[0817] System configuration

[0818] The system consists of the following main components:

[0819] 1. User terminal: A head-mounted display (HMD) that allows workers to access the system and receive training content.

[0820] 2. Server: Performs database management, operation of generative AI models, skill evaluation, educational module generation, answer evaluation, and feedback provision.

[0821] 3. Database: Stores worker profile information, skill evaluation results, education history, training programs, etc.

[0822] Specific operation of the system

[0823] User registration and initial settings

[0824] When the user enters the required information (year of installation, goals, areas of strength and weakness) on the new registration screen, the device sends the data to the server. The server generates a new account ID based on the received data and saves the initial setting data in the database.

[0825] Skills Evaluation

[0826] When a user starts a skills assessment test, the device sends the request to the server. The server generates skills assessment questions according to the worker's role and sends them to the device. When the worker solves the questions and submits their answers, the server scores them and identifies the worker's strengths and weaknesses.

[0827] Creating an Educational Module

[0828] Based on the results of the skill assessment, the server generates an educational module and explanations that focus on the worker's weak areas. The terminal receives this and presents it to the worker. The user studies the educational module and sends the answer results from the terminal to the server. The server evaluates the answer and returns the results and feedback.

[0829] Providing feedback

[0830] The server evaluates the worker's progress based on the results of the training module and generates individual feedback, which is displayed to the worker on the terminal and suggests the next training step.

[0831] Customize your training program

[0832] The server periodically sets tests to evaluate the worker's progress. When the user takes the test, the server creates a customized training program based on the results and sends it to the terminal. The terminal then presents the training program to the worker, supporting their daily education.

[0833] Technology used

[0834] This system uses TensorFlow and Keras to build a generative AI model that evaluates worker skills and generates optimal training programs based on large amounts of data. It also uses an SQL database system for database management, processing and analyzing data in real time.

[0835] Specific examples

[0836] For example, when a new worker A is assigned to a factory, he or she is registered in the system. The initial setup involves entering the year of installation, training goals, areas of strength (e.g., machine operation), and areas of weakness (e.g., safety management). The system receives this information and generates an optimal training program based on it.

[0837] After taking the skill assessment test, the system evaluates Worker A's current skill level and generates a training module that focuses on his weaknesses. It then inputs the following prompt sentence into the generative AI model:

[0838] "Please assess the skill level of your workers and suggest appropriate training programs. The dataset is as follows: [example data]"

[0839] Based on this prompt, the most appropriate training content is generated and displayed on the HMD of Worker A. This allows Worker A to receive the training necessary to improve his or her skills in real time.

[0840] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0841] Step 1:

[0842] The user enters the necessary information (year of establishment, goals, areas of strength, areas of weakness) on the new registration screen. The terminal sends the data to the server.

[0843] Input: Year of establishment, goals, areas of strength and weakness information

[0844] Output: Registration information sent to the server

[0845] Specific operation: The user inputs information using the HMD's user interface and presses the send button.

[0846] Step 2:

[0847] The server generates a new account ID based on the received data and stores the initial setting data in the database.

[0848] Input: Registration information

[0849] Output: Generated account ID and initial setting data

[0850] Specific operation: The server accesses the database, creates a new record, and automatically generates an account ID.

[0851] Step 3:

[0852] When a user starts a skill assessment test, the terminal sends the request to the server.

[0853] Input: Skills Assessment Test Request

[0854] Output: Request sent to the server

[0855] Specific operation: The user presses the evaluation test start button on the HMD.

[0856] Step 4:

[0857] The server generates skill evaluation questions according to the worker's role and sends them to the terminal.

[0858] Input: Role information

[0859] Output: Generated skill assessment questions

[0860] Specific operation: The server uses the generative AI model to generate an appropriate problem set and sends it to the device.

[0861] Step 5:

[0862] The user solves the problem and sends the answer from the terminal to the server.

[0863] Input: Worker's response

[0864] Output: The answer sent to the server

[0865] Specific operation: The user solves the problem using the HMD and presses the answer button to submit the result.

[0866] Step 6:

[0867] The server scores the answers and identifies the worker's strengths and weaknesses.

[0868] Input: Answer data

[0869] Output: Identification of strengths and weaknesses

[0870] What happens: The server uses a scoring algorithm to evaluate and identify answers.

[0871] Step 7:

[0872] Based on the results of the skills assessment, the server generates educational modules and explanations that focus on the worker's areas of weakness.

[0873] Input: Results of identifying strengths and weaknesses

[0874] Output: Educational modules and descriptions

[0875] Specific operation: The server inputs a prompt sentence into the generative AI model and generates educational content.

[0876] Step 8:

[0877] The server sends the generated educational module to the terminal, where the user receives it and begins learning.

[0878] Input: Education Module

[0879] Output: Educational module sent to the device

[0880] Specific operation: The server sends educational content to the terminal and it is displayed on the HMD.

[0881] Step 9:

[0882] The user studies the educational module and sends the answers from the terminal to the server.

[0883] Input: Learning results and answers

[0884] Output: Learning results and answers sent to the server

[0885] Specific operation: The user uses the HMD to learn, input and submit the results.

[0886] Step 10:

[0887] The server evaluates the answers and generates results and feedback.

[0888] Input: Learning results and answers

[0889] Output: Evaluation results and feedback

[0890] Specific operation: The server evaluates the answer using an answer evaluation algorithm and generates feedback.

[0891] Step 11:

[0892] The server evaluates the worker's progress based on the results of the training module and generates individual feedback.

[0893] Input: Answer evaluation result

[0894] Output: Individual feedback

[0895] What happens: The server analyzes the progress data and generates feedback.

[0896] Step 12:

[0897] The server creates a customized training program and sends it to the terminal, which presents it to the user.

[0898] Input: Individual feedback

[0899] Output: Customized training program

[0900] Specific operation: The server generates an educational program using the generative AI model and sends it to the device. It is then displayed on the HMD.

[0901] An example of a specific prompt would be, "Please assess the skill level of workers and suggest appropriate training programs. The dataset is as follows: [Example data]," and you can get output results from the generative AI model.

[0902] 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.

[0903] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[0904] System configuration

[0905] The system consists of the following main components:

[0906] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[0907] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[0908] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[0909] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[0910] Program processing overview

[0911] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[0912] User registration and initial settings

[0913] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[0914] Academic ability analysis

[0915] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[0916] Creating practice questions

[0917] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[0918] Emotion recognition and feedback provision

[0919] The device sends the user's facial and voice data to the emotion engine, which then uses this data to recognize the user's emotional state. After the user completes the exercise, the emotion data is also analyzed and appropriate feedback is generated. For example, if the user looks tired, the system may respond by displaying an encouraging message.

[0920] Creating a customized curriculum

[0921] The server periodically sets tests to evaluate the user's progress and emotional data. After the user takes the test, the server creates a customized learning curriculum based on the results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[0922] Specific examples

[0923] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[0924] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and sends the answers to the server, which immediately scores them and provides feedback.

[0925] Furthermore, if the system's emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, it will take measures such as displaying encouraging messages and temporarily adjusting the difficulty level. Furthermore, a customized learning curriculum that is regularly updated based on User A's learning progress is generated, and specific content that should be learned next is presented.

[0926] In this way, the entire system works together to fully address the learning needs of each individual user, and by incorporating emotion recognition, it is possible to provide more effective and efficient learning support.

[0927] The processing flow will be explained below.

[0928] Step 1:

[0929] The user enters the required information on the new registration screen and presses the "Register" button.

[0930] Step 2:

[0931] The terminal transmits the input information to the server.

[0932] Step 3:

[0933] The server receives the input information, generates a new user ID, and saves the generated user ID and initial setting data in the database.

[0934] Step 4:

[0935] The user logs in, enters information on the screen for entering grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[0936] Step 5:

[0937] The terminal transmits the input initial setting information to the server.

[0938] Step 6:

[0939] The server receives the initial setting information and stores it in the user's profile data. The server prepares for the academic ability diagnostic test.

[0940] Step 7:

[0941] The user presses the "Start academic ability diagnostic test" button.

[0942] Step 8:

[0943] The terminal sends a request to start the academic ability diagnostic test to the server.

[0944] Step 9:

[0945] The server generates appropriate academic ability diagnostic questions according to the user's grade level and transmits them to the terminal.

[0946] Step 10:

[0947] The terminal displays the questions of the academic ability diagnostic test to the user.

[0948] Step 11:

[0949] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[0950] Step 12:

[0951] The terminal sequentially transmits the user's answers to the server.

[0952] Step 13:

[0953] The server scores the received answers and records whether each question is correct or incorrect.

[0954] Step 14:

[0955] The server analyzes the user's strengths and weaknesses based on all responses and generates a report of the results.

[0956] Step 15:

[0957] The terminal displays the academic ability analysis result report to the user.

[0958] Step 16:

[0959] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[0960] Step 17:

[0961] The terminal displays the generated exercises and explanations to the user.

[0962] Step 18:

[0963] The user completes the exercises and enters the answers.

[0964] Step 19:

[0965] The terminal sends the user's answer to the server.

[0966] Step 20:

[0967] The server receives the answers, scores them, determines whether the answers are correct or incorrect, adds explanations, and generates an evaluation result.

[0968] Step 21:

[0969] The terminal displays the evaluation results and explanations to the user.

[0970] Step 22:

[0971] The device sends the user's facial expressions and voice data to the emotion engine.

[0972] Step 23:

[0973] The server analyzes the user's emotional data using an emotion engine, and generates an encouraging message if the user is feeling stressed.

[0974] Step 24:

[0975] The device displays emotion-based feedback messages to the user.

[0976] Step 25:

[0977] The server records the user's progress data and periodically generates feedback and learning progress reports.

[0978] Step 26:

[0979] The device displays feedback and learning progress reports to the user.

[0980] Step 27:

[0981] The server periodically sets academic ability assessment tests for the user and notifies the user.

[0982] Step 28:

[0983] The user takes the academic assessment test and enters the answers.

[0984] Step 29:

[0985] The terminal sends the user's answer to the server.

[0986] Step 30:

[0987] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[0988] Step 31:

[0989] The server generates a curriculum optimized for the user based on the test results.

[0990] Step 32:

[0991] The device displays the generated curriculum to the user and suggests the next learning step.

[0992] The above are the specific processing steps in a system that combines emotion engines. We have described in detail what operations the server, terminal, and user perform at each step.

[0993] Example 2

[0994] 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."

[0995] Conventional learning support systems lack the ability to customize to each user's academic ability and progress, making it difficult to provide effective practice questions for specific areas of weakness. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve motivation to learn or reduce stress. This limits the effectiveness of learning and makes it difficult to provide an optimal learning environment tailored to individual needs.

[0996] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0997] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness;] [means for storing the generated unique identifier and initial setting data in an information storage device; and] [means for performing an analysis of the user's academic ability and identifying areas of strength and weakness.] This makes it possible [to provide customized feedback and curriculum according to the user's individual learning needs].

[0998] "Information input from the user" refers to information provided by the system user, such as name, grade, learning goals, areas of strength and weakness, etc.

[0999] "Grade" is information that indicates the educational level or learning stage to which the system user belongs.

[1000] "Learning objectives" are the learning goals or objectives that system users want to achieve.

[1001] "Areas of expertise" refers to areas of study or subjects in which the system user has particular strengths.

[1002] "Weak areas" are areas of study or subjects that the system user is weak at.

[1003] "Initial settings" refers to basic settings that the system performs based on information input by the user.

[1004] A "unique identifier" is an ID generated to uniquely identify each user within the system.

[1005] An "information storage device" is a storage device used to store data within a system.

[1006] "Academic performance analysis" is the process by which the system evaluates a user's learning status and identifies their strengths and weaknesses.

[1007] "Practice questions" are a collection of questions provided by the system to improve the user's learning ability.

[1008] "Explanation" refers to supporting materials in the form of written, audio, or video that explain the answers and solutions to the practice problems.

[1009] "Answer" refers to the answer entered by the user to the exercise.

[1010] "Scoring" is the process of evaluating a user's answer and determining whether it is correct or not.

[1011] "Result" is information for providing feedback on the results of the scoring to the user.

[1012] "Progress data" is data that records the user's learning process and progress.

[1013] "Feedback" is reaction information including evaluation and advice regarding the user's learning activities.

[1014] A "learning plan" is a customized curriculum based on a user's learning goals and progress.

[1015] "Emotion data" is data that indicates the emotional state extracted from the user's facial expression and voice.

