System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving information inputted when a user logs in for the first time, a means for generating a first set of questions based on the information inputted by the user, a means for displaying questions on a terminal of the user and prompting the user to input an answer, a means for receiving and analyzing answer information of the user, a means for optimizing and generating a next question to be given based on an answer result of the user, and a means for transmitting the optimized set of questions to the terminal of 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] Conventional problem sets and learning systems require students to solve predetermined problems, which does not fully address the needs of individual test takers. Specifically, they require students to repeatedly solve problems for which they have already mastered the solution method, making it difficult for them to efficiently overcome their weak areas. This problem tends to waste study time and reduce learning efficiency. Furthermore, it is difficult to develop individual strategies based on the question trends of the school of choice, making it difficult for test takers to achieve maximum results. Given these factors, there is a need for a system that can improve test takers' study efficiency and effectively overcome their weak areas. [Means for solving the problem]

[0005] In this invention, the system receives information entered by the user when they first log in and generates an initial problem set based on the information entered by the user. This problem set is then displayed on the user's device, allowing the user to enter answers. The system then receives and analyzes the answer information entered by the user, optimizing and generating the next problem based on the results. This optimized problem set is then sent back to the user's device to support repeated problem solving. In particular, the system uses a generative AI model to analyze the user's answering tendencies and areas of weakness, and optimizes the next problem by taking into account the accuracy rates of other users, thereby enabling efficient learning tailored to the needs of test-takers. This system maximizes test-takers' learning efficiency and effectively supports the improvement of individual academic abilities.

[0006] A "user" is a test-taker or learner who solves problems and learns.

[0007] "First time login" refers to the process in which a user accesses the system for the first time and enters individual learning information.

[0008] "Information" refers to data such as the school of choice, current academic level, and weak subjects that the user enters when logging in for the first time.

[0009] "Receiving" refers to the terminal sending the user's input information to the server and the information reaching the server.

[0010] A "problem set" is a collection of multiple problems that a user must solve, and is generated based on the information provided at the time of initial login.

[0011] "Generation" refers to the server selecting and combining appropriate questions from a question database based on the information entered by the user.

[0012] A "terminal" is a device used by a user to answer questions, and includes tablets, computers, etc.

[0013] "Display" refers to the terminal visually presenting the problem set received from the server to the user.

[0014] "Answer" refers to the user's action of answering a question using multiple choice options, text, or other methods.

[0015] "Analysis" is the process of analyzing the user's answer information received by the server and determining whether the answer is correct or incorrect and the tendency of the answer.

[0016] "Optimization" means that the server effectively adjusts the next question to be asked, taking into account the user's answering tendencies and areas of weakness.

[0017] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's answering tendencies and areas of weakness and generates appropriate questions.

[0018] The "correctness rate" is statistical data that indicates how many questions other users have answered correctly. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The system of the present invention dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[0041] System Overview

[0042] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0043] Initial setup and receiving information

[0044] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[0045] Problem set generation

[0046] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions covering a wide range of subjects, with a particular emphasis on subjects in which the user is weak. The generated set of questions is sent to the terminal and displayed to the user.

[0047] Answer to the question

[0048] The user inputs answers to the displayed questions. Answers can be in multiple formats, such as multiple choice or written answers. The device records the user's answers and the time they took to answer them, and sends them to the server.

[0049] Answer analysis and feedback

[0050] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0051] Dynamic Problem Generation

[0052] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the device and presented to the user.

[0053] Specific examples

[0054] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency, such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0055] By repeating this process, users can focus on strengthening their weak areas and study more efficiently.

[0056] Feedback and progress management

[0057] The server periodically generates a report that provides feedback on the user's learning progress, including areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[0058] The above is a specific embodiment of the system of the present invention, which allows users to efficiently overcome their weak areas and maximize their learning efficiency.

[0059] The processing flow will be explained below.

[0060] Program processing steps

[0061] Initial setup and receiving information

[0062] Step 1:

[0063] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[0064] Step 2:

[0065] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[0066] Step 3:

[0067] The server stores the received user information in a database and simultaneously creates a user profile.

[0068] First question generation and question submission

[0069] Step 4:

[0070] The server generates an initial set of problems based on the user's profile, selecting problems from a database of problems evenly across a wide range of subjects.

[0071] Step 5:

[0072] The server sends the generated question set to the terminal, including the question ID, question text, and choice data.

[0073] Step 6:

[0074] The terminal displays the received problem set to the user, and displays the problems and options on the user interface.

[0075] Enter your answer

[0076] Step 7:

[0077] The user can enter answers to the questions displayed, either by selecting options or by entering a written answer.

[0078] Step 8:

[0079] The terminal sends the user's answer data to the server, which includes the question ID, the choice number or written answer, and the answer time.

[0080] Answer analysis and feedback

[0081] Step 9:

[0082] The server analyzes the received answer data, determines whether the answer is correct, and records the time it took to answer.

[0083] Step 10:

[0084] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[0085] Generation and presentation of next questions

[0086] Step 11:

[0087] The server generates the next set of questions based on the latest user data, using a generative AI model to select questions that are specific to the user's weak areas.

[0088] Step 12:

[0089] The server sends the newly generated problem set to the terminal.

[0090] Step 13:

[0091] The terminal displays a new set of questions to the user, who then answers the questions again to continue the cycle.

[0092] Feedback and progress management

[0093] Step 14:

[0094] The server periodically compiles the user's learning progress and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[0095] Step 15:

[0096] The device displays a feedback report to the user, who can then use the feedback to further their learning.

[0097] The above are the specific processing steps of this system, which makes it possible to maximize the user's learning efficiency.

[0098] Example 1

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

[0100] Conventional learning systems have difficulty maximizing individual users' learning efficiency, and have not been able to dynamically generate questions that correspond to a user's strengths and weaknesses. It has also been difficult to analyze a user's learning progress in real time and provide optimal feedback.

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

[0102] In this invention, the server includes means for receiving information entered by a user at initial login, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, means for recording answer times, and means for generating feedback based on user progress data. This maximizes the learning efficiency of each user and enables effective learning progress management and feedback provision.

[0103] "User" refers to an individual who uses the system to learn.

[0104] "First login" refers to the moment when a user accesses the system for the first time, enters authentication information, and begins use.

[0105] "Terminal" refers to an electronic device such as a computer or smartphone that a user uses to input or display data.

[0106] "Server" refers to the central computer system on the network that processes and stores user information and performs problem generation and analysis.

[0107] "Database" refers to a storage device or system in which user information, question sets, answer data, etc. are structured and stored.

[0108] A "problem set" refers to a collection of multiple study questions provided to a user.

[0109] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a user's answering tendencies and areas of weakness and generates the optimal set of questions.

[0110] "Answer information" refers to the content of the answer entered by the user to the question and related data such as the answer time.

[0111] "Analysis" refers to the process by which the server evaluates the answer information received, determines whether each question is correct, and analyzes the user's learning tendencies.

[0112] "Optimization" refers to the process of adjusting the next question based on the user's progress and tendencies.

[0113] "Feedback" refers to providing users with analysis and advice on their learning results and progress.

[0114] The system of the present invention is designed to maximize the learning efficiency of each individual user. A specific embodiment of the program of this system will be described in detail below.

[0115] Entering and receiving user information

[0116] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is entered via a web form or a dedicated mobile application. The entered information is sent to the server via the device. The server receives this information and stores it in a database.

[0117] Generating the initial problem set

[0118] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions, focusing on subjects the user is weak at. A generative AI model is used to select the questions, and the AI ​​model adjusts the difficulty and content of the questions.

[0119] Displaying questions and entering answers

[0120] The generated problem set is sent to the terminal and displayed to the user. The user inputs answers to the displayed problems. The answer format can be multiple choice or written, and the terminal records the answer data and the answer time.

[0121] Sending and analyzing answer data

[0122] The device sends the user's answer data to the server. The server analyzes the received data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0123] Dynamic problem generation and feedback

[0124] The server generates the next set of questions based on the user's latest progress data. This process uses a generative AI model, taking into account the user's answering tendencies and the accuracy rates of other users. The optimized set of questions is then sent back to the device and provided to the user. The server also periodically generates a report that provides feedback on the user's learning progress and displays it on the user's device. This report includes the user's achievement level, areas for improvement, and advice on the next study plan.

[0125] Specific examples

[0126] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set that includes many basic math problems. This includes calculation problems, formula transformations, and basic geometry problems. After the user solves the problems, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0127] Prompt Sentence Examples

[0128] Here are some examples of prompts for generative AI models:

[0129] "User's answer:

[0130] - Calculation problem: 90 points (answer time: average 30 seconds)

[0131] - Mathematical transformation: 60 points (answer time: 90 seconds on average)

[0132] Problems to include in the next problem set:

[0133] 1. Add basic problems on formula transformation

[0134] 2. Include calculation questions as appropriate

[0135] 3. Add new geometry problems.

[0136] The AI ​​model then generates an optimized set of questions for the next problem based on this prompt. This completes the concrete implementation of the present invention, allowing users to study efficiently and focus on overcoming their weak areas.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Enter and submit your user information

[0139] When a user logs in for the first time, they enter information into the terminal, such as their preferred school, current academic level, strong and weak subjects, etc. The input data is saved on the terminal and later sent to the server.

[0140] Specific behavior:

[0141] A user fills out a web form or mobile application.

[0142] The input data is converted to JSON format.

[0143] The terminal transmits the data to the server.

[0144] Input: desired school, academic level, strong subjects, weak subjects

[0145] Output: User information sent to the server

[0146] Step 2: Server receives information and creates profile

[0147] The server receives the information sent by the user and stores it in a database, which creates a profile for each user.

[0148] Specific behavior:

[0149] The server receives an HTTP request from the device.

[0150] The received data is stored in a database and a user profile is generated.

[0151] Input: User information sent from the device

[0152] Output: User profile stored in the database

[0153] Step 3: Generate the initial problem set

[0154] The server generates an initial problem set based on the user profile, selects relevant problems from a problem database, and generates an optimal problem set using a generative AI model.

[0155] Specific behavior:

[0156] The server looks up the user profile.

[0157] Query the issues database to get a list of issues.

[0158] A generative AI model selects and refines the problems to generate an initial set of problems.

[0159] Input: User profile information

[0160] Output: The generated initial problem set

[0161] Step 4: View the question and enter your answer

[0162] The terminal displays the problem set received from the server to the user, who then inputs the answers to the problems. The answers are recorded along with the answer time.

[0163] Specific behavior:

[0164] The device parses the JSON formatted problem data it receives and formats it for display.

[0165] The user enters the answer and the terminal records it.

[0166] Input: Generated initial problem set

[0167] Output: Answer data entered on the terminal and answer time

[0168] Step 5: Submit your answers

[0169] The terminal transmits the user's answer data and answer time to the server.

[0170] Specific behavior:

[0171] The device converts the answer data into JSON format.

[0172] Send the data to the server.

[0173] Input: Answer data and answer time entered into the terminal

[0174] Output: Answer data and answer time sent to the server

[0175] Step 6: Answer analysis and feedback generation

[0176] The server analyzes the received answer data and determines whether it is correct or incorrect. It also evaluates the answer time and answer tendency to identify the user's weak areas. The analysis results are saved in a progress database and used to generate the next problem set.

[0177] Specific behavior:

[0178] The server inputs the answer data into the analysis engine.

[0179] The answers are judged to be correct or incorrect, and the evaluation results are stored in a database.

[0180] Input: Answer data and answer time sent to the server

[0181] Output: Analysis results and updated user profile

[0182] Step 7: Dynamic question generation and distribution

[0183] The server generates the next set of problems based on the user's latest progress data. The generative AI model optimizes the problems by taking into account the user's learning habits and other user data. The optimized set of problems is then sent to the device.

[0184] Specific behavior:

[0185] The server references the user's progress data.

[0186] The generative AI model generates the next set of problems.

[0187] Send the problem set to the device.

[0188] Input: Updated user profile and progress data

[0189] Output: The next optimized problem set

[0190] Step 8: Feedback on learning progress

[0191] The server periodically generates a report that provides feedback on the user's learning progress and sends it to the user's device, including the user's achievement level, areas for improvement, and advice on the next learning plan.

[0192] Specific behavior:

[0193] The server analyzes the progress data and generates a feedback report.

[0194] The feedback report is formatted in PDF or HTML format and sent to the device.

[0195] Input: Updated user profile and progress data

[0196] Output: A feedback report that is displayed to the user

[0197] (Application example 1)

[0198] 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."

[0199] Conventional learning systems have the problem of reducing learning efficiency because they are unable to provide questions tailored to each user's academic ability or specific areas of interest.In addition, they lack the technology to dynamically optimize and provide questions based on a detailed analysis of the user's progress and answer trends, making it difficult to maximize the user's learning proficiency.

[0200] 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.

[0201] In this invention, the server includes means for receiving information entered by the user when logging in for the first time, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, and means for generating and providing a report that provides feedback on the user's learning progress based on the user's answers. This allows the user's learning progress to be dynamically optimized, enabling efficient learning that focuses on specific areas of interest or weak areas.

[0202] "Information entered by the user at the time of initial login" refers to data such as personal information, learning goals, areas of strength and weakness, etc., provided by the system user at the time of initial login.

[0203] "Generating an initial problem set" refers to the process of creating problems that correspond to the current knowledge level and interests of each individual learner based on the received user information.

[0204] A "user device" is an electronic device used by a user to solve problems and input answers, including a smartphone, tablet, or PC.

[0205] "Receiving and analyzing answer information" refers to the process in which the server receives the answers to the questions entered by the user and evaluates whether they are correct or not and the tendency of the answers.

[0206] "Generating optimal questions for the next test" means dynamically generating new questions that address the user's specific needs and weak areas based on the analyzed answer information.

[0207] "Sending the optimized problem set to the user's terminal" means delivering the generated new problem set to the user's learning device.

[0208] "Generating and providing a report that provides feedback on learning progress" refers to the process of creating a report that visually shows the user's learning situation and progress, and supporting the user with instruction and future learning plans.

[0209] The present invention is a system that dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[0210] 1. User information registration

[0211] When a user logs in for the first time, they enter information such as their preferred school, current academic level, strong and weak subjects, etc. This information is sent to the server via the user's terminal.

[0212] 2. Generating the initial problem set

[0213] Based on the received information, the server generates an initial problem set that is tailored to the learner's current level of knowledge and specific areas of interest, with a particular focus on subjects in which the user is weak.

[0214] 3. Displaying and answering questions

[0215] The generated question set is displayed on the user's device, and the user inputs answers to the questions. Answers can be in various formats, such as multiple choice or written answers. The answers entered by the user are sent to the server via the device.

[0216] 4. Answer Analysis

[0217] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The results of this analysis are stored in the user's progress database.

[0218] 5. Generation of the next problem set

[0219] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the user's device and presented to them.

[0220] 6. Feedback and progress management

[0221] The server periodically generates a report that provides feedback on the user's learning progress. This report includes the user's learning status, areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[0222] Specific examples

[0223] For example, if a user wants to learn something specific in a particular field or area of ​​interest, the first time the system generates questions such as "calculating the optimal number of inventory orders" or "simulating handling complaints." Once the user solves these, the server analyzes the answers and evaluates their performance in that particular field. Based on this result, the next time the system presents questions tailored to the user's progress and areas of weakness.

[0224] The hardware used includes "user devices" such as smartphones, tablets, and PCs, as well as "servers" that connect to these devices. The software uses programming languages ​​such as Python to implement generative AI models.

[0225] Prompt Sentence Examples

[0226] "What are some effective ways to improve customer satisfaction?"

[0227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0228] Step 1:

[0229] When a user logs in for the first time, they enter information such as their preferred school, current academic ability, and strong and weak subjects into their device. The server receives this information and stores it in a database. The input data includes the user's personal information, and a user profile is created based on this information.

[0230] Input: Information such as desired school, current academic ability, strong subjects, weak subjects, etc. entered by the user into the device.

[0231] Output: The user profile stored on the server.

[0232] Step 2:

[0233] The server generates an initial problem set based on the user's profile. Using a generative AI model, it selects problems from a variety of areas, focusing on the user's weak areas. This problem set is then sent to the device and displayed to the user.

[0234] Input: User profile, problem database.

[0235] Output: The initial problem set displayed on the user's device.

[0236] Step 3:

[0237] The user inputs answers to the questions displayed on the terminal. Answers can be in multiple formats, such as multiple choice or written format, and the terminal records the user's answers and the time it took to answer them, and sends them to the server.

[0238] Input: The answer to the question that the user types into the terminal.

[0239] Output: Answer data sent to the server (answer content, answer time).

[0240] Step 4:

[0241] The server analyzes the received answer data, determines whether each question is correct, and evaluates the answer time and answer trends. Based on the analysis results, the user's progress database is updated.

[0242] Input: The answer data sent to the server.

[0243] Output: Correct / incorrect result, update of user's progress database.

[0244] Step 5:

[0245] The server generates the next set of problems based on the latest progress data. Using a generative AI model, it creates optimized problems that take into account the user's answering tendencies and the accuracy rates of other users, and sends them to the device.

[0246] Input: User progress database, question database.

[0247] Output: The optimized next problem set, the problem set sent to the device.

[0248] Step 6:

[0249] The server periodically generates a report that provides feedback on the user's learning progress. The report includes the user's learning status, areas for improvement, achievement goals, and advice on future learning plans, and is sent to the user's terminal and displayed to the user.

[0250] Input: User progress database.

[0251] Output: Feedback report, report displayed on terminal.

[0252] Step 7:

[0253] The user can check the feedback report through their device and reflect it in their next study. This makes it easier to study efficiently and continue. For example, if a user receives feedback that they are "strong at calculation problems but weak at formula transformations," the next problem set will include many formula transformation problems. This will allow them to improve their weak areas.

[0254] Input: Feedback report.

[0255] Output: Next lesson plan, user progress improvement.

[0256] 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.

[0257] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can further maximize individual learning efficiency and improve the user's learning experience.

[0258] System Overview

[0259] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0260] Emotion engine integration

[0261] The present invention incorporates an emotion engine that recognizes the emotions of users when answering questions. The emotion engine detects user emotions using facial recognition, voice tone analysis, and even biometric data (such as heart rate).

[0262] Initial setup and receiving information

[0263] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[0264] Problem set generation

[0265] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. In addition, the server also performs initial settings to match the emotion engine.

[0266] Answer to the question

[0267] The user enters the answer to the displayed question. At this time, the emotion engine installed in the device analyzes the user's face and voice in real time to obtain emotional data. This emotional data is sent to the server along with the answer data.

[0268] Answer analysis and feedback

[0269] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the time it takes to answer and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. These analysis results are stored in the user's progress database and are used to generate the next set of questions to be presented.

[0270] Dynamic Problem Generation

[0271] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[0272] Specific examples

[0273] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0274] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[0275] Feedback and progress management

[0276] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes areas for improvement, achieved goals, and advice on the next learning plan. The device displays this feedback report to the user to support their learning.

[0277] The above is a specific embodiment of the system of the present invention, which allows users to focus on strengthening their weak areas and study efficiently while receiving emotional support.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[0281] Step 2:

[0282] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[0283] Step 3:

[0284] The server stores the received user information in a database and creates a user profile.

[0285] Step 4:

[0286] The server generates an initial problem set based on the user profile. The server selects a wide range of problems from the problem database and provides the user with a set that includes cross-disciplinary problems.

[0287] Step 5:

[0288] The server sends the generated question set to the terminal, which includes the question ID, question text, and choice data.

[0289] Step 6:

[0290] The terminal displays the received problem set on the interface and asks the user questions.

[0291] Step 7:

[0292] The user enters answers to the displayed questions, while the device's built-in camera and microphone simultaneously analyze the user's facial expressions and tone of voice to obtain emotional data.

[0293] Step 8:

[0294] The device simultaneously transmits answer data and emotion data to the server, which includes the question ID, multiple choice or written answer, answer time, and emotion data.

[0295] Step 9:

[0296] The server analyzes the received answer data and emotion data, determining whether the answer was correct or incorrect and evaluating the response time and emotion fluctuations. For example, if there were many emotions indicating anxiety, that evaluation will also be included.

[0297] Step 10:

[0298] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[0299] Step 11:

[0300] The server generates the next set of questions based on the latest user data and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's answering tendencies and emotional data.

[0301] Step 12:

[0302] The server sends the generated problem set to the terminal.

[0303] Step 13:

[0304] The terminal displays the newly generated problem set to the user, who then answers the problems again.

[0305] Step 14:

[0306] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[0307] Step 15:

[0308] The device displays the generated feedback report to the user, who can then create a new study plan based on the feedback and begin their next study.

[0309] The above is a description of the specific processing steps of the system. By optimizing the user's learning experience through the analysis of emotion data, users can learn efficiently and effectively.

[0310] Example 2

[0311] 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."

[0312] Current educational systems struggle to fully consider each user's individual academic ability, learning attitude, and emotional state, making it difficult to maximize individual learning efficiency. Furthermore, they lack the ability to present adaptive questions based on the user's progress and emotions, resulting in a lack of improvement in the user's learning experience.

[0313] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for acquiring and receiving the user's emotional data, means for optimizing and generating the next problem to be posed based on the user's answer results and emotional data, and means for transmitting the optimized problem set to the user's terminal. This enables more personalized learning that takes into account the user's individual academic ability and emotional state.

[0314] "User" refers to an individual who uses this system to advance their learning.

[0315] "Terminal" refers to an electronic device that is operated by a user to display questions and input answers.

[0316] "Server" refers to a central processing unit that receives and analyzes data sent from terminals, and generates and sends problem sets.

[0317] "Input information" refers to information related to learning that a user provides when logging in for the first time, and specifically includes personal information, learning goals, desired schools, strong subjects, weak subjects, etc.

[0318] A "problem set" refers to a series of questions that are presented to a user.

[0319] "Answer information" refers to the data of the answer entered by the user to the question.

[0320] "Emotional data" refers to data on the emotional state obtained by analyzing information such as facial recognition, voice tone, and heart rate obtained when the user answers questions.

[0321] "Progress data" refers to data that indicates the user's learning progress and results.

[0322] A "generative AI model" refers to an artificial intelligence model used to analyze a user's answering tendencies and areas of weakness, and optimize the next questions to be asked.

[0323] This invention is a dynamic question generation system for improving the user's learning experience, and aims to maximize the user's learning efficiency by utilizing an emotion engine and a generative AI model. This system comprehensively covers a series of processes, from initial setup to question generation, answer analysis, next question generation, and feedback.

[0324] Hardware and software used

[0325] The system uses the following main hardware and software:

[0326] Server: Receives data, analyzes it, generates questions, and provides feedback. Specifically, it uses Python scripts, a SQL database, and generative AI models.

[0327] Terminal: A device (PC, tablet, smartphone) operated by the user that displays questions, inputs answers, and acquires emotional data. It has a built-in camera and microphone, and analyzes the user's face and voice tone in real time.

[0328] Emotion Engine: Analyzes user emotions based on biometric data such as facial recognition, voice tone analysis, and heart rate. Provides an API for sending data to the server.

[0329] Initial setup and receiving information

[0330] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. This information is sent to the server via their device. The server stores the received information in a database and creates a user profile based on it.

[0331] Problem set generation

[0332] The server generates an initial set of questions based on the user's profile, randomly selects questions from the question database, and focuses on subjects the user is weak in. It also initializes the emotion engine.

[0333] Answering questions and obtaining emotion data

[0334] The user inputs their answers to the displayed questions. The device uses a built-in camera and microphone to recognize the user's face and analyze their voice tone in real time to obtain emotional data. This data is then sent to the server along with the answer data.

[0335] Answer analysis and feedback

[0336] The server receives the answer data and emotion data and begins analysis using a Python script. It determines whether the answer is correct, evaluates the answer time, analyzes emotional fluctuations, and generates appropriate feedback. If the user feels stressed by a particular problem, it adjusts the difficulty and content of the problem. The analysis results are saved in a progress database and are used to generate the next set of problems.

[0337] Dynamic Problem Generation

[0338] The server generates the next set of questions based on the latest progress and emotional data. It uses a generative AI model to select the most appropriate questions, taking into account the user's weak areas and emotional state. The optimized set of questions is then sent to the device, where it is presented to the user again.

[0339] Providing feedback

[0340] The server periodically collects the user's progress and emotion data and generates a feedback report, which includes areas for improvement, achieved goals, and advice for the next learning plan. The device displays this feedback report to the user to support their learning.

[0341] Specific examples

[0342] For example, consider a case where a user wants to go to university but is not good at math when logging in for the first time. The server generates a problem set containing many basic math problems and presents it to the user. This set includes calculation problems, formula transformations, and basic geometry problems. When the user answers these, the server analyzes the answers and identifies tendencies such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0343] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[0344] Prompt Sentence Examples

[0345] For example, by inputting a prompt such as, "Give a third-year high school student who is not good at transforming mathematical formulas some problems that require them to transform mathematical formulas. Gradually increase the difficulty so that the student does not feel stressed when solving the problems. Add hints to each problem and provide feedback after the student answers," into a generative AI model, a problem set optimal for specific learning needs and emotional state can be generated.