[1016] The "emotion engine" is a system function that analyzes the user's emotional data and evaluates the results.

[1017] A "generative AI model" is an artificial intelligence model that generates questions, explanations, and feedback that meet the user's needs.

[1018] MODE FOR CARRYING OUT THE INVENTION

[1019] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[1020] System configuration

[1021] The system consists of the following main components:

[1022] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1023] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[1024] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[1025] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[1026] Program processing overview

[1027] User registration and initial settings

[1028] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[1029] Academic ability analysis

[1030] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[1031] Creating practice questions

[1032] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[1033] Emotion recognition and feedback provision

[1034] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[1035] Creating a customized curriculum

[1036] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[1037] This series of processes enables the system to optimally respond to the individual learning needs and emotional state of each user, providing an efficient and effective learning experience.

[1038] Prompt Sentence Examples

[1039] The system performs specific processing by issuing instructions to the generative AI model using prompt sentences. Below are some examples of prompt sentences.

[1040] "Generate language exercises for elementary school students. Focus on grammar."

[1041] "Generate encouraging messages based on the user's emotional data."

[1042] "Create a customized learning curriculum based on the results of your academic ability analysis."

[1043] As a result, the system of the present invention can provide optimal learning support by taking into account the learning needs and emotional state of each individual user.

[1044] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1045] Step 1: User registration and initial setup

[1046] explanation:

[1047] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[1048] input:

[1049] User name, grade, learning goals, strengths and weaknesses

[1050] Data processing:

[1051] The server validates the received data and generates a unique identifier.

[1052] output:

[1053] User ID, initial setting data

[1054] Specific behavior:

[1055] The server receives the user data sent from the terminal, generates a new user ID, and stores it in the information storage device.

[1056] Step 2: Academic performance analysis

[1057] explanation:

[1058] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[1059] input:

[1060] User's grade, test start request, and academic ability assessment answers

[1061] Data processing:

[1062] The server generates assessment questions, receives and grades answers, and identifies areas of strength and weakness.

[1063] output:

[1064] Generated diagnostic questions and analysis of strengths and weaknesses

[1065] Specific behavior:

[1066] The server generates academic ability diagnostic questions and sends them to the terminal. The user enters the answers, and the terminal sends them to the server for grading.

[1067] Step 3: Create an exercise

[1068] explanation:

[1069] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[1070] input:

[1071] Academic ability analysis results, user answers

[1072] Data processing:

[1073] The server generates practice questions based on the results of the academic ability analysis and evaluates the received answers.

[1074] output:

[1075] Generated exercises, evaluated answers, and feedback

[1076] Specific behavior:

[1077] The server generates exercises and explanations and sends them to the device. The user answers them and sends the answers from the device to the server. The server evaluates the answers and provides feedback.

[1078] Step 4: Recognize emotions and provide feedback

[1079] explanation:

[1080] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[1081] input:

[1082] User's facial expression data, voice data

[1083] Data processing:

[1084] The server uses an emotion engine to analyze the facial expression data and voice data to identify an emotional state.

[1085] output:

[1086] Sentiment analysis results and feedback

[1087] Specific behavior:

[1088] The device captures facial and voice data and sends it to a server, which analyzes the user's emotional state and generates appropriate feedback that is sent back to the device.

[1089] Step 5: Create a customized curriculum

[1090] explanation:

[1091] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[1092] input:

[1093] User progress data, emotion data, test results

[1094] Data processing:

[1095] The server evaluates the progress data and emotional data and creates a new curriculum.

[1096] output:

[1097] Customized Curriculum

[1098] Specific behavior:

[1099] The server analyzes the progress data and emotion data, generates a customized curriculum for the user, and sends it to the device, which then displays it to the user.

[1100] Through these processing steps, the system can optimally respond to the individual learning needs and emotional state of the user, providing an efficient and effective learning experience.

[1101] (Application example 2)

[1102] 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."

[1103] Although systems that provide learning support tailored to individual academic ability already exist, there are still insufficient systems that can provide more effective learning support by recognizing the user's emotional state along with their learning progress and responding in real time.Therefore, there is a need to provide more personalized learning support that simultaneously considers the user's individual learning situation and emotional state.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1105] In this invention, the server includes: [means for receiving user input information and initializing the grade, learning goals, and strong and weak subjects;] [means for saving the generated user ID and initial setting data in a database;] [means for performing an analysis of the user's academic ability and identifying strong and weak areas;] [means for generating practice questions and explanations focusing on weak areas;] [means for receiving the user's answers, grading, and returning the results;] [means for recording the user's progress data and generating periodic feedback;] [means for presenting a customized curriculum to the user; and] [means for recognizing the user's emotional state, analyzing and recording emotional data, and providing appropriate feedback. This makes it possible to provide study questions tailored to the user's individual academic ability, as well as to provide feedback and adjust the curriculum taking the user's emotional state into consideration.

[1106] "User" refers to the learner or individual receiving education who uses the system.

[1107] "Server" refers to the central computer system that processes and manages user input information, academic achievement data, emotional data, etc.

[1108] "Database" refers to a data repository for storing and managing user profile information, learning history, academic ability analysis results, emotional data, etc.

[1109] A "generative AI model" refers to an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, and so on.

[1110] An "emotion engine" is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[1111] "Initial setting data" refers to basic information such as grade level, learning goals, strong and weak subjects, etc., that a user enters when registering with the system.

[1112] "Academic Analysis" refers to the assessment process used to assess a user's academic ability and identify areas of strength and weakness.

[1113] "Practice Problems and Explanations" refers to information that explains problems and how to solve them, provided for the purpose of improving a user's academic ability.

[1114] "Feedback" refers to the evaluation and advice provided to a user regarding their learning progress and answer results.

[1115] "Customized curriculum" refers to an individualized learning plan that is tailored and optimized based on the user's academic ability and emotional state.

[1116] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, voice, actions, etc.

[1117] "Progress Data" means records and data relating to a User's learning progress.

[1118] The system for implementing this invention comprises a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1119] The user terminal is a device such as a smartphone, tablet, or PC that the user uses to access the system. The server is a central computer system that processes and manages user input information, academic achievement data, emotional data, etc. The database is a data repository that stores and manages user profile information, learning history, academic achievement analysis results, emotional data, etc.

[1120] The generative AI model is an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, etc. The emotion engine is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[1121] Program Processing Overview

[1122] The server receives input from the user and initializes the grade, learning goals, and strong and weak subjects. This initialization data is stored in a database. Next, it diagnoses the user's academic ability and identifies their strong and weak areas. It generates practice questions and explanations that focus on the weak areas, and when the user answers them, it grades the results and provides feedback. Feedback is generated periodically to effectively support the user's academic improvement.

[1123] Furthermore, the server records the user's progress data and presents a customized curriculum based on the progress. The emotion engine analyzes the user's facial and voice data to recognize their emotional state. Based on this, the server can provide appropriate feedback and encouraging messages and adjust the learning curriculum.

[1124] Specific example explanation

[1125] For example, if User A, a fifth-grader, uses this system, he or she will initially enter their grade, learning goals, favorite subject (math), and weak subject (Japanese). The system generates a user ID based on this information and stores the information in a database. Next, it conducts an academic ability assessment, and if it is determined that User A has a weakness in Japanese grammar, for example, appropriate practice questions and explanations will be generated.

[1126] While User A is working on a problem, if the emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, the server generates a prompt sentence like the one below and provides appropriate feedback.

[1127] Example prompt sentence:

[1128] User A's stressed facial expression was detected.

[1129] Please choose the appropriate response from the options below:

[1130] 1. Display encouraging messages

[1131] 2. Slow down your learning pace

[1132] 3. Offer a temporary break

[1133] Based on this prompt, the server provides appropriate feedback to User A and adjusts the learning curriculum to maximize the user's learning effectiveness.

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

[1135] Step 1:

[1136] The user enters the initial settings.

[1137] The user inputs initial setting data such as grade, learning goal, strong and weak subjects into the terminal and transmits it to the server.

[1138] Input: Grade, learning goals, strong subjects, weak subjects

[1139] Data processing and calculation: The server generates a user ID based on the received data and saves the initial setting data in the database.

[1140] Output: User ID, initial setting data saved

[1141] Step 2:

[1142] The server runs the academic achievement test.

[1143] When a user starts the academic ability diagnostic test, the server generates a diagnostic test appropriate for the user's grade and sends it to the terminal. The user answers the questions and sends the results back to the server.

[1144] Input: User ID, grade

[1145] Data processing and calculation: Evaluate the user's academic ability and identify areas of strength and weakness.

[1146] Output: Academic achievement evaluation results

[1147] Step 3:

[1148] The server generates individual exercises and explanations.

[1149] Based on the results of the academic ability assessment, the server generates practice questions and explanations that focus on the user's weak areas and sends them to the terminal.

[1150] Input: Academic achievement evaluation results

[1151] Data processing and calculation: Automatically generate practice questions and explanations using a generative AI model.

[1152] Output: Exercises, explanations

[1153] Step 4:

[1154] The user answers the exercises.

[1155] The user answers the exercises presented to them and sends the results to the server via their terminal.

[1156] Input: User's answer

[1157] Data processing and calculation: The server grades the answers, evaluates the results, and generates feedback.

[1158] Output: Marking results, feedback

[1159] Step 5:

[1160] The server tracks the user's progress and provides feedback.

[1161] Once the user has completed the exercises, the server records progress data and provides periodically generated feedback to the user.

[1162] Input: Marking results, progress data

[1163] Data processing and calculation: Feedback is generated from progress data and scoring results and sent to the user.

[1164] Output: Feedback

[1165] Step 6:

[1166] The device uses an emotion engine to recognize the user's emotional state.

[1167] While the user is learning, the device uses a camera and microphone to capture the user's facial expressions and voice, which are then sent to the emotion engine. The server analyzes these and recognizes the user's emotional state.

[1168] Input: facial expression data, voice data

[1169] Data processing and calculation: The emotion engine analyzes the data and identifies the emotional state.

[1170] Output: Emotional state

[1171] Step 7:

[1172] The server adjusts the feedback based on the emotional state.

[1173] Once the user's emotional state is recognized, the server can adjust the feedback and learning curriculum accordingly, for example, sending encouraging messages if the user is feeling stressed.

[1174] Input: Emotional state, feedback

[1175] Data processing and calculation: Adjust existing feedback and curriculum according to emotional states.

[1176] Output: Adjusted feedback and curriculum

[1177] Example prompt sentence:

[1178] User A's stressed facial expression was detected.

[1179] Please choose the appropriate response from the options below:

[1180] 1. Display encouraging messages

[1181] 2. Slow down your learning pace

[1182] 3. Offer a temporary break

[1183] This series of processes enables individual learning support and appropriate feedback based on emotions to be provided to the user.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] [Third embodiment]

[1188] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1189] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1190] 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).

[1191] 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.

[1192] 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.

[1193] 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).

[1194] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1195] 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.

[1196] 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.

[1197] 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.

[1198] 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.

[1199] 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."

[1200] This invention is a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, and manages learning progress.

[1201] System configuration

[1202] The system consists of the following main components:

[1203] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1204] 2. Server: Performs database management, generating AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[1205] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[1206] Program processing overview

[1207] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[1208] User registration and initial settings

[1209] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[1210] Academic ability analysis

[1211] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[1212] Creating practice questions

[1213] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[1214] Providing feedback

[1215] The server evaluates the user's progress based on the results of the exercises and generates personalized feedback, which the device displays to the user and suggests the next learning step.

[1216] Creating a customized curriculum

[1217] The server periodically sets tests to evaluate the user's progress. When the user takes the test, the server creates a customized learning curriculum based on the test results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[1218] Specific examples

[1219] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[1220] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and submits the results to the server, which immediately scores them and provides feedback. Furthermore, a regularly updated customized learning curriculum is generated based on User A's learning progress, providing specific suggestions for what to study next.

[1221] In this way, the entire system works in cooperation to fully meet the learning needs of each user and provide efficient and effective learning support.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] The user enters the required information (user name, password, grade, email address) on the new registration screen and presses the "Register" button.

[1225] Step 2:

[1226] The terminal transmits the input information to the server.

[1227] Step 3:

[1228] The server generates a new user ID based on the received data and saves the initial setting data in the database.

[1229] Step 4:

[1230] The user logs in, enters information on the screen where they can enter their grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[1231] Step 5:

[1232] The terminal transmits the input initial setting information to the server.