[0346] The above is a specific embodiment of the present invention. By using this system, users can obtain an optimal learning experience that takes into account their individual academic ability and emotional state.

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

[0348] Divide the processing flow of the system program into processing steps

[0349] Step 1:

[0350] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. The input data is saved on the device in JSON format and then sent to the server.

[0351] Step 2:

[0352] When the device receives the user's input data, it sends it to the server using the HTTPS protocol. The server receives the data and stores it in a MySQL (registered trademark) database. This creates a user profile.

[0353] Step 3:

[0354] The server generates an initial set of questions based on the user's profile, randomly selects questions from a database of questions using SQL queries, and sends the resulting set of questions to the device in JSON format.

[0355] Step 4:

[0356] The device displays the received problem set to the user, who then enters answers to the displayed problems, and the answer data is saved in JSON format on the device.

[0357] Step 5:

[0358] The emotion engine installed on the device analyzes the user's face, voice tone, and heart rate in real time to obtain emotion data, which is then sent to the server along with the answer data.

[0359] Step 6:

[0360] The server analyzes the answer data and emotion data received. Using a Python script, it determines whether the answer is correct, evaluates the answer time, and analyzes emotional fluctuations, and creates an adjustment plan if the user is feeling stressed by a particular problem. The results of this analysis are stored in a progress database.

[0361] Step 7:

[0362] The server generates the next set of problems based on the user's latest progress and emotional data. It uses a generative AI model to select the most appropriate problems based on the user's weak areas and emotional state. The generated problem set is sent to the device in JSON format.

[0363] Step 8:

[0364] The device displays the optimized problem set to the user, and at the same time, a feedback report is sent from the server and displayed on the device, including areas for improvement, goals achieved, and advice for the next study plan.

[0365] Detailed explanation of each processing step

[0366] Step 1:

[0367] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, strong and weak subjects in a dedicated input form. For example, if a user enters "I'm not good at math," the device converts this into JSON format, saves it, and sends it to the server.

[0368] Step 2:

[0369] Once the device receives the user's input data, it sends it to the server via an HTTPS request. The server receives the data and stores it in a MySQL database. This creates a user profile, including initial settings based on the user's learning goals and preferred schools.

[0370] Step 3:

[0371] The server uses SQL queries to select questions related to the subjects the user is weak at from the question database. It then generates the initial question set and sends it to the device in JSON format. For example, if the user enters "I'm weak at math," a question set containing many basic math questions will be generated.

[0372] Step 4:

[0373] The device displays the received problem set to the user. The user answers the problems, and the answer data is saved on the device. For example, problems involving integer calculations and transformations of basic mathematical expressions are included.

[0374] Step 5:

[0375] The emotion engine installed on the device detects the user's face and voice in real time through facial recognition, voice tone analysis, heart rate, etc. to obtain emotion data. This data is sent to the server along with the answer data. For example, if the user is confused by a mathematical transformation problem, the emotion engine will obtain that data.

[0376] Step 6:

[0377] The server analyzes the answer data and emotion data it receives. A Python script is used to determine whether the answer is correct, and to analyze the time it took to answer and fluctuations in the user's emotions. If it determines that a particular problem is causing stress to the user, the difficulty and content of the next problem can be adjusted. For example, if it takes a long time to transform a mathematical formula, a plan can be made to focus on that part of the problem.

[0378] Step 7:

[0379] The server uses the generative AI model to generate the next set of problems based on the latest progress data and emotion data. An example prompt might be, "For a high school senior who is not good at transforming mathematical formulas, please provide mathematical formula transformation problems with gradually increasing difficulty." This optimizes the generated problem set and sends it to the device in JSON format.

[0380] Step 8:

[0381] The device displays the optimized problem set to the user. At the same time, a feedback report is sent from the server and displayed on the device. The feedback report includes advice such as, "You seemed confused when transforming the formula. Please focus on this part next time."

[0382] These are the specific processing steps of the system according to the present invention, which allows users to have a more efficient and personalized learning experience.

[0383] (Application example 2)

[0384] 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."

[0385] Conventional learning systems generate questions based solely on the user's answers, making it difficult to maximize individual learning efficiency. Furthermore, they generate questions without considering the user's emotional state, which can lead to stress and anxiety, potentially resulting in a poor learning experience. This makes it impossible to provide consistently effective learning support to a diverse range of learners.

[0386] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for optimizing and generating the next problem to be presented based on the user's answer results, means for transmitting the optimized problem set to the user's terminal, emotion recognition means for analyzing the user's emotion data, and means for adjusting the difficulty level of the problems taking the user's emotion data into consideration. This makes it possible to dynamically generate optimal problems based on the individual learning progress while taking the user's emotions into consideration.

[0387] A "user" is an individual who uses this system to study.

[0388] "Information entered at first login" refers to data such as learning goals, current academic level, desired school, strong and weak subjects, etc. that a user enters when using the system for the first time.

[0389] A "problem set" is a collection of multiple problems generated by the server based on the user's academic ability and learning goals.

[0390] A "terminal" is a device that a user uses to answer questions, such as a smartphone, tablet, or computer.

[0391] "Emotion data" is data that indicates the user's emotional state, and is information obtained through facial recognition, voice tone analysis, biological reactions, and the like.

[0392] "Answer information" is data that includes the content of the user's answer and the result of whether it was correct or incorrect.

[0393] The "answer result" is data on whether the answer is correct or incorrect based on the answer entered by the user.

[0394] A "generative AI model" is an algorithm that uses artificial intelligence to analyze a user's answering tendencies and areas of weakness, and then generates new questions.

[0395] "Emotion recognition means" refers to technology and devices for analyzing emotions from a user's facial expressions and voice.

[0396] The "means for adjusting the difficulty level" refers to a method and algorithm for appropriately adjusting the difficulty of questions to be posed, taking into account the user's emotional data.

[0397] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can maximize individual learning efficiency and improve the user's learning experience.

[0398] System Overview

[0399] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. The problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0400] Emotion engine integration

[0401] The present invention incorporates an emotion engine that recognizes the user's emotions when answering questions. The emotion engine detects the user's emotions using facial recognition, voice tone analysis, and even biological response data (such as heart rate). This makes it possible to present questions that correspond to the user's emotional state.

[0402] Initial setup and receiving information

[0403] The server receives data such as personal information, learning goals, preferred schools, and strong and weak subjects entered by the user when they first logged in. This data is sent to the server and stored in a database. The server then creates a user profile based on this data.

[0404] Problem set generation

[0405] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. It also performs initial settings to match the emotion engine.

[0406] Answer to the question

[0407] The user enters an answer to the displayed question. At this time, the emotion engine installed on the device analyzes the user's face and voice in real time to obtain emotional data. The obtained answer data and emotional data are then sent to the server.

[0408] Answer analysis and feedback

[0409] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the answer time and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. The results of this analysis are stored in the user's progress database and are used to generate the next set of questions.

[0410] Dynamic Problem Generation

[0411] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[0412] Specific examples

[0413] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these problems, the server analyzes the answers and identifies a tendency for the user to be "good at calculations but take a long time to transform formulas." Based on this analysis, the next problem set will include more formula transformation problems. Furthermore, if the emotion engine determines that the user feels anxious about solving formula transformation problems, the server will generate a set that includes problems of gradually increasing difficulty and problems with many hints to alleviate the anxiety.

[0414] Example prompts to input to a generative AI model:

[0415] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[0416] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[0417] Generate a suitable problem set.

[0418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0419] Step 1:

[0420] When a user logs in for the first time, they enter data such as personal information, learning goals, preferred schools, and strong and weak subjects. When the user enters this information into a dedicated form on their device and presses the send button, the data is sent from the device to the server. The input data includes learning goals, current academic level, preferred schools, strong and weak subjects, etc. The server receives this data and stores it in a database.

[0421] Step 2:

[0422] The server generates an initial problem set based on the received user data. It creates a well-balanced problem set, taking into account the user's strong and weak subjects. It randomly selects problems from a variety of fields from the problem database. It generates the initial problem set, placing particular emphasis on subjects the user is weak in. The generated problem set is sent to the terminal and displayed on the screen.

[0423] Step 3:

[0424] The terminal provides a UI that allows the user to input answers to the displayed problem sets. The user answers the problems and enters the results into the terminal. The input answer information is sent to the server via the terminal.

[0425] Step 4:

[0426] The emotion engine installed on the device captures emotional data in real time while the user answers questions. This is done by using a camera and microphone to recognize faces, analyze voice tones, and capture biometric data. This allows the user's emotional state, such as stress, anxiety, or happiness, to be analyzed. The captured emotional data is sent to the server along with the answer data.

[0427] Step 5:

[0428] The server analyzes the received answer data and emotional data. First, it determines whether each question is correct based on the answer data, and analyzes the user's answering tendencies and areas of strength and weakness. At the same time, it analyzes the emotional data and evaluates fluctuations in the user's emotions. For example, it can detect an increase in stress level in response to a particular question. The analysis results are stored in the user's progress database.

[0429] Step 6:

[0430] The server generates the next set of questions based on the user profile, answers, and emotional data. It uses a generative AI model to generate and apply prompts such as:

[0431] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[0432] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[0433] Generate a suitable problem set.

[0434] The generated problem set is adjusted to include the most appropriate problems, taking into account the user's weak areas and emotional state.

[0435] Step 7:

[0436] The server then sends the optimized problem set to the user's device. The next time the user studies, they can receive the newly generated problem set and continue studying. Through this process, the user can continuously enjoy a personalized learning experience.

[0437] 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.

[0438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0439] 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.

[0440] [Second embodiment]

[0441] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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."

[0453] The system of the present invention dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[0454] System Overview

[0455] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0456] Initial setup and receiving information

[0457] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[0458] Problem set generation

[0459] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions covering a wide range of subjects, with a particular emphasis on subjects in which the user is weak. The generated set of questions is sent to the terminal and displayed to the user.

[0460] Answer to the question

[0461] The user inputs answers to the displayed questions. Answers can be in multiple formats, such as multiple choice or written answers. The device records the user's answers and the time they took to answer them, and sends them to the server.

[0462] Answer analysis and feedback

[0463] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0464] Dynamic Problem Generation

[0465] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the device and presented to the user.

[0466] Specific examples

[0467] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency, such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0468] By repeating this process, users can focus on strengthening their weak areas and study more efficiently.

[0469] Feedback and progress management

[0470] The server periodically generates a report that provides feedback on the user's learning progress, including areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[0471] The above is a specific embodiment of the system of the present invention, which allows users to efficiently overcome their weak areas and maximize their learning efficiency.

[0472] The processing flow will be explained below.

[0473] Program processing steps

[0474] Initial setup and receiving information

[0475] Step 1:

[0476] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[0477] Step 2:

[0478] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[0479] Step 3:

[0480] The server stores the received user information in a database and simultaneously creates a user profile.

[0481] First question generation and question submission

[0482] Step 4:

[0483] The server generates an initial set of problems based on the user's profile, selecting problems from a database of problems evenly across a wide range of subjects.

[0484] Step 5:

[0485] The server sends the generated question set to the terminal, including the question ID, question text, and choice data.

[0486] Step 6:

[0487] The terminal displays the received problem set to the user, and displays the problems and options on the user interface.

[0488] Enter your answer

[0489] Step 7:

[0490] The user can enter answers to the questions displayed, either by selecting options or by entering a written answer.

[0491] Step 8:

[0492] The terminal sends the user's answer data to the server, which includes the question ID, the choice number or written answer, and the answer time.

[0493] Answer analysis and feedback

[0494] Step 9:

[0495] The server analyzes the received answer data, determines whether the answer is correct, and records the time it took to answer.

[0496] Step 10:

[0497] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[0498] Generation and presentation of next questions

[0499] Step 11:

[0500] The server generates the next set of questions based on the latest user data, using a generative AI model to select questions that are specific to the user's weak areas.

[0501] Step 12:

[0502] The server sends the newly generated problem set to the terminal.

[0503] Step 13:

[0504] The terminal displays a new set of questions to the user, who then answers the questions again to continue the cycle.

[0505] Feedback and progress management

[0506] Step 14:

[0507] The server periodically compiles the user's learning progress and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[0508] Step 15:

[0509] The device displays a feedback report to the user, who can then use the feedback to further their learning.

[0510] The above are the specific processing steps of this system, which makes it possible to maximize the user's learning efficiency.

[0511] Example 1

[0512] 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."

[0513] Conventional learning systems have difficulty maximizing individual users' learning efficiency, and have not been able to dynamically generate questions that correspond to a user's strengths and weaknesses. It has also been difficult to analyze a user's learning progress in real time and provide optimal feedback.

[0514] 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.

[0515] In this invention, the server includes means for receiving information entered by a user at initial login, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, means for recording answer times, and means for generating feedback based on user progress data. This maximizes the learning efficiency of each user and enables effective learning progress management and feedback provision.

[0516] "User" refers to an individual who uses the system to learn.

[0517] "First login" refers to the moment when a user accesses the system for the first time, enters authentication information, and begins use.

[0518] "Terminal" refers to an electronic device such as a computer or smartphone that a user uses to input or display data.

[0519] "Server" refers to the central computer system on the network that processes and stores user information and performs problem generation and analysis.

[0520] "Database" refers to a storage device or system in which user information, question sets, answer data, etc. are structured and stored.

[0521] A "problem set" refers to a collection of multiple study questions provided to a user.

[0522] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a user's answering tendencies and areas of weakness and generates the optimal set of questions.

[0523] "Answer information" refers to the content of the answer entered by the user to the question and related data such as the answer time.

[0524] "Analysis" refers to the process by which the server evaluates the answer information received, determines whether each question is correct, and analyzes the user's learning tendencies.

[0525] "Optimization" refers to the process of adjusting the next question based on the user's progress and tendencies.

[0526] "Feedback" refers to providing users with analysis and advice on their learning results and progress.

[0527] The system of the present invention is designed to maximize the learning efficiency of each individual user. A specific embodiment of the program of this system will be described in detail below.

[0528] Entering and receiving user information

[0529] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is entered via a web form or a dedicated mobile application. The entered information is sent to the server via the device. The server receives this information and stores it in a database.

[0530] Generating the initial problem set

[0531] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions, focusing on subjects the user is weak at. A generative AI model is used to select the questions, and the AI ​​model adjusts the difficulty and content of the questions.

[0532] Displaying questions and entering answers

[0533] The generated problem set is sent to the terminal and displayed to the user. The user inputs answers to the displayed problems. The answer format can be multiple choice or written, and the terminal records the answer data and the answer time.

[0534] Sending and analyzing answer data

[0535] The device sends the user's answer data to the server. The server analyzes the received data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0536] Dynamic problem generation and feedback

[0537] The server generates the next set of questions based on the user's latest progress data. This process uses a generative AI model, taking into account the user's answering tendencies and the accuracy rates of other users. The optimized set of questions is then sent back to the device and provided to the user. The server also periodically generates a report that provides feedback on the user's learning progress and displays it on the user's device. This report includes the user's achievement level, areas for improvement, and advice on the next study plan.

[0538] Specific examples

[0539] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set that includes many basic math problems. This includes calculation problems, formula transformations, and basic geometry problems. After the user solves the problems, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0540] Prompt Sentence Examples

[0541] Here are some examples of prompts for generative AI models:

[0542] "User's answer:

[0543] - Calculation problem: 90 points (answer time: average 30 seconds)

[0544] - Mathematical transformation: 60 points (answer time: 90 seconds on average)

[0545] Problems to include in the next problem set:

[0546] 1. Add basic problems on formula transformation

[0547] 2. Include calculation questions as appropriate

[0548] 3. Add new geometry problems.

[0549] The AI ​​model then generates an optimized set of questions for the next problem based on this prompt. This completes the concrete implementation of the present invention, allowing users to study efficiently and focus on overcoming their weak areas.

[0550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0551] Step 1: Enter and submit your user information

[0552] When a user logs in for the first time, they enter information into the terminal, such as their preferred school, current academic level, strong and weak subjects, etc. The input data is saved on the terminal and later sent to the server.

[0553] Specific behavior:

[0554] A user fills out a web form or mobile application.

[0555] The input data is converted to JSON format.

[0556] The terminal transmits the data to the server.

[0557] Input: desired school, academic level, strong subjects, weak subjects

[0558] Output: User information sent to the server

[0559] Step 2: Server receives information and creates profile

[0560] The server receives the information sent by the user and stores it in a database, which creates a profile for each user.

[0561] Specific behavior:

[0562] The server receives an HTTP request from the device.

[0563] The received data is stored in a database and a user profile is generated.

[0564] Input: User information sent from the device

[0565] Output: User profile stored in the database

[0566] Step 3: Generate the initial problem set

[0567] The server generates an initial problem set based on the user profile, selects relevant problems from a problem database, and generates an optimal problem set using a generative AI model.

[0568] Specific behavior:

[0569] The server looks up the user profile.

[0570] Query the issues database to get a list of issues.

[0571] A generative AI model selects and refines the problems to generate an initial set of problems.

[0572] Input: User profile information

[0573] Output: The generated initial problem set

[0574] Step 4: View the question and enter your answer

[0575] The terminal displays the problem set received from the server to the user, who then inputs the answers to the problems. The answers are recorded along with the answer time.

[0576] Specific behavior:

[0577] The device parses the JSON formatted problem data it receives and formats it for display.

[0578] The user enters the answer and the terminal records it.

[0579] Input: Generated initial problem set

[0580] Output: Answer data entered on the terminal and answer time

[0581] Step 5: Submit your answers

[0582] The terminal transmits the user's answer data and answer time to the server.

[0583] Specific behavior:

[0584] The device converts the answer data into JSON format.

[0585] Send the data to the server.

[0586] Input: Answer data and answer time entered into the terminal

[0587] Output: Answer data and answer time sent to the server

[0588] Step 6: Answer analysis and feedback generation

[0589] The server analyzes the received answer data and determines whether it is correct or incorrect. It also evaluates the answer time and answer tendency to identify the user's weak areas. The analysis results are saved in a progress database and used to generate the next problem set.

[0590] Specific behavior:

[0591] The server inputs the answer data into the analysis engine.

[0592] The answers are judged to be correct or incorrect, and the evaluation results are stored in a database.

[0593] Input: Answer data and answer time sent to the server

[0594] Output: Analysis results and updated user profile

[0595] Step 7: Dynamic question generation and distribution

[0596] The server generates the next set of problems based on the user's latest progress data. The generative AI model optimizes the problems by taking into account the user's learning habits and other user data. The optimized set of problems is then sent to the device.

[0597] Specific behavior:

[0598] The server references the user's progress data.

[0599] The generative AI model generates the next set of problems.

[0600] Send the problem set to the device.

[0601] Input: Updated user profile and progress data

[0602] Output: The next optimized problem set

[0603] Step 8: Feedback on learning progress

[0604] The server periodically generates a report that provides feedback on the user's learning progress and sends it to the user's device, including the user's achievement level, areas for improvement, and advice on the next learning plan.

[0605] Specific behavior:

[0606] The server analyzes the progress data and generates a feedback report.

[0607] The feedback report is formatted in PDF or HTML format and sent to the device.

[0608] Input: Updated user profile and progress data

[0609] Output: A feedback report that is displayed to the user

[0610] (Application example 1)

[0611] 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."

[0612] Conventional learning systems have the problem of reducing learning efficiency because they are unable to provide questions tailored to each user's academic ability or specific areas of interest.In addition, they lack the technology to dynamically optimize and provide questions based on a detailed analysis of the user's progress and answer trends, making it difficult to maximize the user's learning proficiency.

[0613] 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.

[0614] In this invention, the server includes means for receiving information entered by the user when logging in for the first time, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, and means for generating and providing a report that provides feedback on the user's learning progress based on the user's answers. This allows the user's learning progress to be dynamically optimized, enabling efficient learning that focuses on specific areas of interest or weak areas.

[0615] "Information entered by the user at the time of initial login" refers to data such as personal information, learning goals, areas of strength and weakness, etc., provided by the system user at the time of initial login.

[0616] "Generating an initial problem set" refers to the process of creating problems that correspond to the current knowledge level and interests of each individual learner based on the received user information.

[0617] A "user device" is an electronic device used by a user to solve problems and input answers, including a smartphone, tablet, or PC.

[0618] "Receiving and analyzing answer information" refers to the process in which the server receives the answers to the questions entered by the user and evaluates whether they are correct or not and the tendency of the answers.

[0619] "Generating optimal questions for the next test" means dynamically generating new questions that address the user's specific needs and weak areas based on the analyzed answer information.

[0620] "Sending the optimized problem set to the user's terminal" means delivering the generated new problem set to the user's learning device.

[0621] "Generating and providing a report that provides feedback on learning progress" refers to the process of creating a report that visually shows the user's learning situation and progress, and supporting the user with instruction and future learning plans.

[0622] The present invention is a system that dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[0623] 1. User information registration

[0624] When a user logs in for the first time, they enter information such as their preferred school, current academic level, strong and weak subjects, etc. This information is sent to the server via the user's terminal.

[0625] 2. Generating the initial problem set

[0626] Based on the received information, the server generates an initial problem set that is tailored to the learner's current level of knowledge and specific areas of interest, with a particular focus on subjects in which the user is weak.

[0627] 3. Displaying and answering questions

[0628] The generated question set is displayed on the user's device, and the user inputs answers to the questions. Answers can be in various formats, such as multiple choice or written answers. The answers entered by the user are sent to the server via the device.

[0629] 4. Answer Analysis

[0630] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The results of this analysis are stored in the user's progress database.

[0631] 5. Generation of the next problem set

[0632] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the user's device and presented to them.

[0633] 6. Feedback and progress management

[0634] The server periodically generates a report that provides feedback on the user's learning progress. This report includes the user's learning status, areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[0635] Specific examples

[0636] For example, if a user wants to learn something specific in a particular field or area of ​​interest, the first time the system generates questions such as "calculating the optimal number of inventory orders" or "simulating handling complaints." Once the user solves these, the server analyzes the answers and evaluates their performance in that particular field. Based on this result, the next time the system presents questions tailored to the user's progress and areas of weakness.

[0637] The hardware used includes "user devices" such as smartphones, tablets, and PCs, as well as "servers" that connect to these devices. The software uses programming languages ​​such as Python to implement generative AI models.

[0638] Prompt Sentence Examples

[0639] "What are some effective ways to improve customer satisfaction?"

[0640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0641] Step 1:

[0642] When a user logs in for the first time, they enter information such as their preferred school, current academic ability, and strong and weak subjects into their device. The server receives this information and stores it in a database. The input data includes the user's personal information, and a user profile is created based on this information.

[0643] Input: Information such as desired school, current academic ability, strong subjects, weak subjects, etc. entered by the user into the device.

[0644] Output: The user profile stored on the server.

[0645] Step 2:

[0646] The server generates an initial problem set based on the user's profile. Using a generative AI model, it selects problems from a variety of areas, focusing on the user's weak areas. This problem set is then sent to the device and displayed to the user.

[0647] Input: User profile, problem database.

[0648] Output: The initial problem set displayed on the user's device.

[0649] Step 3:

[0650] The user inputs answers to the questions displayed on the terminal. Answers can be in multiple formats, such as multiple choice or written format, and the terminal records the user's answers and the time it took to answer them, and sends them to the server.

[0651] Input: The answer to the question that the user types into the terminal.

[0652] Output: Answer data sent to the server (answer content, answer time).

[0653] Step 4:

[0654] The server analyzes the received answer data, determines whether each question is correct, and evaluates the answer time and answer trends. Based on the analysis results, the user's progress database is updated.

[0655] Input: The answer data sent to the server.

[0656] Output: Correct / incorrect result, update of user's progress database.

[0657] Step 5:

[0658] The server generates the next set of problems based on the latest progress data. Using a generative AI model, it creates optimized problems that take into account the user's answering tendencies and the accuracy rates of other users, and sends them to the device.

[0659] Input: User progress database, question database.

[0660] Output: The optimized next problem set, the problem set sent to the device.

[0661] Step 6:

[0662] The server periodically generates a report that provides feedback on the user's learning progress. The report includes the user's learning status, areas for improvement, achievement goals, and advice on future learning plans, and is sent to the user's terminal and displayed to the user.

[0663] Input: User progress database.

[0664] Output: Feedback report, report displayed on terminal.

[0665] Step 7:

[0666] The user can check the feedback report through their device and reflect it in their next study. This makes it easier to study efficiently and continue. For example, if a user receives feedback that they are "strong at calculation problems but weak at formula transformations," the next problem set will include many formula transformation problems. This will allow them to improve their weak areas.

[0667] Input: Feedback report.

[0668] Output: Next lesson plan, user progress improvement.

[0669] 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.

[0670] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can further maximize individual learning efficiency and improve the user's learning experience.

[0671] System Overview

[0672] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0673] Emotion engine integration

[0674] The present invention incorporates an emotion engine that recognizes the emotions of users when answering questions. The emotion engine detects user emotions using facial recognition, voice tone analysis, and even biometric data (such as heart rate).