[1233] Step 6:

[1234] The server receives the initial setting information, stores it in the user's profile data, and simultaneously prepares to start the academic ability diagnostic test.

[1235] Step 7:

[1236] The user presses the "Start academic ability diagnostic test" button.

[1237] Step 8:

[1238] The terminal transmits a request to start the academic ability diagnostic test to the server.

[1239] Step 9:

[1240] The server generates appropriate academic ability diagnostic questions according to the user's grade level and sends them to the terminal.

[1241] Step 10:

[1242] The terminal displays the questions of the academic ability diagnostic test to the user.

[1243] Step 11:

[1244] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[1245] Step 12:

[1246] The terminal sequentially transmits the user's answers to the server.

[1247] Step 13:

[1248] The server scores the received answers and records whether each question is correct or incorrect.

[1249] Step 14:

[1250] Based on all the responses, the server analyzes the user's strengths and weaknesses and generates a report of the results.

[1251] Step 15:

[1252] The terminal displays the academic ability analysis result report to the user.

[1253] Step 16:

[1254] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[1255] Step 17:

[1256] The terminal displays the generated exercises and explanations to the user.

[1257] Step 18:

[1258] The user completes the exercises and enters their answers.

[1259] Step 19:

[1260] The terminal transmits the user's answer to the server.

[1261] Step 20:

[1262] The server receives the answers, scores them, determines whether they are correct or incorrect, adds explanations, and generates an evaluation result.

[1263] Step 21:

[1264] The terminal displays the evaluation results and explanations to the user.

[1265] Step 22:

[1266] The server records the user's progress data and periodically generates feedback and learning progress reports.

[1267] Step 23:

[1268] The device displays feedback and learning progress reports to the user.

[1269] Step 24:

[1270] The server periodically sets up an academic ability assessment test for the user and notifies the user.

[1271] Step 25:

[1272] The user takes an academic assessment test and enters their answers.

[1273] Step 26:

[1274] The terminal transmits the user's answer to the server.

[1275] Step 27:

[1276] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[1277] Step 28:

[1278] The server generates a curriculum optimized for the user based on the test results.

[1279] Step 29:

[1280] The terminal displays the generated curriculum to the user and suggests the next learning stage.

[1281] The above are the specific processing steps for carrying out the invention. The operations performed by the server, terminal, and user at each step are described in detail.

[1282] Example 1

[1283] 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."

[1284] Conventional learning support systems have had the problem of being difficult to provide effective learning support because they are unable to respond to the academic ability and progress of individual users. Furthermore, they are unable to provide appropriate practice problems to overcome weaknesses in specific areas. Furthermore, they are inadequate in providing customized feedback and creating learning plans based on the user's learning progress, making it difficult to expect improvements in learning efficiency.

[1285] 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.

[1286] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness; [means for saving the generated user identification information and initial setting data in a database; [means for conducting a user's academic ability diagnostic test and evaluating academic ability; [means for identifying the user's areas of strength and weakness; [means for using a generative AI model to generate practice questions and explanations focusing on areas of weakness; [means for receiving the user's answers, grading and returning the results; [means for recording the user's progress and generating individual feedback; and [means for presenting a customized study plan to the user.] This enables learning support tailored to each individual user, effectively supporting the user's improvement in academic ability.

[1287] "User identification information" is information generated to uniquely identify each individual user.

[1288] "Initial setting data" refers to data such as grade, learning goals, strong subjects, and weak subjects that are input by the user when registering for the first time.

[1289] A "database" is a system for storing user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[1290] An "academic ability diagnostic test" is a collection of questions used to evaluate a user's current academic ability.

[1291] A "generative AI model" is an artificial intelligence model that generates appropriate practice questions and explanations based on the user's weak areas.

[1292] "Practice questions" are questions that are given with the aim of improving the user's academic ability.

[1293] "Feedback" refers to notifying users of evaluations and areas for improvement based on their learning outcomes and progress.

[1294] A "customized study plan" is a study schedule that is individually created based on the user's academic ability and progress.

[1295] This invention provides a learning support system equipped with a generative AI model. It analyzes the user's academic ability and provides individually optimized learning plans and feedback, thereby achieving efficient and effective learning support.

[1296] System configuration

[1297] The system consists of the following main components:

[1298] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or personal computer.

[1299] 2. Server: Performs database management, processing using generative AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[1300] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, learning curriculum, etc.

[1301] User registration and initial settings

[1302] The process begins when the user enters information such as name, grade, learning goals, and areas of strength and weakness on the new registration screen. The device sends this information to the server, which then generates new user identification information based on the received information. The generated identification information and initial setting data are stored in a database.

[1303] Academic ability analysis

[1304] When a user starts an academic ability diagnostic test, the device sends a request to the server. The server uses a generative AI model to create appropriate academic ability diagnostic questions based on the user's grade level, and then sends them to the device. The user's answers are sent via the device to the server, which automatically scores them and identifies the user's strengths and weaknesses.

[1305] Creating practice questions

[1306] Based on the results of the academic ability assessment, the server uses a generative AI model to generate practice questions that focus on the user's weak areas. The generated questions are sent to the device and presented to the user. The user's answers are sent via the device to the server, which evaluates them and generates feedback.

[1307] Providing feedback

[1308] Based on the results of the exercises the user answers, the server generates personalized feedback, which the device displays to the user and suggests the next steps to take. The feedback includes detailed evaluations and advice, with the aim of deepening the user's understanding.

[1309] Creating a customized curriculum

[1310] The server periodically evaluates the user's progress and sets new tests as needed. Based on the user's test results, a customized learning plan is created using a generative AI model. The generated curriculum is sent to the device and presented to the user.

[1311] Specific use cases

[1312] For example, consider the case where User A, a fifth-grader in elementary school, newly registers with the system. User A enters information such as his name, grade, learning goals, favorite subject (math), and weak subject (Japanese). This information is sent from the terminal to the server, which generates new user identification information and stores it in a database. User A then begins an academic ability diagnostic test, and the server generates appropriate questions and sends them to the terminal. User A's answers are graded by the server, and grammar questions that User A is particularly weak at are extracted.

[1313] The server automatically generates practice questions focusing on weak grammar points and provides them to User A via the terminal. User A answers these questions and submits them to the server again, where the server evaluates the answers and generates feedback, including suggestions for improvement and additional practice questions.

[1314] Examples of prompt statements

[1315] "Please generate grammar exercises for a fifth-grade elementary school student. The user feels that he or she is not good at grammar."

[1316] Based on this prompt, the generative AI model provides appropriate practice questions for User A. This allows the entire system to work together to meet the user's learning needs and provide efficient and effective learning support.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The user enters the required information (name, grade, learning goals, areas of strength and weakness, etc.) on the new registration screen.

[1320] Input: User's personal and study-related information

[1321] Output: User input data

[1322] Specific behavior: The user enters information into the input form and presses the "Submit" button.

[1323] Step 2:

[1324] The terminal transmits the input user information to the server.

[1325] Input: User-entered data

[1326] Output: Data sent to the server

[1327] Specific operation: The terminal sends the received user input data to the server using the HTTPS protocol.

[1328] Step 3:

[1329] The server generates new user identification information based on the received information and stores the initial setting data in a database.

[1330] Input: Data to send to the server

[1331] Output: User identity and database updates

[1332] Specific operation: The server generates user identification information from the received data and executes an SQL query to store it in a database.

[1333] Step 4:

[1334] The server generates an academic ability diagnostic test, selects appropriate questions based on grade information, and sends them to the terminal.

[1335] Input: User's grade information and initial setting data

[1336] Output: Academic ability diagnostic test

[1337] Specific operation: The server selects appropriate questions from the question bank based on grade information, and if necessary, generates new questions using a generative AI model and sends them to the terminal.

[1338] Step 5:

[1339] The user takes an academic ability diagnostic test and transmits the answers to the server via the terminal.

[1340] Input: Academic ability diagnostic test and user answers

[1341] Output: User answer data

[1342] Specific operation: The user answers the diagnostic test using the terminal and presses the send answer button, which sends the answer data to the server.

[1343] Step 6:

[1344] The server automatically scores the user's answer data and identifies areas of strength and weakness.

[1345] Input: User answer data

[1346] Output: Analysis of strengths and weaknesses

[1347] Specific operation: The server automatically scores the received answer data and analyzes the areas of strength and weakness using a specific algorithm.

[1348] Step 7:

[1349] The server uses a generative AI model to generate practice questions and explanations based on the user's weak areas and sends them to the device.

[1350] Input: Analysis results of strengths and weaknesses

[1351] Output: Exercises and explanations

[1352] Specific operation: The server uses the generative AI model to generate questions that focus on the user's weak areas and sends them to the device.

[1353] Step 8:

[1354] The user answers the exercises and sends the results from the terminal to the server.

[1355] Input: Exercises and user answers

[1356] Output: User answer data

[1357] Specific operation: The user answers the practice questions and sends the results to the server using the send button on the device.

[1358] Step 9:

[1359] The server evaluates the practice question answer data and generates feedback.

[1360] Input: User answer data

[1361] Output: Feedback

[1362] Specific operation: The server evaluates the answer data and uses a generative AI model to create detailed feedback for the user and send it to the device.

[1363] Step 10:

[1364] A server periodically evaluates the user's progress data and generates a customized learning curriculum that is regularly updated.

[1365] Input: User progress data

[1366] Output: Customized learning curriculum

[1367] Specific operation: The server evaluates the user's progress data, uses a generative AI model to generate an individually optimized learning curriculum, and sends it to the device.

[1368] Step 11:

[1369] The terminal displays the customized learning curriculum to the user.

[1370] Input: Customized Learning Curriculum

[1371] Output: Presentation of study schedule

[1372] Specific operation: The terminal displays the received curriculum to the user and indicates the specific content that should be studied next.

[1373] In this way, the entire system cooperates to provide effective learning support that meets the user's learning needs.

[1374] (Application example 1)

[1375] 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."

[1376] Conventional factory worker training systems have made it difficult to provide effective training programs tailored to the skill level of each worker. Standardized training programs cannot adequately reflect the actual abilities and progress of workers, resulting in reduced training efficiency. Customizing training content also requires a significant amount of time and effort, making it difficult to manage progress and provide feedback in real time.

[1377] 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.

[1378] In this invention, the server includes: means for receiving input information from a user and initializing the installation year, goals, strengths and weaknesses; means for saving the generated account ID and initial setting data in a database; means for performing a skill evaluation of the worker and identifying strengths and weaknesses; means for generating training modules and explanations focusing on the weaknesses; means for receiving the worker's answers, scoring, and returning the results; means for recording the worker's progress data and periodically generating feedback; means for presenting a customized training program to the worker; means for generating optimal training content for the worker using a generative AI model; and means for inputting prompts to the generative AI model and outputting the required training content. This enables the provision of an effective training program tailored to the skill level of each worker.

[1379] "User input" is data that operators use to communicate initial setup and individual training needs to the system.

[1380] "Year of installation" refers to the year in which the worker began performing the work.

[1381] "Goal" refers to a specific educational or skill-building goal that a worker seeks to achieve.

[1382] "Area of ​​expertise" refers to an area in which a worker has relatively high skills or knowledge.

[1383] "Weak areas" refer to areas in which a worker has relatively low skills or knowledge.

[1384] An "account ID" is an identifier generated to uniquely identify a worker within the system.

[1385] "Initial setting data" is data that collects setting information provided when an operator starts using the system.

[1386] "Skills assessment" is the process of analyzing a worker's current skill level and identifying their strengths and weaknesses.

[1387] An "educational module" is an educational unit that includes a series of instructional content for acquiring specific skills or knowledge.

[1388] "Explanation" refers to detailed explanatory text and illustrations that allow workers to understand the content contained in the training module.

[1389] An "answer" is a response that a worker submits to an educational module or test.

[1390] "Scoring" is the process of evaluating a worker's answers to determine their accuracy.

[1391] "Results" refers to the evaluation and feedback generated based on the worker's answers.

[1392] "Progress data" is data that records the progress of a worker's education and training.

[1393] "Feedback" refers to advice and evaluation provided to workers regarding their education and training progress.

[1394] A "training program" is a set of educational content customized to improve a worker's skills.

[1395] A "generative AI model" is an artificial intelligence model that is trained to perform a specific task based on large amounts of data.

[1396] A "prompt sentence" is an instruction sentence input to a generative AI model to instruct the worker on how to generate training content.

[1397] This invention relates to a head-mounted display (HMD) application for supporting worker training in factories and a training content generation system that uses a generative AI model. This system provides appropriate training programs according to the skill level of each worker, achieving efficient and effective training.