[0675] Initial setup and receiving information

[0676] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[0677] Problem set generation

[0678] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. In addition, the server also performs initial settings to match the emotion engine.

[0679] Answer to the question

[0680] The user enters the answer to the displayed question. At this time, the emotion engine installed in the device analyzes the user's face and voice in real time to obtain emotional data. This emotional data is sent to the server along with the answer data.

[0681] Answer analysis and feedback

[0682] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the time it takes to answer and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. These analysis results are stored in the user's progress database and are used to generate the next set of questions to be presented.

[0683] Dynamic Problem Generation

[0684] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[0685] Specific examples

[0686] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0687] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[0688] Feedback and progress management

[0689] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes areas for improvement, achieved goals, and advice on the next learning plan. The device displays this feedback report to the user to support their learning.

[0690] The above is a specific embodiment of the system of the present invention, which allows users to focus on strengthening their weak areas and study efficiently while receiving emotional support.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[0694] Step 2:

[0695] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[0696] Step 3:

[0697] The server stores the received user information in a database and creates a user profile.

[0698] Step 4:

[0699] The server generates an initial problem set based on the user profile. The server selects a wide range of problems from the problem database and provides the user with a set that includes cross-disciplinary problems.

[0700] Step 5:

[0701] The server sends the generated question set to the terminal, which includes the question ID, question text, and choice data.

[0702] Step 6:

[0703] The terminal displays the received problem set on the interface and asks the user questions.

[0704] Step 7:

[0705] The user enters answers to the displayed questions, while the device's built-in camera and microphone simultaneously analyze the user's facial expressions and tone of voice to obtain emotional data.

[0706] Step 8:

[0707] The device simultaneously transmits answer data and emotion data to the server, which includes the question ID, multiple choice or written answer, answer time, and emotion data.

[0708] Step 9:

[0709] The server analyzes the received answer data and emotion data, determining whether the answer was correct or incorrect and evaluating the response time and emotion fluctuations. For example, if there were many emotions indicating anxiety, that evaluation will also be included.

[0710] Step 10:

[0711] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[0712] Step 11:

[0713] The server generates the next set of questions based on the latest user data and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's answering tendencies and emotional data.

[0714] Step 12:

[0715] The server sends the generated problem set to the terminal.

[0716] Step 13:

[0717] The terminal displays the newly generated problem set to the user, who then answers the problems again.

[0718] Step 14:

[0719] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[0720] Step 15:

[0721] The device displays the generated feedback report to the user, who can then create a new study plan based on the feedback and begin their next study.

[0722] The above is a description of the specific processing steps of the system. By optimizing the user's learning experience through the analysis of emotion data, users can learn efficiently and effectively.

[0723] Example 2

[0724] 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."

[0725] Current educational systems struggle to fully consider each user's individual academic ability, learning attitude, and emotional state, making it difficult to maximize individual learning efficiency. Furthermore, they lack the ability to present adaptive questions based on the user's progress and emotions, resulting in a lack of improvement in the user's learning experience.

[0726] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for acquiring and receiving the user's emotional data, means for optimizing and generating the next problem to be posed based on the user's answer results and emotional data, and means for transmitting the optimized problem set to the user's terminal. This enables more personalized learning that takes into account the user's individual academic ability and emotional state.

[0727] "User" refers to an individual who uses this system to advance their learning.

[0728] "Terminal" refers to an electronic device that is operated by a user to display questions and input answers.

[0729] "Server" refers to a central processing unit that receives and analyzes data sent from terminals, and generates and sends problem sets.

[0730] "Input information" refers to information related to learning that a user provides when logging in for the first time, and specifically includes personal information, learning goals, desired schools, strong subjects, weak subjects, etc.

[0731] A "problem set" refers to a series of questions that are presented to a user.

[0732] "Answer information" refers to the data of the answer entered by the user to the question.

[0733] "Emotional data" refers to data on the emotional state obtained by analyzing information such as facial recognition, voice tone, and heart rate obtained when the user answers questions.

[0734] "Progress data" refers to data that indicates the user's learning progress and results.

[0735] A "generative AI model" refers to an artificial intelligence model used to analyze a user's answering tendencies and areas of weakness, and optimize the next questions to be asked.

[0736] This invention is a dynamic question generation system for improving the user's learning experience, and aims to maximize the user's learning efficiency by utilizing an emotion engine and a generative AI model. This system comprehensively covers a series of processes, from initial setup to question generation, answer analysis, next question generation, and feedback.

[0737] Hardware and software used

[0738] The system uses the following main hardware and software:

[0739] Server: Receives data, analyzes it, generates questions, and provides feedback. Specifically, it uses Python scripts, a SQL database, and generative AI models.

[0740] Terminal: A device (PC, tablet, smartphone) operated by the user that displays questions, inputs answers, and acquires emotional data. It has a built-in camera and microphone, and analyzes the user's face and voice tone in real time.

[0741] Emotion Engine: Analyzes user emotions based on biometric data such as facial recognition, voice tone analysis, and heart rate. Provides an API for sending data to the server.

[0742] Initial setup and receiving information

[0743] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. This information is sent to the server via their device. The server stores the received information in a database and creates a user profile based on it.

[0744] Problem set generation

[0745] The server generates an initial set of questions based on the user's profile, randomly selects questions from the question database, and focuses on subjects the user is weak in. It also initializes the emotion engine.

[0746] Answering questions and obtaining emotion data

[0747] The user inputs their answers to the displayed questions. The device uses a built-in camera and microphone to recognize the user's face and analyze their voice tone in real time to obtain emotional data. This data is then sent to the server along with the answer data.

[0748] Answer analysis and feedback

[0749] The server receives the answer data and emotion data and begins analysis using a Python script. It determines whether the answer is correct, evaluates the answer time, analyzes emotional fluctuations, and generates appropriate feedback. If the user feels stressed by a particular problem, it adjusts the difficulty and content of the problem. The analysis results are saved in a progress database and are used to generate the next set of problems.

[0750] Dynamic Problem Generation

[0751] The server generates the next set of questions based on the latest progress and emotional data. It uses a generative AI model to select the most appropriate questions, taking into account the user's weak areas and emotional state. The optimized set of questions is then sent to the device, where it is presented to the user again.

[0752] Providing feedback

[0753] The server periodically collects the user's progress and emotion data and generates a feedback report, which includes areas for improvement, achieved goals, and advice for the next learning plan. The device displays this feedback report to the user to support their learning.

[0754] Specific examples

[0755] For example, consider a case where a user wants to go to university but is not good at math when logging in for the first time. The server generates a problem set containing many basic math problems and presents it to the user. This set includes calculation problems, formula transformations, and basic geometry problems. When the user answers these, the server analyzes the answers and identifies tendencies such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0756] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[0757] Prompt Sentence Examples

[0758] For example, by inputting a prompt such as, "Give a third-year high school student who is not good at transforming mathematical formulas some problems that require them to transform mathematical formulas. Gradually increase the difficulty so that the student does not feel stressed when solving the problems. Add hints to each problem and provide feedback after the student answers," into a generative AI model, a problem set optimal for specific learning needs and emotional state can be generated.

[0759] The above is a specific embodiment of the present invention. By using this system, users can obtain an optimal learning experience that takes into account their individual academic ability and emotional state.

[0760] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0761] Divide the processing flow of the system program into processing steps

[0762] Step 1:

[0763] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. The input data is saved on the device in JSON format and then sent to the server.

[0764] Step 2:

[0765] When the device receives the user's input data, it sends it to the server using the HTTPS protocol. The server receives the data and stores it in a MySQL database, which creates a user profile.

[0766] Step 3:

[0767] The server generates an initial set of questions based on the user's profile, randomly selects questions from a database of questions using SQL queries, and sends the resulting set of questions to the device in JSON format.

[0768] Step 4:

[0769] The device displays the received problem set to the user, who then enters answers to the displayed problems, and the answer data is saved in JSON format on the device.

[0770] Step 5:

[0771] The emotion engine installed on the device analyzes the user's face, voice tone, and heart rate in real time to obtain emotion data, which is then sent to the server along with the answer data.

[0772] Step 6:

[0773] The server analyzes the answer data and emotion data received. Using a Python script, it determines whether the answer is correct, evaluates the answer time, and analyzes emotional fluctuations, and creates an adjustment plan if the user is feeling stressed by a particular problem. The results of this analysis are stored in a progress database.

[0774] Step 7:

[0775] The server generates the next set of problems based on the user's latest progress and emotional data. It uses a generative AI model to select the most appropriate problems based on the user's weak areas and emotional state. The generated problem set is sent to the device in JSON format.

[0776] Step 8:

[0777] The device displays the optimized problem set to the user, and at the same time, a feedback report is sent from the server and displayed on the device, including areas for improvement, goals achieved, and advice for the next study plan.

[0778] Detailed explanation of each processing step

[0779] Step 1:

[0780] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, strong and weak subjects in a dedicated input form. For example, if a user enters "I'm not good at math," the device converts this into JSON format, saves it, and sends it to the server.

[0781] Step 2:

[0782] Once the device receives the user's input data, it sends it to the server via an HTTPS request. The server receives the data and stores it in a MySQL database. This creates a user profile, including initial settings based on the user's learning goals and preferred schools.

[0783] Step 3:

[0784] The server uses SQL queries to select questions related to the subjects the user is weak at from the question database. It then generates the initial question set and sends it to the device in JSON format. For example, if the user enters "I'm weak at math," a question set containing many basic math questions will be generated.

[0785] Step 4:

[0786] The device displays the received problem set to the user. The user answers the problems, and the answer data is saved on the device. For example, problems involving integer calculations and transformations of basic mathematical expressions are included.

[0787] Step 5:

[0788] The emotion engine installed on the device detects the user's face and voice in real time through facial recognition, voice tone analysis, heart rate, etc. to obtain emotion data. This data is sent to the server along with the answer data. For example, if the user is confused by a mathematical transformation problem, the emotion engine will obtain that data.

[0789] Step 6:

[0790] The server analyzes the answer data and emotion data it receives. A Python script is used to determine whether the answer is correct, and to analyze the time it took to answer and fluctuations in the user's emotions. If it determines that a particular problem is causing stress to the user, the difficulty and content of the next problem can be adjusted. For example, if it takes a long time to transform a mathematical formula, a plan can be made to focus on that part of the problem.

[0791] Step 7:

[0792] The server uses the generative AI model to generate the next set of problems based on the latest progress data and emotion data. An example prompt might be, "For a high school senior who is not good at transforming mathematical formulas, please provide mathematical formula transformation problems with gradually increasing difficulty." This optimizes the generated problem set and sends it to the device in JSON format.

[0793] Step 8:

[0794] The device displays the optimized problem set to the user. At the same time, a feedback report is sent from the server and displayed on the device. The feedback report includes advice such as, "You seemed confused when transforming the formula. Please focus on this part next time."

[0795] These are the specific processing steps of the system according to the present invention, which allows users to have a more efficient and personalized learning experience.

[0796] (Application example 2)

[0797] 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."

[0798] Conventional learning systems generate questions based solely on the user's answers, making it difficult to maximize individual learning efficiency. Furthermore, they generate questions without considering the user's emotional state, which can lead to stress and anxiety, potentially resulting in a poor learning experience. This makes it impossible to provide consistently effective learning support to a diverse range of learners.

[0799] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for optimizing and generating the next problem to be presented based on the user's answer results, means for transmitting the optimized problem set to the user's terminal, emotion recognition means for analyzing the user's emotion data, and means for adjusting the difficulty level of the problems taking the user's emotion data into consideration. This makes it possible to dynamically generate optimal problems based on the individual learning progress while taking the user's emotions into consideration.

[0800] A "user" is an individual who uses this system to study.

[0801] "Information entered at first login" refers to data such as learning goals, current academic level, desired school, strong and weak subjects, etc. that a user enters when using the system for the first time.

[0802] A "problem set" is a collection of multiple problems generated by the server based on the user's academic ability and learning goals.

[0803] A "terminal" is a device that a user uses to answer questions, such as a smartphone, tablet, or computer.

[0804] "Emotion data" is data that indicates the user's emotional state, and is information obtained through facial recognition, voice tone analysis, biological reactions, and the like.

[0805] "Answer information" is data that includes the content of the user's answer and the result of whether it was correct or incorrect.

[0806] The "answer result" is data on whether the answer is correct or incorrect based on the answer entered by the user.

[0807] A "generative AI model" is an algorithm that uses artificial intelligence to analyze a user's answering tendencies and areas of weakness, and then generates new questions.

[0808] "Emotion recognition means" refers to technology and devices for analyzing emotions from a user's facial expressions and voice.