[1398] System configuration

[1399] The system consists of the following main components:

[1400] 1. User terminal: A head-mounted display (HMD) that allows workers to access the system and receive training content.

[1401] 2. Server: Performs database management, operation of generative AI models, skill evaluation, educational module generation, answer evaluation, and feedback provision.

[1402] 3. Database: Stores worker profile information, skill evaluation results, education history, training programs, etc.

[1403] Specific operation of the system

[1404] User registration and initial settings

[1405] When the user enters the required information (year of installation, goals, areas of strength and weakness) on the new registration screen, the device sends the data to the server. The server generates a new account ID based on the received data and saves the initial setting data in the database.

[1406] Skills Evaluation

[1407] When a user starts a skills assessment test, the device sends the request to the server. The server generates skills assessment questions according to the worker's role and sends them to the device. When the worker solves the questions and submits their answers, the server scores them and identifies the worker's strengths and weaknesses.

[1408] Creating an Educational Module

[1409] Based on the results of the skill assessment, the server generates an educational module and explanations that focus on the worker's weak areas. The terminal receives this and presents it to the worker. The user studies the educational module and sends the answer results from the terminal to the server. The server evaluates the answer and returns the results and feedback.

[1410] Providing feedback

[1411] The server evaluates the worker's progress based on the results of the training module and generates individual feedback, which is displayed to the worker on the terminal and suggests the next training step.

[1412] Customize your training program

[1413] The server periodically sets tests to evaluate the worker's progress. When the user takes the test, the server creates a customized training program based on the results and sends it to the terminal. The terminal then presents the training program to the worker, supporting their daily education.

[1414] Technology used

[1415] This system uses TensorFlow and Keras to build a generative AI model that evaluates worker skills and generates optimal training programs based on large amounts of data. It also uses an SQL database system for database management, processing and analyzing data in real time.

[1416] Specific examples

[1417] For example, when a new worker A is assigned to a factory, he or she is registered in the system. The initial setup involves entering the year of installation, training goals, areas of strength (e.g., machine operation), and areas of weakness (e.g., safety management). The system receives this information and generates an optimal training program based on it.

[1418] After taking the skill assessment test, the system evaluates Worker A's current skill level and generates a training module that focuses on his weaknesses. It then inputs the following prompt sentence into the generative AI model:

[1419] "Please assess the skill level of your workers and suggest appropriate training programs. The dataset is as follows: [example data]"

[1420] Based on this prompt, the most appropriate training content is generated and displayed on the HMD of Worker A. This allows Worker A to receive the training necessary to improve his or her skills in real time.

[1421] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1422] Step 1:

[1423] The user enters the necessary information (year of establishment, goals, areas of strength, areas of weakness) on the new registration screen. The terminal sends the data to the server.

[1424] Input: Year of establishment, goals, areas of strength and weakness information

[1425] Output: Registration information sent to the server

[1426] Specific operation: The user inputs information using the HMD's user interface and presses the send button.

[1427] Step 2:

[1428] The server generates a new account ID based on the received data and stores the initial setting data in the database.

[1429] Input: Registration information

[1430] Output: Generated account ID and initial setting data

[1431] Specific operation: The server accesses the database, creates a new record, and automatically generates an account ID.

[1432] Step 3:

[1433] When a user starts a skill assessment test, the terminal sends the request to the server.

[1434] Input: Skills Assessment Test Request

[1435] Output: Request sent to the server

[1436] Specific operation: The user presses the evaluation test start button on the HMD.

[1437] Step 4:

[1438] The server generates skill evaluation questions according to the worker's role and sends them to the terminal.

[1439] Input: Role information

[1440] Output: Generated skill assessment questions

[1441] Specific operation: The server uses the generative AI model to generate an appropriate problem set and sends it to the device.

[1442] Step 5:

[1443] The user solves the problem and sends the answer from the terminal to the server.

[1444] Input: Worker's response

[1445] Output: The answer sent to the server

[1446] Specific operation: The user solves the problem using the HMD and presses the answer button to submit the result.

[1447] Step 6:

[1448] The server scores the answers and identifies the worker's strengths and weaknesses.

[1449] Input: Answer data

[1450] Output: Identification of strengths and weaknesses

[1451] What happens: The server uses a scoring algorithm to evaluate and identify answers.

[1452] Step 7:

[1453] Based on the results of the skills assessment, the server generates educational modules and explanations that focus on the worker's areas of weakness.

[1454] Input: Results of identifying strengths and weaknesses

[1455] Output: Educational modules and descriptions

[1456] Specific operation: The server inputs a prompt sentence into the generative AI model and generates educational content.

[1457] Step 8:

[1458] The server sends the generated educational module to the terminal, where the user receives it and begins learning.

[1459] Input: Education Module

[1460] Output: Educational module sent to the device

[1461] Specific operation: The server sends educational content to the terminal and it is displayed on the HMD.

[1462] Step 9:

[1463] The user studies the educational module and sends the answers from the terminal to the server.

[1464] Input: Learning results and answers

[1465] Output: Learning results and answers sent to the server

[1466] Specific operation: The user uses the HMD to learn, input and submit the results.

[1467] Step 10:

[1468] The server evaluates the answers and generates results and feedback.

[1469] Input: Learning results and answers

[1470] Output: Evaluation results and feedback

[1471] Specific operation: The server evaluates the answer using an answer evaluation algorithm and generates feedback.

[1472] Step 11:

[1473] The server evaluates the worker's progress based on the results of the training module and generates individual feedback.

[1474] Input: Answer evaluation result

[1475] Output: Individual feedback

[1476] What happens: The server analyzes the progress data and generates feedback.

[1477] Step 12:

[1478] The server creates a customized training program and sends it to the terminal, which presents it to the user.

[1479] Input: Individual feedback

[1480] Output: Customized training program

[1481] Specific operation: The server generates an educational program using the generative AI model and sends it to the device. It is then displayed on the HMD.

[1482] An example of a specific prompt would be, "Please assess the skill level of workers and suggest appropriate training programs. The dataset is as follows: [Example data]," and you can get output results from the generative AI model.

[1483] 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.

[1484] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[1485] System configuration

[1486] The system consists of the following main components:

[1487] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1488] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[1489] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[1490] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[1491] Program processing overview

[1492] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[1493] User registration and initial settings

[1494] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[1495] Academic ability analysis

[1496] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[1497] Creating practice questions

[1498] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[1499] Emotion recognition and feedback provision

[1500] The device sends the user's facial and voice data to the emotion engine, which then uses this data to recognize the user's emotional state. After the user completes the exercise, the emotion data is also analyzed and appropriate feedback is generated. For example, if the user looks tired, the system may respond by displaying an encouraging message.

[1501] Creating a customized curriculum

[1502] The server periodically sets tests to evaluate the user's progress and emotional data. After the user takes the test, the server creates a customized learning curriculum based on the results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[1503] Specific examples

[1504] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[1505] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and sends the answers to the server, which immediately scores them and provides feedback.

[1506] Furthermore, if the system's emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, it will take measures such as displaying encouraging messages and temporarily adjusting the difficulty level. Furthermore, a customized learning curriculum that is regularly updated based on User A's learning progress is generated, and specific content that should be learned next is presented.

[1507] In this way, the entire system works together to fully address the learning needs of each individual user, and by incorporating emotion recognition, it is possible to provide more effective and efficient learning support.

[1508] The processing flow will be explained below.

[1509] Step 1:

[1510] The user enters the required information on the new registration screen and presses the "Register" button.

[1511] Step 2:

[1512] The terminal transmits the input information to the server.

[1513] Step 3:

[1514] The server receives the input information, generates a new user ID, and saves the generated user ID and initial setting data in the database.

[1515] Step 4:

[1516] The user logs in, enters information on the screen for entering grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[1517] Step 5:

[1518] The terminal transmits the input initial setting information to the server.

[1519] Step 6:

[1520] The server receives the initial setting information and stores it in the user's profile data. The server prepares for the academic ability diagnostic test.

[1521] Step 7:

[1522] The user presses the "Start academic ability diagnostic test" button.

[1523] Step 8:

[1524] The terminal sends a request to start the academic ability diagnostic test to the server.

[1525] Step 9:

[1526] The server generates appropriate academic ability diagnostic questions according to the user's grade level and transmits them to the terminal.

[1527] Step 10:

[1528] The terminal displays the questions of the academic ability diagnostic test to the user.

[1529] Step 11:

[1530] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[1531] Step 12:

[1532] The terminal sequentially transmits the user's answers to the server.

[1533] Step 13:

[1534] The server scores the received answers and records whether each question is correct or incorrect.

[1535] Step 14:

[1536] The server analyzes the user's strengths and weaknesses based on all responses and generates a report of the results.

[1537] Step 15:

[1538] The terminal displays the academic ability analysis result report to the user.

[1539] Step 16:

[1540] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[1541] Step 17:

[1542] The terminal displays the generated exercises and explanations to the user.

[1543] Step 18:

[1544] The user completes the exercises and enters the answers.

[1545] Step 19:

[1546] The terminal sends the user's answer to the server.

[1547] Step 20:

[1548] The server receives the answers, scores them, determines whether the answers are correct or incorrect, adds explanations, and generates an evaluation result.

[1549] Step 21:

[1550] The terminal displays the evaluation results and explanations to the user.

[1551] Step 22:

[1552] The device sends the user's facial expressions and voice data to the emotion engine.

[1553] Step 23:

[1554] The server analyzes the user's emotional data using an emotion engine, and generates an encouraging message if the user is feeling stressed.

[1555] Step 24:

[1556] The device displays emotion-based feedback messages to the user.

[1557] Step 25:

[1558] The server records the user's progress data and periodically generates feedback and learning progress reports.

[1559] Step 26:

[1560] The device displays feedback and learning progress reports to the user.

[1561] Step 27:

[1562] The server periodically sets academic ability assessment tests for the user and notifies the user.

[1563] Step 28:

[1564] The user takes the academic assessment test and enters the answers.

[1565] Step 29:

[1566] The terminal sends the user's answer to the server.

[1567] Step 30:

[1568] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[1569] Step 31:

[1570] The server generates a curriculum optimized for the user based on the test results.

[1571] Step 32:

[1572] The device displays the generated curriculum to the user and suggests the next learning step.

[1573] The above are the specific processing steps in a system that combines emotion engines. We have described in detail what operations the server, terminal, and user perform at each step.

[1574] Example 2

[1575] 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."

[1576] Conventional learning support systems lack the ability to customize to each user's academic ability and progress, making it difficult to provide effective practice questions for specific areas of weakness. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve motivation to learn or reduce stress. This limits the effectiveness of learning and makes it difficult to provide an optimal learning environment tailored to individual needs.

[1577] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1578] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness;] [means for storing the generated unique identifier and initial setting data in an information storage device; and] [means for performing an analysis of the user's academic ability and identifying areas of strength and weakness.] This makes it possible [to provide customized feedback and curriculum according to the user's individual learning needs].

[1579] "Information input from the user" refers to information provided by the system user, such as name, grade, learning goals, areas of strength and weakness, etc.

[1580] "Grade" is information that indicates the educational level or learning stage to which the system user belongs.

[1581] "Learning objectives" are the learning goals or objectives that system users want to achieve.

[1582] "Areas of expertise" refers to areas of study or subjects in which the system user has particular strengths.

[1583] "Weak areas" are areas of study or subjects that the system user is weak at.

[1584] "Initial settings" refers to basic settings that the system performs based on information input by the user.

[1585] A "unique identifier" is an ID generated to uniquely identify each user within the system.

[1586] An "information storage device" is a storage device used to store data within a system.

[1587] "Academic performance analysis" is the process by which the system evaluates a user's learning status and identifies their strengths and weaknesses.

[1588] "Practice questions" are a collection of questions provided by the system to improve the user's learning ability.

[1589] "Explanation" refers to supporting materials in the form of written, audio, or video that explain the answers and solutions to the practice problems.

[1590] "Answer" refers to the answer entered by the user to the exercise.

[1591] "Scoring" is the process of evaluating a user's answer and determining whether it is correct or not.

[1592] "Result" is information for providing feedback on the results of the scoring to the user.

[1593] "Progress data" is data that records the user's learning process and progress.

[1594] "Feedback" is reaction information including evaluation and advice regarding the user's learning activities.

[1595] A "learning plan" is a customized curriculum based on a user's learning goals and progress.

[1596] "Emotion data" is data that indicates the emotional state extracted from the user's facial expression and voice.

[1597] The "emotion engine" is a system function that analyzes the user's emotional data and evaluates the results.

[1598] A "generative AI model" is an artificial intelligence model that generates questions, explanations, and feedback that meet the user's needs.

[1599] MODE FOR CARRYING OUT THE INVENTION

[1600] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[1601] System configuration

[1602] The system consists of the following main components:

[1603] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1604] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[1605] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[1606] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[1607] Program processing overview

[1608] User registration and initial settings

[1609] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[1610] Academic ability analysis

[1611] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[1612] Creating practice questions

[1613] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[1614] Emotion recognition and feedback provision

[1615] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[1616] Creating a customized curriculum

[1617] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[1618] This series of processes enables the system to optimally respond to the individual learning needs and emotional state of each user, providing an efficient and effective learning experience.

[1619] Prompt Sentence Examples

[1620] The system performs specific processing by issuing instructions to the generative AI model using prompt sentences. Below are some examples of prompt sentences.

[1621] "Generate language exercises for elementary school students. Focus on grammar."

[1622] "Generate encouraging messages based on the user's emotional data."

[1623] "Create a customized learning curriculum based on the results of your academic ability analysis."

[1624] As a result, the system of the present invention can provide optimal learning support by taking into account the learning needs and emotional state of each individual user.

[1625] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1626] Step 1: User registration and initial setup

[1627] explanation:

[1628] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[1629] input:

[1630] User name, grade, learning goals, strengths and weaknesses

[1631] Data processing:

[1632] The server validates the received data and generates a unique identifier.

[1633] output:

[1634] User ID, initial setting data

[1635] Specific behavior:

[1636] The server receives the user data sent from the terminal, generates a new user ID, and stores it in the information storage device.

[1637] Step 2: Academic performance analysis

[1638] explanation:

[1639] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[1640] input:

[1641] User's grade, test start request, and academic ability assessment answers

[1642] Data processing:

[1643] The server generates assessment questions, receives and grades answers, and identifies areas of strength and weakness.

[1644] output:

[1645] Generated diagnostic questions and analysis of strengths and weaknesses

[1646] Specific behavior:

[1647] The server generates academic ability diagnostic questions and sends them to the terminal. The user enters the answers, and the terminal sends them to the server for grading.

[1648] Step 3: Create an exercise

[1649] explanation:

[1650] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[1651] input:

[1652] Academic ability analysis results, user answers

[1653] Data processing:

[1654] The server generates practice questions based on the results of the academic ability analysis and evaluates the received answers.

[1655] output:

[1656] Generated exercises, evaluated answers, and feedback

[1657] Specific behavior:

[1658] The server generates exercises and explanations and sends them to the device. The user answers them and sends the answers from the device to the server. The server evaluates the answers and provides feedback.

[1659] Step 4: Recognize emotions and provide feedback

[1660] explanation:

[1661] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[1662] input:

[1663] User's facial expression data, voice data

[1664] Data processing:

[1665] The server uses an emotion engine to analyze the facial expression data and voice data to identify an emotional state.

[1666] output:

[1667] Sentiment analysis results and feedback

[1668] Specific behavior:

[1669] The device captures facial and voice data and sends it to a server, which analyzes the user's emotional state and generates appropriate feedback that is sent back to the device.

[1670] Step 5: Create a customized curriculum

[1671] explanation:

[1672] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[1673] input:

[1674] User progress data, emotion data, test results

[1675] Data processing:

[1676] The server evaluates the progress data and emotional data and creates a new curriculum.

[1677] output:

[1678] Customized Curriculum

[1679] Specific behavior:

[1680] The server analyzes the progress data and emotion data, generates a customized curriculum for the user, and sends it to the device, which then displays it to the user.

[1681] Through these processing steps, the system can optimally respond to the individual learning needs and emotional state of the user, providing an efficient and effective learning experience.

[1682] (Application example 2)

[1683] 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."

[1684] Although systems that provide learning support tailored to individual academic ability already exist, there are still insufficient systems that can provide more effective learning support by recognizing the user's emotional state along with their learning progress and responding in real time.Therefore, there is a need to provide more personalized learning support that simultaneously considers the user's individual learning situation and emotional state.

[1685] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1686] In this invention, the server includes: [means for receiving user input information and initializing the grade, learning goals, and strong and weak subjects;] [means for saving the generated user ID and initial setting data in a database;] [means for performing an analysis of the user's academic ability and identifying strong and weak areas;] [means for generating practice questions and explanations focusing on weak areas;] [means for receiving the user's answers, grading, and returning the results;] [means for recording the user's progress data and generating periodic feedback;] [means for presenting a customized curriculum to the user; and] [means for recognizing the user's emotional state, analyzing and recording emotional data, and providing appropriate feedback. This makes it possible to provide study questions tailored to the user's individual academic ability, as well as to provide feedback and adjust the curriculum taking the user's emotional state into consideration.

[1687] "User" refers to the learner or individual receiving education who uses the system.

[1688] "Server" refers to the central computer system that processes and manages user input information, academic achievement data, emotional data, etc.

[1689] "Database" refers to a data repository for storing and managing user profile information, learning history, academic ability analysis results, emotional data, etc.

[1690] A "generative AI model" refers to an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, and so on.

[1691] An "emotion engine" is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[1692] "Initial setting data" refers to basic information such as grade level, learning goals, strong and weak subjects, etc., that a user enters when registering with the system.

[1693] "Academic Analysis" refers to the assessment process used to assess a user's academic ability and identify areas of strength and weakness.

[1694] "Practice Problems and Explanations" refers to information that explains problems and how to solve them, provided for the purpose of improving a user's academic ability.

[1695] "Feedback" refers to the evaluation and advice provided to a user regarding their learning progress and answer results.

[1696] "Customized curriculum" refers to an individualized learning plan that is tailored and optimized based on the user's academic ability and emotional state.

[1697] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, voice, actions, etc.

[1698] "Progress Data" means records and data relating to a User's learning progress.

[1699] The system for implementing this invention comprises a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1700] The user terminal is a device such as a smartphone, tablet, or PC that the user uses to access the system. The server is a central computer system that processes and manages user input information, academic achievement data, emotional data, etc. The database is a data repository that stores and manages user profile information, learning history, academic achievement analysis results, emotional data, etc.

[1701] The generative AI model is an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, etc. The emotion engine is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[1702] Program Processing Overview

[1703] The server receives input from the user and initializes the grade, learning goals, and strong and weak subjects. This initialization data is stored in a database. Next, it diagnoses the user's academic ability and identifies their strong and weak areas. It generates practice questions and explanations that focus on the weak areas, and when the user answers them, it grades the results and provides feedback. Feedback is generated periodically to effectively support the user's academic improvement.

[1704] Furthermore, the server records the user's progress data and presents a customized curriculum based on the progress. The emotion engine analyzes the user's facial and voice data to recognize their emotional state. Based on this, the server can provide appropriate feedback and encouraging messages and adjust the learning curriculum.

[1705] Specific example explanation

[1706] For example, if User A, a fifth-grader, uses this system, he or she will initially enter their grade, learning goals, favorite subject (math), and weak subject (Japanese). The system generates a user ID based on this information and stores the information in a database. Next, it conducts an academic ability assessment, and if it is determined that User A has a weakness in Japanese grammar, for example, appropriate practice questions and explanations will be generated.

[1707] While User A is working on a problem, if the emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, the server generates a prompt sentence like the one below and provides appropriate feedback.

[1708] Example prompt sentence:

[1709] User A's stressed facial expression was detected.

[1710] Please choose the appropriate response from the options below:

[1711] 1. Display encouraging messages

[1712] 2. Slow down your learning pace

[1713] 3. Offer a temporary break

[1714] Based on this prompt, the server provides appropriate feedback to User A and adjusts the learning curriculum to maximize the user's learning effectiveness.

[1715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1716] Step 1:

[1717] The user enters the initial settings.

[1718] The user inputs initial setting data such as grade, learning goal, strong and weak subjects into the terminal and transmits it to the server.

[1719] Input: Grade, learning goals, strong subjects, weak subjects

[1720] Data processing and calculation: The server generates a user ID based on the received data and saves the initial setting data in the database.

[1721] Output: User ID, initial setting data saved

[1722] Step 2:

[1723] The server runs the academic achievement test.

[1724] When a user starts the academic ability diagnostic test, the server generates a diagnostic test appropriate for the user's grade and sends it to the terminal. The user answers the questions and sends the results back to the server.

[1725] Input: User ID, grade

[1726] Data processing and calculation: Evaluate the user's academic ability and identify areas of strength and weakness.

[1727] Output: Academic achievement evaluation results

[1728] Step 3:

[1729] The server generates individual exercises and explanations.

[1730] Based on the results of the academic ability assessment, the server generates practice questions and explanations that focus on the user's weak areas and sends them to the terminal.

[1731] Input: Academic achievement evaluation results

[1732] Data processing and calculation: Automatically generate practice questions and explanations using a generative AI model.

[1733] Output: Exercises, explanations

[1734] Step 4:

[1735] The user answers the exercises.

[1736] The user answers the exercises presented to them and sends the results to the server via their terminal.

[1737] Input: User's answer

[1738] Data processing and calculation: The server grades the answers, evaluates the results, and generates feedback.

[1739] Output: Marking results, feedback

[1740] Step 5:

[1741] The server tracks the user's progress and provides feedback.

[1742] Once the user has completed the exercises, the server records progress data and provides periodically generated feedback to the user.

[1743] Input: Marking results, progress data

[1744] Data processing and calculation: Feedback is generated from progress data and scoring results and sent to the user.

[1745] Output: Feedback

[1746] Step 6:

[1747] The device uses an emotion engine to recognize the user's emotional state.

[1748] While the user is learning, the device uses a camera and microphone to capture the user's facial expressions and voice, which are then sent to the emotion engine. The server analyzes these and recognizes the user's emotional state.

[1749] Input: facial expression data, voice data

[1750] Data processing and calculation: The emotion engine analyzes the data and identifies the emotional state.

[1751] Output: Emotional state

[1752] Step 7:

[1753] The server adjusts the feedback based on the emotional state.

[1754] Once the user's emotional state is recognized, the server can adjust the feedback and learning curriculum accordingly, for example, sending encouraging messages if the user is feeling stressed.

[1755] Input: Emotional state, feedback

[1756] Data processing and calculation: Adjust existing feedback and curriculum according to emotional states.

[1757] Output: Adjusted feedback and curriculum

[1758] Example prompt sentence:

[1759] User A's stressed facial expression was detected.

[1760] Please choose the appropriate response from the options below:

[1761] 1. Display encouraging messages

[1762] 2. Slow down your learning pace

[1763] 3. Offer a temporary break

[1764] This series of processes enables individual learning support and appropriate feedback based on emotions to be provided to the user.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] [Fourth embodiment]

[1769] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1770] 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.

[1771] 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).

[1772] 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.

[1773] 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.

[1774] 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).

[1775] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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."

[1782] This invention is a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, and manages learning progress.

[1783] System configuration

[1784] The system consists of the following main components:

[1785] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[1786] 2. Server: Performs database management, generating AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[1787] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[1788] Program processing overview

[1789] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[1790] User registration and initial settings

[1791] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[1792] Academic ability analysis

[1793] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[1794] Creating practice questions

[1795] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[1796] Providing feedback

[1797] The server evaluates the user's progress based on the results of the exercises and generates personalized feedback, which the device displays to the user and suggests the next learning step.

[1798] Creating a customized curriculum

[1799] The server periodically sets tests to evaluate the user's progress. When the user takes the test, the server creates a customized learning curriculum based on the test results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[1800] Specific examples

[1801] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[1802] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and submits the results to the server, which immediately scores them and provides feedback. Furthermore, a regularly updated customized learning curriculum is generated based on User A's learning progress, providing specific suggestions for what to study next.

[1803] In this way, the entire system works in cooperation to fully meet the learning needs of each user and provide efficient and effective learning support.

[1804] The processing flow will be explained below.

[1805] Step 1:

[1806] The user enters the required information (user name, password, grade, email address) on the new registration screen and presses the "Register" button.

[1807] Step 2:

[1808] The terminal transmits the input information to the server.

[1809] Step 3:

[1810] The server generates a new user ID based on the received data and saves the initial setting data in the database.

[1811] Step 4:

[1812] The user logs in, enters information on the screen where they can enter their grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[1813] Step 5:

[1814] The terminal transmits the input initial setting information to the server.