[0809] The "means for adjusting the difficulty level" refers to a method and algorithm for appropriately adjusting the difficulty of questions to be posed, taking into account the user's emotional data.

[0810] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can maximize individual learning efficiency and improve the user's learning experience.

[0811] System Overview

[0812] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. The problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0813] Emotion engine integration

[0814] The present invention incorporates an emotion engine that recognizes the user's emotions when answering questions. The emotion engine detects the user's emotions using facial recognition, voice tone analysis, and even biological response data (such as heart rate). This makes it possible to present questions that correspond to the user's emotional state.

[0815] Initial setup and receiving information

[0816] The server receives data such as personal information, learning goals, preferred schools, and strong and weak subjects entered by the user when they first logged in. This data is sent to the server and stored in a database. The server then creates a user profile based on this data.

[0817] Problem set generation

[0818] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. It also performs initial settings to match the emotion engine.

[0819] Answer to the question

[0820] The user enters an answer to the displayed question. At this time, the emotion engine installed on the device analyzes the user's face and voice in real time to obtain emotional data. The obtained answer data and emotional data are then sent to the server.

[0821] Answer analysis and feedback

[0822] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the answer time and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. The results of this analysis are stored in the user's progress database and are used to generate the next set of questions.

[0823] Dynamic Problem Generation

[0824] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[0825] Specific examples

[0826] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these problems, the server analyzes the answers and identifies a tendency for the user to be "good at calculations but take a long time to transform formulas." Based on this analysis, the next problem set will include more formula transformation problems. Furthermore, if the emotion engine determines that the user feels anxious about solving formula transformation problems, the server will generate a set that includes problems of gradually increasing difficulty and problems with many hints to alleviate the anxiety.

[0827] Example prompts to input to a generative AI model:

[0828] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[0829] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[0830] Generate a suitable problem set.

[0831] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0832] Step 1:

[0833] When a user logs in for the first time, they enter data such as personal information, learning goals, preferred schools, and strong and weak subjects. When the user enters this information into a dedicated form on their device and presses the send button, the data is sent from the device to the server. The input data includes learning goals, current academic level, preferred schools, strong and weak subjects, etc. The server receives this data and stores it in a database.

[0834] Step 2:

[0835] The server generates an initial problem set based on the received user data. It creates a well-balanced problem set, taking into account the user's strong and weak subjects. It randomly selects problems from a variety of fields from the problem database. It generates the initial problem set, placing particular emphasis on subjects the user is weak in. The generated problem set is sent to the terminal and displayed on the screen.

[0836] Step 3:

[0837] The terminal provides a UI that allows the user to input answers to the displayed problem sets. The user answers the problems and enters the results into the terminal. The input answer information is sent to the server via the terminal.

[0838] Step 4:

[0839] The emotion engine installed on the device captures emotional data in real time while the user answers questions. This is done by using a camera and microphone to recognize faces, analyze voice tones, and capture biometric data. This allows the user's emotional state, such as stress, anxiety, or happiness, to be analyzed. The captured emotional data is sent to the server along with the answer data.

[0840] Step 5:

[0841] The server analyzes the received answer data and emotional data. First, it determines whether each question is correct based on the answer data, and analyzes the user's answering tendencies and areas of strength and weakness. At the same time, it analyzes the emotional data and evaluates fluctuations in the user's emotions. For example, it can detect an increase in stress level in response to a particular question. The analysis results are stored in the user's progress database.

[0842] Step 6:

[0843] The server generates the next set of questions based on the user profile, answers, and emotional data. It uses a generative AI model to generate and apply prompts such as:

[0844] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[0845] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[0846] Generate a suitable problem set.

[0847] The generated problem set is adjusted to include the most appropriate problems, taking into account the user's weak areas and emotional state.

[0848] Step 7:

[0849] The server then sends the optimized problem set to the user's device. The next time the user studies, they can receive the newly generated problem set and continue studying. Through this process, the user can continuously enjoy a personalized learning experience.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] [Third embodiment]

[0854] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0855] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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).

[0860] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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."

[0866] The system of the present invention dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[0867] System Overview

[0868] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[0869] Initial setup and receiving information

[0870] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[0871] Problem set generation

[0872] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions covering a wide range of subjects, with a particular emphasis on subjects in which the user is weak. The generated set of questions is sent to the terminal and displayed to the user.

[0873] Answer to the question

[0874] The user inputs answers to the displayed questions. Answers can be in multiple formats, such as multiple choice or written answers. The device records the user's answers and the time they took to answer them, and sends them to the server.

[0875] Answer analysis and feedback

[0876] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0877] Dynamic Problem Generation

[0878] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the device and presented to the user.

[0879] Specific examples

[0880] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency, such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0881] By repeating this process, users can focus on strengthening their weak areas and study more efficiently.

[0882] Feedback and progress management

[0883] The server periodically generates a report that provides feedback on the user's learning progress, including areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[0884] The above is a specific embodiment of the system of the present invention, which allows users to efficiently overcome their weak areas and maximize their learning efficiency.

[0885] The processing flow will be explained below.

[0886] Program processing steps

[0887] Initial setup and receiving information

[0888] Step 1:

[0889] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[0890] Step 2:

[0891] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[0892] Step 3:

[0893] The server stores the received user information in a database and simultaneously creates a user profile.

[0894] First question generation and question submission

[0895] Step 4:

[0896] The server generates an initial set of problems based on the user's profile, selecting problems from a database of problems evenly across a wide range of subjects.

[0897] Step 5:

[0898] The server sends the generated question set to the terminal, including the question ID, question text, and choice data.

[0899] Step 6:

[0900] The terminal displays the received problem set to the user, and displays the problems and options on the user interface.

[0901] Enter your answer

[0902] Step 7:

[0903] The user can enter answers to the questions displayed, either by selecting options or by entering a written answer.

[0904] Step 8:

[0905] The terminal sends the user's answer data to the server, which includes the question ID, the choice number or written answer, and the answer time.

[0906] Answer analysis and feedback

[0907] Step 9:

[0908] The server analyzes the received answer data, determines whether the answer is correct, and records the time it took to answer.

[0909] Step 10:

[0910] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[0911] Generation and presentation of next questions

[0912] Step 11:

[0913] The server generates the next set of questions based on the latest user data, using a generative AI model to select questions that are specific to the user's weak areas.

[0914] Step 12:

[0915] The server sends the newly generated problem set to the terminal.

[0916] Step 13:

[0917] The terminal displays a new set of questions to the user, who then answers the questions again to continue the cycle.

[0918] Feedback and progress management

[0919] Step 14:

[0920] The server periodically compiles the user's learning progress and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[0921] Step 15:

[0922] The device displays a feedback report to the user, who can then use the feedback to further their learning.

[0923] The above are the specific processing steps of this system, which makes it possible to maximize the user's learning efficiency.

[0924] Example 1

[0925] 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."

[0926] Conventional learning systems have difficulty maximizing individual users' learning efficiency, and have not been able to dynamically generate questions that correspond to a user's strengths and weaknesses. It has also been difficult to analyze a user's learning progress in real time and provide optimal feedback.

[0927] 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.

[0928] In this invention, the server includes means for receiving information entered by a user at initial login, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, means for recording answer times, and means for generating feedback based on user progress data. This maximizes the learning efficiency of each user and enables effective learning progress management and feedback provision.

[0929] "User" refers to an individual who uses the system to learn.

[0930] "First login" refers to the moment when a user accesses the system for the first time, enters authentication information, and begins use.

[0931] "Terminal" refers to an electronic device such as a computer or smartphone that a user uses to input or display data.

[0932] "Server" refers to the central computer system on the network that processes and stores user information and performs problem generation and analysis.

[0933] "Database" refers to a storage device or system in which user information, question sets, answer data, etc. are structured and stored.

[0934] A "problem set" refers to a collection of multiple study questions provided to a user.

[0935] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a user's answering tendencies and areas of weakness and generates the optimal set of questions.

[0936] "Answer information" refers to the content of the answer entered by the user to the question and related data such as the answer time.

[0937] "Analysis" refers to the process by which the server evaluates the answer information received, determines whether each question is correct, and analyzes the user's learning tendencies.

[0938] "Optimization" refers to the process of adjusting the next question based on the user's progress and tendencies.

[0939] "Feedback" refers to providing users with analysis and advice on their learning results and progress.

[0940] The system of the present invention is designed to maximize the learning efficiency of each individual user. A specific embodiment of the program of this system will be described in detail below.

[0941] Entering and receiving user information

[0942] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is entered via a web form or a dedicated mobile application. The entered information is sent to the server via the device. The server receives this information and stores it in a database.

[0943] Generating the initial problem set

[0944] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions, focusing on subjects the user is weak at. A generative AI model is used to select the questions, and the AI ​​model adjusts the difficulty and content of the questions.

[0945] Displaying questions and entering answers

[0946] The generated problem set is sent to the terminal and displayed to the user. The user inputs answers to the displayed problems. The answer format can be multiple choice or written, and the terminal records the answer data and the answer time.

[0947] Sending and analyzing answer data

[0948] The device sends the user's answer data to the server. The server analyzes the received data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[0949] Dynamic problem generation and feedback

[0950] The server generates the next set of questions based on the user's latest progress data. This process uses a generative AI model, taking into account the user's answering tendencies and the accuracy rates of other users. The optimized set of questions is then sent back to the device and provided to the user. The server also periodically generates a report that provides feedback on the user's learning progress and displays it on the user's device. This report includes the user's achievement level, areas for improvement, and advice on the next study plan.

[0951] Specific examples

[0952] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set that includes many basic math problems. This includes calculation problems, formula transformations, and basic geometry problems. After the user solves the problems, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[0953] Prompt Sentence Examples

[0954] Here are some examples of prompts for generative AI models:

[0955] "User's answer:

[0956] - Calculation problem: 90 points (answer time: average 30 seconds)

[0957] - Mathematical transformation: 60 points (answer time: 90 seconds on average)

[0958] Problems to include in the next problem set:

[0959] 1. Add basic problems on formula transformation

[0960] 2. Include calculation questions as appropriate

[0961] 3. Add new geometry problems.

[0962] The AI ​​model then generates an optimized set of questions for the next problem based on this prompt. This completes the concrete implementation of the present invention, allowing users to study efficiently and focus on overcoming their weak areas.

[0963] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0964] Step 1: Enter and submit your user information

[0965] When a user logs in for the first time, they enter information into the terminal, such as their preferred school, current academic level, strong and weak subjects, etc. The input data is saved on the terminal and later sent to the server.

[0966] Specific behavior:

[0967] A user fills out a web form or mobile application.

[0968] The input data is converted to JSON format.

[0969] The terminal transmits the data to the server.

[0970] Input: desired school, academic level, strong subjects, weak subjects

[0971] Output: User information sent to the server

[0972] Step 2: Server receives information and creates profile

[0973] The server receives the information sent by the user and stores it in a database, which creates a profile for each user.

[0974] Specific behavior:

[0975] The server receives an HTTP request from the device.

[0976] The received data is stored in a database and a user profile is generated.

[0977] Input: User information sent from the device

[0978] Output: User profile stored in the database

[0979] Step 3: Generate the initial problem set

[0980] The server generates an initial problem set based on the user profile, selects relevant problems from a problem database, and generates an optimal problem set using a generative AI model.

[0981] Specific behavior:

[0982] The server looks up the user profile.

[0983] Query the issues database to get a list of issues.

[0984] A generative AI model selects and refines the problems to generate an initial set of problems.

[0985] Input: User profile information

[0986] Output: The generated initial problem set

[0987] Step 4: View the question and enter your answer

[0988] The terminal displays the problem set received from the server to the user, who then inputs the answers to the problems. The answers are recorded along with the answer time.

[0989] Specific behavior:

[0990] The device parses the JSON formatted problem data it receives and formats it for display.

[0991] The user enters the answer and the terminal records it.

[0992] Input: Generated initial problem set

[0993] Output: Answer data entered on the terminal and answer time

[0994] Step 5: Submit your answers

[0995] The terminal transmits the user's answer data and answer time to the server.

[0996] Specific behavior:

[0997] The device converts the answer data into JSON format.

[0998] Send the data to the server.

[0999] Input: Answer data and answer time entered into the terminal

[1000] Output: Answer data and answer time sent to the server

[1001] Step 6: Answer analysis and feedback generation

[1002] The server analyzes the received answer data and determines whether it is correct or incorrect. It also evaluates the answer time and answer tendency to identify the user's weak areas. The analysis results are saved in a progress database and used to generate the next problem set.

[1003] Specific behavior:

[1004] The server inputs the answer data into the analysis engine.