[1815] Step 6:

[1816] The server receives the initial setting information, stores it in the user's profile data, and simultaneously prepares to start the academic ability diagnostic test.

[1817] Step 7:

[1818] The user presses the "Start academic ability diagnostic test" button.

[1819] Step 8:

[1820] The terminal transmits a request to start the academic ability diagnostic test to the server.

[1821] Step 9:

[1822] The server generates appropriate academic ability diagnostic questions according to the user's grade level and sends them to the terminal.

[1823] Step 10:

[1824] The terminal displays the questions of the academic ability diagnostic test to the user.

[1825] Step 11:

[1826] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[1827] Step 12:

[1828] The terminal sequentially transmits the user's answers to the server.

[1829] Step 13:

[1830] The server scores the received answers and records whether each question is correct or incorrect.

[1831] Step 14:

[1832] Based on all the responses, the server analyzes the user's strengths and weaknesses and generates a report of the results.

[1833] Step 15:

[1834] The terminal displays the academic ability analysis result report to the user.

[1835] Step 16:

[1836] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[1837] Step 17:

[1838] The terminal displays the generated exercises and explanations to the user.

[1839] Step 18:

[1840] The user completes the exercises and enters their answers.

[1841] Step 19:

[1842] The terminal transmits the user's answer to the server.

[1843] Step 20:

[1844] The server receives the answers, scores them, determines whether they are correct or incorrect, adds explanations, and generates an evaluation result.

[1845] Step 21:

[1846] The terminal displays the evaluation results and explanations to the user.

[1847] Step 22:

[1848] The server records the user's progress data and periodically generates feedback and learning progress reports.

[1849] Step 23:

[1850] The device displays feedback and learning progress reports to the user.

[1851] Step 24:

[1852] The server periodically sets up an academic ability assessment test for the user and notifies the user.

[1853] Step 25:

[1854] The user takes an academic assessment test and enters their answers.

[1855] Step 26:

[1856] The terminal transmits the user's answer to the server.

[1857] Step 27:

[1858] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[1859] Step 28:

[1860] The server generates a curriculum optimized for the user based on the test results.

[1861] Step 29:

[1862] The terminal displays the generated curriculum to the user and suggests the next learning stage.

[1863] The above are the specific processing steps for carrying out the invention. The operations performed by the server, terminal, and user at each step are described in detail.

[1864] Example 1

[1865] 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."

[1866] Conventional learning support systems have had the problem of being difficult to provide effective learning support because they are unable to respond to the academic ability and progress of individual users. Furthermore, they are unable to provide appropriate practice problems to overcome weaknesses in specific areas. Furthermore, they are inadequate in providing customized feedback and creating learning plans based on the user's learning progress, making it difficult to expect improvements in learning efficiency.

[1867] 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.

[1868] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness; [means for saving the generated user identification information and initial setting data in a database; [means for conducting a user's academic ability diagnostic test and evaluating academic ability; [means for identifying the user's areas of strength and weakness; [means for using a generative AI model to generate practice questions and explanations focusing on areas of weakness; [means for receiving the user's answers, grading and returning the results; [means for recording the user's progress and generating individual feedback; and [means for presenting a customized study plan to the user.] This enables learning support tailored to each individual user, effectively supporting the user's improvement in academic ability.

[1869] "User identification information" is information generated to uniquely identify each individual user.

[1870] "Initial setting data" refers to data such as grade, learning goals, strong subjects, and weak subjects that are input by the user when registering for the first time.

[1871] A "database" is a system for storing user profile information, learning history, academic ability analysis results, practice questions, curriculum, etc.

[1872] An "academic ability diagnostic test" is a collection of questions used to evaluate a user's current academic ability.

[1873] A "generative AI model" is an artificial intelligence model that generates appropriate practice questions and explanations based on the user's weak areas.

[1874] "Practice questions" are questions that are given with the aim of improving the user's academic ability.

[1875] "Feedback" refers to notifying users of evaluations and areas for improvement based on their learning outcomes and progress.

[1876] A "customized study plan" is a study schedule that is individually created based on the user's academic ability and progress.

[1877] This invention provides a learning support system equipped with a generative AI model. It analyzes the user's academic ability and provides individually optimized learning plans and feedback, thereby achieving efficient and effective learning support.

[1878] System configuration

[1879] The system consists of the following main components:

[1880] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or personal computer.

[1881] 2. Server: Performs database management, processing using generative AI models, academic ability analysis, question generation, answer evaluation, and feedback provision.

[1882] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, learning curriculum, etc.

[1883] User registration and initial settings

[1884] The process begins when the user enters information such as name, grade, learning goals, and areas of strength and weakness on the new registration screen. The device sends this information to the server, which then generates new user identification information based on the received information. The generated identification information and initial setting data are stored in a database.

[1885] Academic ability analysis

[1886] When a user starts an academic ability diagnostic test, the device sends a request to the server. The server uses a generative AI model to create appropriate academic ability diagnostic questions based on the user's grade level, and then sends them to the device. The user's answers are sent via the device to the server, which automatically scores them and identifies the user's strengths and weaknesses.

[1887] Creating practice questions

[1888] Based on the results of the academic ability assessment, the server uses a generative AI model to generate practice questions that focus on the user's weak areas. The generated questions are sent to the device and presented to the user. The user's answers are sent via the device to the server, which evaluates them and generates feedback.

[1889] Providing feedback

[1890] Based on the results of the exercises the user answers, the server generates personalized feedback, which the device displays to the user and suggests the next steps to take. The feedback includes detailed evaluations and advice, with the aim of deepening the user's understanding.

[1891] Creating a customized curriculum

[1892] The server periodically evaluates the user's progress and sets new tests as needed. Based on the user's test results, a customized learning plan is created using a generative AI model. The generated curriculum is sent to the device and presented to the user.

[1893] Specific use cases

[1894] For example, consider the case where User A, a fifth-grader in elementary school, newly registers with the system. User A enters information such as his name, grade, learning goals, favorite subject (math), and weak subject (Japanese). This information is sent from the terminal to the server, which generates new user identification information and stores it in a database. User A then begins an academic ability diagnostic test, and the server generates appropriate questions and sends them to the terminal. User A's answers are graded by the server, and grammar questions that User A is particularly weak at are extracted.

[1895] The server automatically generates practice questions focusing on weak grammar points and provides them to User A via the terminal. User A answers these questions and submits them to the server again, where the server evaluates the answers and generates feedback, including suggestions for improvement and additional practice questions.

[1896] Examples of prompt statements

[1897] "Please generate grammar exercises for a fifth-grade elementary school student. The user feels that he or she is not good at grammar."

[1898] Based on this prompt, the generative AI model provides appropriate practice questions for User A. This allows the entire system to work together to meet the user's learning needs and provide efficient and effective learning support.

[1899] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1900] Step 1:

[1901] The user enters the required information (name, grade, learning goals, areas of strength and weakness, etc.) on the new registration screen.

[1902] Input: User's personal and study-related information

[1903] Output: User input data

[1904] Specific behavior: The user enters information into the input form and presses the "Submit" button.

[1905] Step 2:

[1906] The terminal transmits the input user information to the server.

[1907] Input: User-entered data

[1908] Output: Data sent to the server

[1909] Specific operation: The terminal sends the received user input data to the server using the HTTPS protocol.

[1910] Step 3:

[1911] The server generates new user identification information based on the received information and stores the initial setting data in a database.

[1912] Input: Data to send to the server

[1913] Output: User identity and database updates

[1914] Specific operation: The server generates user identification information from the received data and executes an SQL query to store it in a database.

[1915] Step 4:

[1916] The server generates an academic ability diagnostic test, selects appropriate questions based on grade information, and sends them to the terminal.

[1917] Input: User's grade information and initial setting data

[1918] Output: Academic ability diagnostic test

[1919] Specific operation: The server selects appropriate questions from the question bank based on grade information, and if necessary, generates new questions using a generative AI model and sends them to the terminal.

[1920] Step 5:

[1921] The user takes an academic ability diagnostic test and transmits the answers to the server via the terminal.

[1922] Input: Academic ability diagnostic test and user answers

[1923] Output: User answer data

[1924] Specific operation: The user answers the diagnostic test using the terminal and presses the send answer button, which sends the answer data to the server.

[1925] Step 6:

[1926] The server automatically scores the user's answer data and identifies areas of strength and weakness.

[1927] Input: User answer data

[1928] Output: Analysis of strengths and weaknesses

[1929] Specific operation: The server automatically scores the received answer data and analyzes the areas of strength and weakness using a specific algorithm.

[1930] Step 7:

[1931] The server uses a generative AI model to generate practice questions and explanations based on the user's weak areas and sends them to the device.

[1932] Input: Analysis results of strengths and weaknesses

[1933] Output: Exercises and explanations

[1934] Specific operation: The server uses the generative AI model to generate questions that focus on the user's weak areas and sends them to the device.

[1935] Step 8:

[1936] The user answers the exercises and sends the results from the terminal to the server.

[1937] Input: Exercises and user answers

[1938] Output: User answer data

[1939] Specific operation: The user answers the practice questions and sends the results to the server using the send button on the device.

[1940] Step 9:

[1941] The server evaluates the practice question answer data and generates feedback.

[1942] Input: User answer data

[1943] Output: Feedback

[1944] Specific operation: The server evaluates the answer data and uses a generative AI model to create detailed feedback for the user and send it to the device.

[1945] Step 10:

[1946] A server periodically evaluates the user's progress data and generates a customized learning curriculum that is regularly updated.

[1947] Input: User progress data

[1948] Output: Customized learning curriculum

[1949] Specific operation: The server evaluates the user's progress data, uses a generative AI model to generate an individually optimized learning curriculum, and sends it to the device.

[1950] Step 11:

[1951] The terminal displays the customized learning curriculum to the user.

[1952] Input: Customized Learning Curriculum

[1953] Output: Presentation of study schedule

[1954] Specific operation: The terminal displays the received curriculum to the user and indicates the specific content that should be studied next.

[1955] In this way, the entire system cooperates to provide effective learning support that meets the user's learning needs.

[1956] (Application example 1)

[1957] 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."

[1958] Conventional factory worker training systems have made it difficult to provide effective training programs tailored to the skill level of each worker. Standardized training programs cannot adequately reflect the actual abilities and progress of workers, resulting in reduced training efficiency. Customizing training content also requires a significant amount of time and effort, making it difficult to manage progress and provide feedback in real time.

[1959] 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.

[1960] In this invention, the server includes: means for receiving input information from a user and initializing the installation year, goals, strengths and weaknesses; means for saving the generated account ID and initial setting data in a database; means for performing a skill evaluation of the worker and identifying strengths and weaknesses; means for generating training modules and explanations focusing on the weaknesses; means for receiving the worker's answers, scoring, and returning the results; means for recording the worker's progress data and periodically generating feedback; means for presenting a customized training program to the worker; means for generating optimal training content for the worker using a generative AI model; and means for inputting prompts to the generative AI model and outputting the required training content. This enables the provision of an effective training program tailored to the skill level of each worker.

[1961] "User input" is data that operators use to communicate initial setup and individual training needs to the system.

[1962] "Year of installation" refers to the year in which the worker began performing the work.

[1963] "Goal" refers to a specific educational or skill-building goal that a worker seeks to achieve.

[1964] "Area of ​​expertise" refers to an area in which a worker has relatively high skills or knowledge.

[1965] "Weak areas" refer to areas in which a worker has relatively low skills or knowledge.

[1966] An "account ID" is an identifier generated to uniquely identify a worker within the system.

[1967] "Initial setting data" is data that collects setting information provided when an operator starts using the system.

[1968] "Skills assessment" is the process of analyzing a worker's current skill level and identifying their strengths and weaknesses.

[1969] An "educational module" is an educational unit that includes a series of instructional content for acquiring specific skills or knowledge.

[1970] "Explanation" refers to detailed explanatory text and illustrations that allow workers to understand the content contained in the training module.

[1971] An "answer" is a response that a worker submits to an educational module or test.

[1972] "Scoring" is the process of evaluating a worker's answers to determine their accuracy.

[1973] "Results" refers to the evaluation and feedback generated based on the worker's answers.

[1974] "Progress data" is data that records the progress of a worker's education and training.

[1975] "Feedback" refers to advice and evaluation provided to workers regarding their education and training progress.

[1976] A "training program" is a set of educational content customized to improve a worker's skills.

[1977] A "generative AI model" is an artificial intelligence model that is trained to perform a specific task based on large amounts of data.

[1978] A "prompt sentence" is an instruction sentence input to a generative AI model to instruct the worker on how to generate training content.

[1979] This invention relates to a head-mounted display (HMD) application for supporting worker training in factories and a training content generation system that uses a generative AI model. This system provides appropriate training programs according to the skill level of each worker, achieving efficient and effective training.

[1980] System configuration

[1981] The system consists of the following main components:

[1982] 1. User terminal: A head-mounted display (HMD) that allows workers to access the system and receive training content.

[1983] 2. Server: Performs database management, operation of generative AI models, skill evaluation, educational module generation, answer evaluation, and feedback provision.

[1984] 3. Database: Stores worker profile information, skill evaluation results, education history, training programs, etc.

[1985] Specific operation of the system

[1986] User registration and initial settings

[1987] When the user enters the required information (year of installation, goals, areas of strength and weakness) on the new registration screen, the device sends the data to the server. The server generates a new account ID based on the received data and saves the initial setting data in the database.

[1988] Skills Evaluation

[1989] When a user starts a skills assessment test, the device sends the request to the server. The server generates skills assessment questions according to the worker's role and sends them to the device. When the worker solves the questions and submits their answers, the server scores them and identifies the worker's strengths and weaknesses.

[1990] Creating an Educational Module

[1991] Based on the results of the skill assessment, the server generates an educational module and explanations that focus on the worker's weak areas. The terminal receives this and presents it to the worker. The user studies the educational module and sends the answer results from the terminal to the server. The server evaluates the answer and returns the results and feedback.

[1992] Providing feedback

[1993] The server evaluates the worker's progress based on the results of the training module and generates individual feedback, which is displayed to the worker on the terminal and suggests the next training step.

[1994] Customize your training program

[1995] The server periodically sets tests to evaluate the worker's progress. When the user takes the test, the server creates a customized training program based on the results and sends it to the terminal. The terminal then presents the training program to the worker, supporting their daily education.

[1996] Technology used

[1997] This system uses TensorFlow and Keras to build a generative AI model that evaluates worker skills and generates optimal training programs based on large amounts of data. It also uses an SQL database system for database management, processing and analyzing data in real time.

[1998] Specific examples

[1999] For example, when a new worker A is assigned to a factory, he or she is registered in the system. The initial setup involves entering the year of installation, training goals, areas of strength (e.g., machine operation), and areas of weakness (e.g., safety management). The system receives this information and generates an optimal training program based on it.

[2000] After taking the skill assessment test, the system evaluates Worker A's current skill level and generates a training module that focuses on his weaknesses. It then inputs the following prompt sentence into the generative AI model:

[2001] "Please assess the skill level of your workers and suggest appropriate training programs. The dataset is as follows: [example data]"

[2002] Based on this prompt, the most appropriate training content is generated and displayed on the HMD of Worker A. This allows Worker A to receive the training necessary to improve his or her skills in real time.

[2003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2004] Step 1:

[2005] The user enters the necessary information (year of establishment, goals, areas of strength, areas of weakness) on the new registration screen. The terminal sends the data to the server.

[2006] Input: Year of establishment, goals, areas of strength and weakness information

[2007] Output: Registration information sent to the server

[2008] Specific operation: The user inputs information using the HMD's user interface and presses the send button.

[2009] Step 2:

[2010] The server generates a new account ID based on the received data and stores the initial setting data in the database.

[2011] Input: Registration information

[2012] Output: Generated account ID and initial setting data

[2013] Specific operation: The server accesses the database, creates a new record, and automatically generates an account ID.

[2014] Step 3:

[2015] When a user starts a skill assessment test, the terminal sends the request to the server.

[2016] Input: Skills Assessment Test Request

[2017] Output: Request sent to the server

[2018] Specific operation: The user presses the evaluation test start button on the HMD.

[2019] Step 4:

[2020] The server generates skill evaluation questions according to the worker's role and sends them to the terminal.

[2021] Input: Role information

[2022] Output: Generated skill assessment questions

[2023] Specific operation: The server uses the generative AI model to generate an appropriate problem set and sends it to the device.

[2024] Step 5:

[2025] The user solves the problem and sends the answer from the terminal to the server.

[2026] Input: Worker's response

[2027] Output: The answer sent to the server

[2028] Specific operation: The user solves the problem using the HMD and presses the answer button to submit the result.

[2029] Step 6:

[2030] The server scores the answers and identifies the worker's strengths and weaknesses.

[2031] Input: Answer data

[2032] Output: Identification of strengths and weaknesses

[2033] What happens: The server uses a scoring algorithm to evaluate and identify answers.

[2034] Step 7:

[2035] Based on the results of the skills assessment, the server generates educational modules and explanations that focus on the worker's areas of weakness.

[2036] Input: Results of identifying strengths and weaknesses

[2037] Output: Educational modules and descriptions

[2038] Specific operation: The server inputs a prompt sentence into the generative AI model and generates educational content.

[2039] Step 8:

[2040] The server sends the generated educational module to the terminal, where the user receives it and begins learning.

[2041] Input: Education Module

[2042] Output: Educational module sent to the device

[2043] Specific operation: The server sends educational content to the terminal and it is displayed on the HMD.

[2044] Step 9:

[2045] The user studies the educational module and sends the answers from the terminal to the server.

[2046] Input: Learning results and answers

[2047] Output: Learning results and answers sent to the server

[2048] Specific operation: The user uses the HMD to learn, input and submit the results.

[2049] Step 10:

[2050] The server evaluates the answers and generates results and feedback.

[2051] Input: Learning results and answers

[2052] Output: Evaluation results and feedback

[2053] Specific operation: The server evaluates the answer using an answer evaluation algorithm and generates feedback.

[2054] Step 11:

[2055] The server evaluates the worker's progress based on the results of the training module and generates individual feedback.

[2056] Input: Answer evaluation result

[2057] Output: Individual feedback

[2058] What happens: The server analyzes the progress data and generates feedback.

[2059] Step 12:

[2060] The server creates a customized training program and sends it to the terminal, which presents it to the user.

[2061] Input: Individual feedback

[2062] Output: Customized training program

[2063] Specific operation: The server generates an educational program using the generative AI model and sends it to the device. It is then displayed on the HMD.

[2064] An example of a specific prompt would be, "Please assess the skill level of workers and suggest appropriate training programs. The dataset is as follows: [Example data]," and you can get output results from the generative AI model.

[2065] 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.

[2066] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[2067] System configuration

[2068] The system consists of the following main components:

[2069] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[2070] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[2071] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[2072] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[2073] Program processing overview

[2074] Each processing step of the program will be explained in detail from the perspectives of the user, the terminal, and the server.

[2075] User registration and initial settings

[2076] When a user enters the necessary information on the new registration screen, the device sends that data to the server, which then generates a new user ID based on the received data and saves the initial setting data in the database.

[2077] Academic ability analysis

[2078] When a user starts an academic ability diagnostic test, the device sends the request to the server. The server generates academic ability diagnostic questions appropriate for the user's grade and sends them to the device. When the user solves the questions and submits their answers, the server scores them and identifies the user's strengths and weaknesses.

[2079] Creating practice questions

[2080] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas. The device receives these and presents them to the user. The user answers the questions and sends the results from the device to the server. The server evaluates the answers and returns the results and feedback.

[2081] Emotion recognition and feedback provision

[2082] The device sends the user's facial and voice data to the emotion engine, which then uses this data to recognize the user's emotional state. After the user completes the exercise, the emotion data is also analyzed and appropriate feedback is generated. For example, if the user looks tired, the system may respond by displaying an encouraging message.

[2083] Creating a customized curriculum

[2084] The server periodically sets tests to evaluate the user's progress and emotional data. After the user takes the test, the server creates a customized learning curriculum based on the results and sends it to the device. The device then presents the curriculum to the user and supports their daily learning.

[2085] Specific examples

[2086] For example, consider the case where User A, a fifth-grader, newly registers with the system. User A initially enters his / her grade, learning goals, favorite subject (math), and weak subject (Japanese). The system saves User A's information in the database and then runs an academic ability diagnostic test. This test evaluates User A's current academic ability and provides important data for generating practice questions focused on specific areas.

[2087] For example, if the diagnostic results reveal that User A has difficulty with Japanese grammar, the system automatically generates grammar exercises and detailed explanations. User A answers these exercises and sends the answers to the server, which immediately scores them and provides feedback.

[2088] Furthermore, if the system's emotion engine analyzes User A's facial expression data and determines that User A is feeling stressed, it will take measures such as displaying encouraging messages and temporarily adjusting the difficulty level. Furthermore, a customized learning curriculum that is regularly updated based on User A's learning progress is generated, and specific content that should be learned next is presented.

[2089] In this way, the entire system works together to fully address the learning needs of each individual user, and by incorporating emotion recognition, it is possible to provide more effective and efficient learning support.

[2090] The processing flow will be explained below.

[2091] Step 1:

[2092] The user enters the required information on the new registration screen and presses the "Register" button.

[2093] Step 2:

[2094] The terminal transmits the input information to the server.

[2095] Step 3:

[2096] The server receives the input information, generates a new user ID, and saves the generated user ID and initial setting data in the database.

[2097] Step 4:

[2098] The user logs in, enters information on the screen for entering grade, learning goals, favorite subjects, and favorite subjects, and presses the "Save" button.

[2099] Step 5:

[2100] The terminal transmits the input initial setting information to the server.

[2101] Step 6:

[2102] The server receives the initial setting information and stores it in the user's profile data. The server prepares for the academic ability diagnostic test.

[2103] Step 7:

[2104] The user presses the "Start academic ability diagnostic test" button.

[2105] Step 8:

[2106] The terminal sends a request to start the academic ability diagnostic test to the server.

[2107] Step 9:

[2108] The server generates appropriate academic ability diagnostic questions according to the user's grade level and transmits them to the terminal.

[2109] Step 10:

[2110] The terminal displays the questions of the academic ability diagnostic test to the user.

[2111] Step 11:

[2112] The user solves the questions in the academic ability diagnostic test and inputs the answers to each question.

[2113] Step 12:

[2114] The terminal sequentially transmits the user's answers to the server.

[2115] Step 13:

[2116] The server scores the received answers and records whether each question is correct or incorrect.

[2117] Step 14:

[2118] The server analyzes the user's strengths and weaknesses based on all responses and generates a report of the results.

[2119] Step 15:

[2120] The terminal displays the academic ability analysis result report to the user.

[2121] Step 16:

[2122] Based on the results of the academic ability analysis, the server generates practice questions and explanations that focus on the user's weak areas.

[2123] Step 17:

[2124] The terminal displays the generated exercises and explanations to the user.

[2125] Step 18:

[2126] The user completes the exercises and enters the answers.

[2127] Step 19:

[2128] The terminal sends the user's answer to the server.

[2129] Step 20:

[2130] The server receives the answers, scores them, determines whether the answers are correct or incorrect, adds explanations, and generates an evaluation result.

[2131] Step 21:

[2132] The terminal displays the evaluation results and explanations to the user.

[2133] Step 22:

[2134] The device sends the user's facial expressions and voice data to the emotion engine.

[2135] Step 23:

[2136] The server analyzes the user's emotional data using an emotion engine, and generates an encouraging message if the user is feeling stressed.

[2137] Step 24:

[2138] The device displays emotion-based feedback messages to the user.

[2139] Step 25:

[2140] The server records the user's progress data and periodically generates feedback and learning progress reports.

[2141] Step 26:

[2142] The device displays feedback and learning progress reports to the user.

[2143] Step 27:

[2144] The server periodically sets academic ability assessment tests for the user and notifies the user.

[2145] Step 28:

[2146] The user takes the academic assessment test and enters the answers.

[2147] Step 29:

[2148] The terminal sends the user's answer to the server.

[2149] Step 30:

[2150] The server receives the answers to the academic assessment test and performs scoring and overall progress assessment.

[2151] Step 31:

[2152] The server generates a curriculum optimized for the user based on the test results.

[2153] Step 32:

[2154] The device displays the generated curriculum to the user and suggests the next learning step.

[2155] The above are the specific processing steps in a system that combines emotion engines. We have described in detail what operations the server, terminal, and user perform at each step.

[2156] Example 2

[2157] 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."

[2158] Conventional learning support systems lack the ability to customize to each user's academic ability and progress, making it difficult to provide effective practice questions for specific areas of weakness. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve motivation to learn or reduce stress. This limits the effectiveness of learning and makes it difficult to provide an optimal learning environment tailored to individual needs.