[1005] The answers are judged to be correct or incorrect, and the evaluation results are stored in a database.

[1006] Input: Answer data and answer time sent to the server

[1007] Output: Analysis results and updated user profile

[1008] Step 7: Dynamic question generation and distribution

[1009] The server generates the next set of problems based on the user's latest progress data. The generative AI model optimizes the problems by taking into account the user's learning habits and other user data. The optimized set of problems is then sent to the device.

[1010] Specific behavior:

[1011] The server references the user's progress data.

[1012] The generative AI model generates the next set of problems.

[1013] Send the problem set to the device.

[1014] Input: Updated user profile and progress data

[1015] Output: The next optimized problem set

[1016] Step 8: Feedback on learning progress

[1017] The server periodically generates a report that provides feedback on the user's learning progress and sends it to the user's device, including the user's achievement level, areas for improvement, and advice on the next learning plan.

[1018] Specific behavior:

[1019] The server analyzes the progress data and generates a feedback report.

[1020] The feedback report is formatted in PDF or HTML format and sent to the device.

[1021] Input: Updated user profile and progress data

[1022] Output: A feedback report that is displayed to the user

[1023] (Application example 1)

[1024] 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."

[1025] Conventional learning systems have the problem of reducing learning efficiency because they are unable to provide questions tailored to each user's academic ability or specific areas of interest.In addition, they lack the technology to dynamically optimize and provide questions based on a detailed analysis of the user's progress and answer trends, making it difficult to maximize the user's learning proficiency.

[1026] 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.

[1027] In this invention, the server includes means for receiving information entered by the user when logging in for the first time, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, and means for generating and providing a report that provides feedback on the user's learning progress based on the user's answers. This allows the user's learning progress to be dynamically optimized, enabling efficient learning that focuses on specific areas of interest or weak areas.

[1028] "Information entered by the user at the time of initial login" refers to data such as personal information, learning goals, areas of strength and weakness, etc., provided by the system user at the time of initial login.

[1029] "Generating an initial problem set" refers to the process of creating problems that correspond to the current knowledge level and interests of each individual learner based on the received user information.

[1030] A "user device" is an electronic device used by a user to solve problems and input answers, including a smartphone, tablet, or PC.

[1031] "Receiving and analyzing answer information" refers to the process in which the server receives the answers to the questions entered by the user and evaluates whether they are correct or not and the tendency of the answers.

[1032] "Generating optimal questions for the next test" means dynamically generating new questions that address the user's specific needs and weak areas based on the analyzed answer information.

[1033] "Sending the optimized problem set to the user's terminal" means delivering the generated new problem set to the user's learning device.

[1034] "Generating and providing a report that provides feedback on learning progress" refers to the process of creating a report that visually shows the user's learning situation and progress, and supporting the user with instruction and future learning plans.

[1035] The present invention is a system that dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[1036] 1. User information registration

[1037] When a user logs in for the first time, they enter information such as their preferred school, current academic level, strong and weak subjects, etc. This information is sent to the server via the user's terminal.

[1038] 2. Generating the initial problem set

[1039] Based on the received information, the server generates an initial problem set that is tailored to the learner's current level of knowledge and specific areas of interest, with a particular focus on subjects in which the user is weak.

[1040] 3. Displaying and answering questions

[1041] The generated question set is displayed on the user's device, and the user inputs answers to the questions. Answers can be in various formats, such as multiple choice or written answers. The answers entered by the user are sent to the server via the device.

[1042] 4. Answer Analysis

[1043] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The results of this analysis are stored in the user's progress database.

[1044] 5. Generation of the next problem set

[1045] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the user's device and presented to them.

[1046] 6. Feedback and progress management

[1047] The server periodically generates a report that provides feedback on the user's learning progress. This report includes the user's learning status, areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[1048] Specific examples

[1049] For example, if a user wants to learn something specific in a particular field or area of ​​interest, the first time the system generates questions such as "calculating the optimal number of inventory orders" or "simulating handling complaints." Once the user solves these, the server analyzes the answers and evaluates their performance in that particular field. Based on this result, the next time the system presents questions tailored to the user's progress and areas of weakness.

[1050] The hardware used includes "user devices" such as smartphones, tablets, and PCs, as well as "servers" that connect to these devices. The software uses programming languages ​​such as Python to implement generative AI models.

[1051] Prompt Sentence Examples

[1052] "What are some effective ways to improve customer satisfaction?"

[1053] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1054] Step 1:

[1055] When a user logs in for the first time, they enter information such as their preferred school, current academic ability, and strong and weak subjects into their device. The server receives this information and stores it in a database. The input data includes the user's personal information, and a user profile is created based on this information.

[1056] Input: Information such as desired school, current academic ability, strong subjects, weak subjects, etc. entered by the user into the device.

[1057] Output: The user profile stored on the server.

[1058] Step 2:

[1059] The server generates an initial problem set based on the user's profile. Using a generative AI model, it selects problems from a variety of areas, focusing on the user's weak areas. This problem set is then sent to the device and displayed to the user.

[1060] Input: User profile, problem database.

[1061] Output: The initial problem set displayed on the user's device.

[1062] Step 3:

[1063] The user inputs answers to the questions displayed on the terminal. Answers can be in multiple formats, such as multiple choice or written format, and the terminal records the user's answers and the time it took to answer them, and sends them to the server.

[1064] Input: The answer to the question that the user types into the terminal.

[1065] Output: Answer data sent to the server (answer content, answer time).

[1066] Step 4:

[1067] The server analyzes the received answer data, determines whether each question is correct, and evaluates the answer time and answer trends. Based on the analysis results, the user's progress database is updated.

[1068] Input: The answer data sent to the server.

[1069] Output: Correct / incorrect result, update of user's progress database.

[1070] Step 5:

[1071] The server generates the next set of problems based on the latest progress data. Using a generative AI model, it creates optimized problems that take into account the user's answering tendencies and the accuracy rates of other users, and sends them to the device.

[1072] Input: User progress database, question database.

[1073] Output: The optimized next problem set, the problem set sent to the device.

[1074] Step 6:

[1075] The server periodically generates a report that provides feedback on the user's learning progress. The report includes the user's learning status, areas for improvement, achievement goals, and advice on future learning plans, and is sent to the user's terminal and displayed to the user.

[1076] Input: User progress database.

[1077] Output: Feedback report, report displayed on terminal.

[1078] Step 7:

[1079] The user can check the feedback report through their device and reflect it in their next study. This makes it easier to study efficiently and continue. For example, if a user receives feedback that they are "strong at calculation problems but weak at formula transformations," the next problem set will include many formula transformation problems. This will allow them to improve their weak areas.

[1080] Input: Feedback report.

[1081] Output: Next lesson plan, user progress improvement.

[1082] 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.

[1083] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can further maximize individual learning efficiency and improve the user's learning experience.

[1084] System Overview

[1085] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[1086] Emotion engine integration

[1087] The present invention incorporates an emotion engine that recognizes the emotions of users when answering questions. The emotion engine detects user emotions using facial recognition, voice tone analysis, and even biometric data (such as heart rate).

[1088] Initial setup and receiving information

[1089] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[1090] Problem set generation

[1091] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. In addition, the server also performs initial settings to match the emotion engine.

[1092] Answer to the question

[1093] The user enters the answer to the displayed question. At this time, the emotion engine installed in the device analyzes the user's face and voice in real time to obtain emotional data. This emotional data is sent to the server along with the answer data.

[1094] Answer analysis and feedback

[1095] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the time it takes to answer and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. These analysis results are stored in the user's progress database and are used to generate the next set of questions to be presented.

[1096] Dynamic Problem Generation

[1097] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[1098] Specific examples

[1099] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1100] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[1101] Feedback and progress management

[1102] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes areas for improvement, achieved goals, and advice on the next learning plan. The device displays this feedback report to the user to support their learning.

[1103] The above is a specific embodiment of the system of the present invention, which allows users to focus on strengthening their weak areas and study efficiently while receiving emotional support.

[1104] The processing flow will be explained below.

[1105] Step 1:

[1106] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[1107] Step 2:

[1108] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[1109] Step 3:

[1110] The server stores the received user information in a database and creates a user profile.

[1111] Step 4:

[1112] The server generates an initial problem set based on the user profile. The server selects a wide range of problems from the problem database and provides the user with a set that includes cross-disciplinary problems.

[1113] Step 5:

[1114] The server sends the generated question set to the terminal, which includes the question ID, question text, and choice data.

[1115] Step 6:

[1116] The terminal displays the received problem set on the interface and asks the user questions.

[1117] Step 7:

[1118] The user enters answers to the displayed questions, while the device's built-in camera and microphone simultaneously analyze the user's facial expressions and tone of voice to obtain emotional data.

[1119] Step 8:

[1120] The device simultaneously transmits answer data and emotion data to the server, which includes the question ID, multiple choice or written answer, answer time, and emotion data.

[1121] Step 9:

[1122] The server analyzes the received answer data and emotion data, determining whether the answer was correct or incorrect and evaluating the response time and emotion fluctuations. For example, if there were many emotions indicating anxiety, that evaluation will also be included.

[1123] Step 10:

[1124] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[1125] Step 11:

[1126] The server generates the next set of questions based on the latest user data and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's answering tendencies and emotional data.

[1127] Step 12:

[1128] The server sends the generated problem set to the terminal.

[1129] Step 13:

[1130] The terminal displays the newly generated problem set to the user, who then answers the problems again.

[1131] Step 14:

[1132] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[1133] Step 15:

[1134] The device displays the generated feedback report to the user, who can then create a new study plan based on the feedback and begin their next study.

[1135] The above is a description of the specific processing steps of the system. By optimizing the user's learning experience through the analysis of emotion data, users can learn efficiently and effectively.

[1136] Example 2

[1137] 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."

[1138] Current educational systems struggle to fully consider each user's individual academic ability, learning attitude, and emotional state, making it difficult to maximize individual learning efficiency. Furthermore, they lack the ability to present adaptive questions based on the user's progress and emotions, resulting in a lack of improvement in the user's learning experience.

[1139] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for acquiring and receiving the user's emotional data, means for optimizing and generating the next problem to be posed based on the user's answer results and emotional data, and means for transmitting the optimized problem set to the user's terminal. This enables more personalized learning that takes into account the user's individual academic ability and emotional state.

[1140] "User" refers to an individual who uses this system to advance their learning.

[1141] "Terminal" refers to an electronic device that is operated by a user to display questions and input answers.

[1142] "Server" refers to a central processing unit that receives and analyzes data sent from terminals, and generates and sends problem sets.

[1143] "Input information" refers to information related to learning that a user provides when logging in for the first time, and specifically includes personal information, learning goals, desired schools, strong subjects, weak subjects, etc.

[1144] A "problem set" refers to a series of questions that are presented to a user.

[1145] "Answer information" refers to the data of the answer entered by the user to the question.

[1146] "Emotional data" refers to data on the emotional state obtained by analyzing information such as facial recognition, voice tone, and heart rate obtained when the user answers questions.

[1147] "Progress data" refers to data that indicates the user's learning progress and results.

[1148] A "generative AI model" refers to an artificial intelligence model used to analyze a user's answering tendencies and areas of weakness, and optimize the next questions to be asked.

[1149] This invention is a dynamic question generation system for improving the user's learning experience, and aims to maximize the user's learning efficiency by utilizing an emotion engine and a generative AI model. This system comprehensively covers a series of processes, from initial setup to question generation, answer analysis, next question generation, and feedback.

[1150] Hardware and software used

[1151] The system uses the following main hardware and software:

[1152] Server: Receives data, analyzes it, generates questions, and provides feedback. Specifically, it uses Python scripts, a SQL database, and generative AI models.

[1153] Terminal: A device (PC, tablet, smartphone) operated by the user that displays questions, inputs answers, and acquires emotional data. It has a built-in camera and microphone, and analyzes the user's face and voice tone in real time.

[1154] Emotion Engine: Analyzes user emotions based on biometric data such as facial recognition, voice tone analysis, and heart rate. Provides an API for sending data to the server.

[1155] Initial setup and receiving information

[1156] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. This information is sent to the server via their device. The server stores the received information in a database and creates a user profile based on it.

[1157] Problem set generation

[1158] The server generates an initial set of questions based on the user's profile, randomly selects questions from the question database, and focuses on subjects the user is weak in. It also initializes the emotion engine.

[1159] Answering questions and obtaining emotion data

[1160] The user inputs their answers to the displayed questions. The device uses a built-in camera and microphone to recognize the user's face and analyze their voice tone in real time to obtain emotional data. This data is then sent to the server along with the answer data.