[2159] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2160] In this invention, the server includes: [means for receiving input information from a user and initializing the grade, learning goals, and areas of strength and weakness;] [means for storing the generated unique identifier and initial setting data in an information storage device; and] [means for performing an analysis of the user's academic ability and identifying areas of strength and weakness.] This makes it possible [to provide customized feedback and curriculum according to the user's individual learning needs].

[2161] "Information input from the user" refers to information provided by the system user, such as name, grade, learning goals, areas of strength and weakness, etc.

[2162] "Grade" is information that indicates the educational level or learning stage to which the system user belongs.

[2163] "Learning objectives" are the learning goals or objectives that system users want to achieve.

[2164] "Areas of expertise" refers to areas of study or subjects in which the system user has particular strengths.

[2165] "Weak areas" are areas of study or subjects that the system user is weak at.

[2166] "Initial settings" refers to basic settings that the system performs based on information input by the user.

[2167] A "unique identifier" is an ID generated to uniquely identify each user within the system.

[2168] An "information storage device" is a storage device used to store data within a system.

[2169] "Academic performance analysis" is the process by which the system evaluates a user's learning status and identifies their strengths and weaknesses.

[2170] "Practice questions" are a collection of questions provided by the system to improve the user's learning ability.

[2171] "Explanation" refers to supporting materials in the form of written, audio, or video that explain the answers and solutions to the practice problems.

[2172] "Answer" refers to the answer entered by the user to the exercise.

[2173] "Scoring" is the process of evaluating a user's answer and determining whether it is correct or not.

[2174] "Result" is information for providing feedback on the results of the scoring to the user.

[2175] "Progress data" is data that records the user's learning process and progress.

[2176] "Feedback" is reaction information including evaluation and advice regarding the user's learning activities.

[2177] A "learning plan" is a customized curriculum based on a user's learning goals and progress.

[2178] "Emotion data" is data that indicates the emotional state extracted from the user's facial expression and voice.

[2179] The "emotion engine" is a system function that analyzes the user's emotional data and evaluates the results.

[2180] A "generative AI model" is an artificial intelligence model that generates questions, explanations, and feedback that meet the user's needs.

[2181] MODE FOR CARRYING OUT THE INVENTION

[2182] This invention combines an emotion engine with a system that uses a study support tool equipped with a generative AI model to create a personal tutor suited to each user. This system analyzes the user's academic ability, provides individual practice problems, manages learning progress, and recognizes the user's emotional state to customize learning feedback and curriculum.

[2183] System configuration

[2184] The system consists of the following main components:

[2185] 1. User terminal: A device used by a user to access the system, such as a smartphone, tablet, or PC.

[2186] 2. Server: Database management, generative AI model, academic ability analysis, question generation, answer evaluation, feedback provision, and emotion recognition.

[2187] 3. Database: Stores user profile information, learning history, academic ability analysis results, practice questions, curriculum, emotional data, etc.

[2188] 4. Emotion Engine: A function for recognizing user emotions and analyzing and recording that data.

[2189] Program processing overview

[2190] User registration and initial settings

[2191] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[2192] Academic ability analysis

[2193] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[2194] Creating practice questions

[2195] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[2196] Emotion recognition and feedback provision

[2197] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[2198] Creating a customized curriculum

[2199] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[2200] This series of processes enables the system to optimally respond to the individual learning needs and emotional state of each user, providing an efficient and effective learning experience.

[2201] Prompt Sentence Examples

[2202] The system performs specific processing by issuing instructions to the generative AI model using prompt sentences. Below are some examples of prompt sentences.

[2203] "Generate language exercises for elementary school students. Focus on grammar."

[2204] "Generate encouraging messages based on the user's emotional data."

[2205] "Create a customized learning curriculum based on the results of your academic ability analysis."

[2206] As a result, the system of the present invention can provide optimal learning support by taking into account the learning needs and emotional state of each individual user.

[2207] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2208] Step 1: User registration and initial setup

[2209] explanation:

[2210] The user opens a new registration screen on a device such as a smartphone, tablet, or PC and enters the necessary information, such as name, grade, learning goals, and areas of strength and weakness. The device checks this input data in real time to verify that there are no errors. Once verification is complete, the device sends the data to the server. The server generates a unique identifier based on the received data and stores the ID and initial setting data in an information storage device.

[2211] input:

[2212] User name, grade, learning goals, strengths and weaknesses

[2213] Data processing:

[2214] The server validates the received data and generates a unique identifier.

[2215] output:

[2216] User ID, initial setting data

[2217] Specific behavior:

[2218] The server receives the user data sent from the terminal, generates a new user ID, and stores it in the information storage device.

[2219] Step 2: Academic performance analysis

[2220] explanation:

[2221] To take the academic ability diagnostic test, the user presses a start test button on their device. The device sends data requesting the academic ability diagnostic test to the server. The server uses a generative AI model to generate appropriate diagnostic questions for the student's grade and sends the questions to the device. The user solves the questions on the device and sends the answers from the device to the server. The server scores the received answers and uses the AI ​​model to identify the user's strengths and weaknesses.

[2222] input:

[2223] User's grade, test start request, and academic ability assessment answers

[2224] Data processing:

[2225] The server generates assessment questions, receives and grades answers, and identifies areas of strength and weakness.

[2226] output:

[2227] Generated diagnostic questions and analysis of strengths and weaknesses

[2228] Specific behavior:

[2229] The server generates academic ability diagnostic questions and sends them to the terminal. The user enters the answers, and the terminal sends them to the server for grading.

[2230] Step 3: Create an exercise

[2231] explanation:

[2232] Based on the results of previous academic ability analysis, the server uses a generative AI model to create practice questions and explanations that focus on the user's weak areas. The practice questions and detailed explanations are sent to the device, where the user receives them and begins answering them. After the user completes the answers, they send the answers from the device to the server. The server evaluates the answers and generates appropriate feedback, which is sent back to the device.

[2233] input:

[2234] Academic ability analysis results, user answers

[2235] Data processing:

[2236] The server generates practice questions based on the results of the academic ability analysis and evaluates the received answers.

[2237] output:

[2238] Generated exercises, evaluated answers, and feedback

[2239] Specific behavior:

[2240] The server generates exercises and explanations and sends them to the device. The user answers them and sends the answers from the device to the server. The server evaluates the answers and provides feedback.

[2241] Step 4: Recognize emotions and provide feedback

[2242] explanation:

[2243] While the user is answering questions, the device captures facial and voice data in real time through a camera and microphone. This data is sent to the server, where it is analyzed by an emotion engine. The server identifies the user's emotional state (e.g., stress, fatigue, satisfaction, etc.) and generates appropriate feedback and encouraging messages accordingly. The generated feedback is sent to the device and displayed to the user.

[2244] input:

[2245] User's facial expression data, voice data

[2246] Data processing:

[2247] The server uses an emotion engine to analyze the facial expression data and voice data to identify an emotional state.

[2248] output:

[2249] Sentiment analysis results and feedback

[2250] Specific behavior:

[2251] The device captures facial and voice data and sends it to a server, which analyzes the user's emotional state and generates appropriate feedback that is sent back to the device.

[2252] Step 5: Create a customized curriculum

[2253] explanation:

[2254] The server periodically evaluates the user's learning progress and emotional state. Based on the evaluation results, it sets a test containing the next learning content. The user takes the test and sends the test results from their device to the server. The server analyzes the results and customizes a learning curriculum. This curriculum is designed to strengthen the user's weak areas and further develop their strong areas. Once the curriculum is complete, it is sent to the device and presented to the user.

[2255] input:

[2256] User progress data, emotion data, test results

[2257] Data processing:

[2258] The server evaluates the progress data and emotional data and creates a new curriculum.

[2259] output:

[2260] Customized Curriculum

[2261] Specific behavior:

[2262] The server analyzes the progress data and emotion data, generates a customized curriculum for the user, and sends it to the device, which then displays it to the user.

[2263] Through these processing steps, the system can optimally respond to the individual learning needs and emotional state of the user, providing an efficient and effective learning experience.

[2264] (Application example 2)

[2265] 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."

[2266] Although systems that provide learning support tailored to individual academic ability already exist, there are still insufficient systems that can provide more effective learning support by recognizing the user's emotional state along with their learning progress and responding in real time.Therefore, there is a need to provide more personalized learning support that simultaneously considers the user's individual learning situation and emotional state.

[2267] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2268] In this invention, the server includes: [means for receiving user input information and initializing the grade, learning goals, and strong and weak subjects;] [means for saving the generated user ID and initial setting data in a database;] [means for performing an analysis of the user's academic ability and identifying strong and weak areas;] [means for generating practice questions and explanations focusing on weak areas;] [means for receiving the user's answers, grading, and returning the results;] [means for recording the user's progress data and generating periodic feedback;] [means for presenting a customized curriculum to the user; and] [means for recognizing the user's emotional state, analyzing and recording emotional data, and providing appropriate feedback. This makes it possible to provide study questions tailored to the user's individual academic ability, as well as to provide feedback and adjust the curriculum taking the user's emotional state into consideration.

[2269] "User" refers to the learner or individual receiving education who uses the system.

[2270] "Server" refers to the central computer system that processes and manages user input information, academic achievement data, emotional data, etc.

[2271] "Database" refers to a data repository for storing and managing user profile information, learning history, academic ability analysis results, emotional data, etc.

[2272] A "generative AI model" refers to an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, and so on.

[2273] An "emotion engine" is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[2274] "Initial setting data" refers to basic information such as grade level, learning goals, strong and weak subjects, etc., that a user enters when registering with the system.

[2275] "Academic Analysis" refers to the assessment process used to assess a user's academic ability and identify areas of strength and weakness.

[2276] "Practice Problems and Explanations" refers to information that explains problems and how to solve them, provided for the purpose of improving a user's academic ability.

[2277] "Feedback" refers to the evaluation and advice provided to a user regarding their learning progress and answer results.

[2278] "Customized curriculum" refers to an individualized learning plan that is tailored and optimized based on the user's academic ability and emotional state.

[2279] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, voice, actions, etc.

[2280] "Progress Data" means records and data relating to a User's learning progress.

[2281] The system for implementing this invention comprises a user terminal, a server, a database, a generative AI model, and an emotion engine.

[2282] The user terminal is a device such as a smartphone, tablet, or PC that the user uses to access the system. The server is a central computer system that processes and manages user input information, academic achievement data, emotional data, etc. The database is a data repository that stores and manages user profile information, learning history, academic achievement analysis results, emotional data, etc.

[2283] The generative AI model is an artificial intelligence system that analyzes a user's academic ability, generates study questions, provides feedback, etc. The emotion engine is a system that recognizes the user's emotional state, analyzes and records that data, and reflects it in feedback.

[2284] Program Processing Overview

[2285] The server receives input from the user and initializes the grade, learning goals, and strong and weak subjects. This initialization data is stored in a database. Next, it diagnoses the user's academic ability and identifies their strong and weak areas. It generates practice questions and explanations that focus on the weak areas, and when the user answers them, it grades the results and provides feedback. Feedback is generated periodically to effectively support the user's academic improvement.

[2286] Furthermore, the server records the user's progress data and presents a customized curriculum based on the progress. The emotion engine analyzes the user's facial and voice data to recognize their emotional state. Based on this, the server can provide appropriate feedback and encouraging messages and adjust the learning curriculum.

[2287] Specific example explanation

[2288] For example, if User A, a fifth-grader, uses this system, he or she will initially enter their grade, learning goals, favorite subject (math), and weak subject (Japanese). The system generates a user ID based on this information and stores the information in a database. Next, it conducts an academic ability assessment, and if it is determined that User A has a weakness in Japanese grammar, for example, appropriate practice questions and explanations will be generated.

[2289] While User A is working on a problem, if the emotion engine analyzes Us...

Claims

1. A means for receiving input information from a user and initializing the grade, learning goal, favorite subjects, and favorite subjects; A means for storing the generated user ID and initial setting data in a database; A means for analyzing a user's academic ability and identifying areas of strength and weakness; a means of generating practice questions and explanations that focus on weak areas; means for receiving the user's answers and returning the scores and results; a means for recording user progress data and generating periodic feedback; means for presenting a customized curriculum to a user; A system including:

2. The system of claim 1 , further comprising means for administering a diagnostic test to visualize the user's academic ability.

3. The system of claim 1 further comprising means for periodically assessing the user's progress and customizing the study plan through periodic testing.

Images