[1161] Answer analysis and feedback

[1162] The server receives the answer data and emotion data and begins analysis using a Python script. It determines whether the answer is correct, evaluates the answer time, analyzes emotional fluctuations, and generates appropriate feedback. If the user feels stressed by a particular problem, it adjusts the difficulty and content of the problem. The analysis results are saved in a progress database and are used to generate the next set of problems.

[1163] Dynamic Problem Generation

[1164] The server generates the next set of questions based on the latest progress and emotional data. It uses a generative AI model to select the most appropriate questions, taking into account the user's weak areas and emotional state. The optimized set of questions is then sent to the device, where it is presented to the user again.

[1165] Providing feedback

[1166] The server periodically collects the user's progress and emotion data and generates a feedback report, which includes areas for improvement, achieved goals, and advice for the next learning plan. The device displays this feedback report to the user to support their learning.

[1167] Specific examples

[1168] For example, consider a case where a user wants to go to university but is not good at math when logging in for the first time. The server generates a problem set containing many basic math problems and presents it to the user. This set includes calculation problems, formula transformations, and basic geometry problems. When the user answers these, the server analyzes the answers and identifies tendencies such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1169] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[1170] Prompt Sentence Examples

[1171] For example, by inputting a prompt such as, "Give a third-year high school student who is not good at transforming mathematical formulas some problems that require them to transform mathematical formulas. Gradually increase the difficulty so that the student does not feel stressed when solving the problems. Add hints to each problem and provide feedback after the student answers," into a generative AI model, a problem set optimal for specific learning needs and emotional state can be generated.

[1172] The above is a specific embodiment of the present invention. By using this system, users can obtain an optimal learning experience that takes into account their individual academic ability and emotional state.

[1173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1174] Divide the processing flow of the system program into processing steps

[1175] Step 1:

[1176] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. The input data is saved on the device in JSON format and then sent to the server.

[1177] Step 2:

[1178] When the device receives the user's input data, it sends it to the server using the HTTPS protocol. The server receives the data and stores it in a MySQL database, which creates a user profile.

[1179] Step 3:

[1180] The server generates an initial set of questions based on the user's profile, randomly selects questions from a database of questions using SQL queries, and sends the resulting set of questions to the device in JSON format.

[1181] Step 4:

[1182] The device displays the received problem set to the user, who then enters answers to the displayed problems, and the answer data is saved in JSON format on the device.

[1183] Step 5:

[1184] The emotion engine installed on the device analyzes the user's face, voice tone, and heart rate in real time to obtain emotion data, which is then sent to the server along with the answer data.

[1185] Step 6:

[1186] The server analyzes the answer data and emotion data received. Using a Python script, it determines whether the answer is correct, evaluates the answer time, and analyzes emotional fluctuations, and creates an adjustment plan if the user is feeling stressed by a particular problem. The results of this analysis are stored in a progress database.

[1187] Step 7:

[1188] The server generates the next set of problems based on the user's latest progress and emotional data. It uses a generative AI model to select the most appropriate problems based on the user's weak areas and emotional state. The generated problem set is sent to the device in JSON format.

[1189] Step 8:

[1190] The device displays the optimized problem set to the user, and at the same time, a feedback report is sent from the server and displayed on the device, including areas for improvement, goals achieved, and advice for the next study plan.

[1191] Detailed explanation of each processing step

[1192] Step 1:

[1193] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, strong and weak subjects in a dedicated input form. For example, if a user enters "I'm not good at math," the device converts this into JSON format, saves it, and sends it to the server.

[1194] Step 2:

[1195] Once the device receives the user's input data, it sends it to the server via an HTTPS request. The server receives the data and stores it in a MySQL database. This creates a user profile, including initial settings based on the user's learning goals and preferred schools.

[1196] Step 3:

[1197] The server uses SQL queries to select questions related to the subjects the user is weak at from the question database. It then generates the initial question set and sends it to the device in JSON format. For example, if the user enters "I'm weak at math," a question set containing many basic math questions will be generated.

[1198] Step 4:

[1199] The device displays the received problem set to the user. The user answers the problems, and the answer data is saved on the device. For example, problems involving integer calculations and transformations of basic mathematical expressions are included.

[1200] Step 5:

[1201] The emotion engine installed on the device detects the user's face and voice in real time through facial recognition, voice tone analysis, heart rate, etc. to obtain emotion data. This data is sent to the server along with the answer data. For example, if the user is confused by a mathematical transformation problem, the emotion engine will obtain that data.

[1202] Step 6:

[1203] The server analyzes the answer data and emotion data it receives. A Python script is used to determine whether the answer is correct, and to analyze the time it took to answer and fluctuations in the user's emotions. If it determines that a particular problem is causing stress to the user, the difficulty and content of the next problem can be adjusted. For example, if it takes a long time to transform a mathematical formula, a plan can be made to focus on that part of the problem.

[1204] Step 7:

[1205] The server uses the generative AI model to generate the next set of problems based on the latest progress data and emotion data. An example prompt might be, "For a high school senior who is not good at transforming mathematical formulas, please provide mathematical formula transformation problems with gradually increasing difficulty." This optimizes the generated problem set and sends it to the device in JSON format.

[1206] Step 8:

[1207] The device displays the optimized problem set to the user. At the same time, a feedback report is sent from the server and displayed on the device. The feedback report includes advice such as, "You seemed confused when transforming the formula. Please focus on this part next time."

[1208] These are the specific processing steps of the system according to the present invention, which allows users to have a more efficient and personalized learning experience.

[1209] (Application example 2)

[1210] 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."

[1211] Conventional learning systems generate questions based solely on the user's answers, making it difficult to maximize individual learning efficiency. Furthermore, they generate questions without considering the user's emotional state, which can lead to stress and anxiety, potentially resulting in a poor learning experience. This makes it impossible to provide consistently effective learning support to a diverse range of learners.

[1212] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for optimizing and generating the next problem to be presented based on the user's answer results, means for transmitting the optimized problem set to the user's terminal, emotion recognition means for analyzing the user's emotion data, and means for adjusting the difficulty level of the problems taking the user's emotion data into consideration. This makes it possible to dynamically generate optimal problems based on the individual learning progress while taking the user's emotions into consideration.

[1213] A "user" is an individual who uses this system to study.

[1214] "Information entered at first login" refers to data such as learning goals, current academic level, desired school, strong and weak subjects, etc. that a user enters when using the system for the first time.

[1215] A "problem set" is a collection of multiple problems generated by the server based on the user's academic ability and learning goals.

[1216] A "terminal" is a device that a user uses to answer questions, such as a smartphone, tablet, or computer.

[1217] "Emotion data" is data that indicates the user's emotional state, and is information obtained through facial recognition, voice tone analysis, biological reactions, and the like.

[1218] "Answer information" is data that includes the content of the user's answer and the result of whether it was correct or incorrect.

[1219] The "answer result" is data on whether the answer is correct or incorrect based on the answer entered by the user.

[1220] A "generative AI model" is an algorithm that uses artificial intelligence to analyze a user's answering tendencies and areas of weakness, and then generates new questions.

[1221] "Emotion recognition means" refers to technology and devices for analyzing emotions from a user's facial expressions and voice.

[1222] The "means for adjusting the difficulty level" refers to a method and algorithm for appropriately adjusting the difficulty of questions to be posed, taking into account the user's emotional data.

[1223] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can maximize individual learning efficiency and improve the user's learning experience.

[1224] System Overview

[1225] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. The problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[1226] Emotion engine integration

[1227] The present invention incorporates an emotion engine that recognizes the user's emotions when answering questions. The emotion engine detects the user's emotions using facial recognition, voice tone analysis, and even biological response data (such as heart rate). This makes it possible to present questions that correspond to the user's emotional state.

[1228] Initial setup and receiving information

[1229] The server receives data such as personal information, learning goals, preferred schools, and strong and weak subjects entered by the user when they first logged in. This data is sent to the server and stored in a database. The server then creates a user profile based on this data.

[1230] Problem set generation

[1231] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. It also performs initial settings to match the emotion engine.

[1232] Answer to the question

[1233] The user enters an answer to the displayed question. At this time, the emotion engine installed on the device analyzes the user's face and voice in real time to obtain emotional data. The obtained answer data and emotional data are then sent to the server.

[1234] Answer analysis and feedback

[1235] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the answer time and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. The results of this analysis are stored in the user's progress database and are used to generate the next set of questions.

[1236] Dynamic Problem Generation

[1237] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[1238] Specific examples

[1239] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these problems, the server analyzes the answers and identifies a tendency for the user to be "good at calculations but take a long time to transform formulas." Based on this analysis, the next problem set will include more formula transformation problems. Furthermore, if the emotion engine determines that the user feels anxious about solving formula transformation problems, the server will generate a set that includes problems of gradually increasing difficulty and problems with many hints to alleviate the anxiety.

[1240] Example prompts to input to a generative AI model:

[1241] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[1242] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[1243] Generate a suitable problem set.

[1244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1245] Step 1:

[1246] When a user logs in for the first time, they enter data such as personal information, learning goals, preferred schools, and strong and weak subjects. When the user enters this information into a dedicated form on their device and presses the send button, the data is sent from the device to the server. The input data includes learning goals, current academic level, preferred schools, strong and weak subjects, etc. The server receives this data and stores it in a database.

[1247] Step 2:

[1248] The server generates an initial problem set based on the received user data. It creates a well-balanced problem set, taking into account the user's strong and weak subjects. It randomly selects problems from a variety of fields from the problem database. It generates the initial problem set, placing particular emphasis on subjects the user is weak in. The generated problem set is sent to the terminal and displayed on the screen.

[1249] Step 3:

[1250] The terminal provides a UI that allows the user to input answers to the displayed problem sets. The user answers the problems and enters the results into the terminal. The input answer information is sent to the server via the terminal.

[1251] Step 4:

[1252] The emotion engine installed on the device captures emotional data in real time while the user answers questions. This is done by using a camera and microphone to recognize faces, analyze voice tones, and capture biometric data. This allows the user's emotional state, such as stress, anxiety, or happiness, to be analyzed. The captured emotional data is sent to the server along with the answer data.

[1253] Step 5:

[1254] The server analyzes the received answer data and emotional data. First, it determines whether each question is correct based on the answer data, and analyzes the user's answering tendencies and areas of strength and weakness. At the same time, it analyzes the emotional data and evaluates fluctuations in the user's emotions. For example, it can detect an increase in stress level in response to a particular question. The analysis results are stored in the user's progress database.

[1255] Step 6:

[1256] The server generates the next set of questions based on the user profile, answers, and emotional data. It uses a generative AI model to generate and apply prompts such as:

[1257] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[1258] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[1259] Generate a suitable problem set.

[1260] The generated problem set is adjusted to include the most appropriate problems, taking into account the user's weak areas and emotional state.

[1261] Step 7:

[1262] The server then sends the optimized problem set to the user's device. The next time the user studies, they can receive the newly generated problem set and continue studying. Through this process, the user can continuously enjoy a personalized learning experience.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] [Fourth embodiment]

[1267] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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.

[1272] 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).

[1273] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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."

[1280] The system of the present invention dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[1281] System Overview

[1282] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[1283] Initial setup and receiving information

[1284] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[1285] Problem set generation

[1286] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions covering a wide range of subjects, with a particular emphasis on subjects in which the user is weak. The generated set of questions is sent to the terminal and displayed to the user.

[1287] Answer to the question

[1288] The user inputs answers to the displayed questions. Answers can be in multiple formats, such as multiple choice or written answers. The device records the user's answers and the time they took to answer them, and sends them to the server.

[1289] Answer analysis and feedback

[1290] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[1291] Dynamic Problem Generation

[1292] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the device and presented to the user.

[1293] Specific examples

[1294] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency, such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1295] By repeating this process, users can focus on strengthening their weak areas and study more efficiently.

[1296] Feedback and progress management

[1297] The server periodically generates a report that provides feedback on the user's learning progress, including areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[1298] The above is a specific embodiment of the system of the present invention, which allows users to efficiently overcome their weak areas and maximize their learning efficiency.

[1299] The processing flow will be explained below.

[1300] Program processing steps

[1301] Initial setup and receiving information

[1302] Step 1:

[1303] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[1304] Step 2:

[1305] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[1306] Step 3:

[1307] The server stores the received user information in a database and simultaneously creates a user profile.

[1308] First question generation and question submission

[1309] Step 4:

[1310] The server generates an initial set of problems based on the user's profile, selecting problems from a database of problems evenly across a wide range of subjects.

[1311] Step 5:

[1312] The server sends the generated question set to the terminal, including the question ID, question text, and choice data.

[1313] Step 6:

[1314] The terminal displays the received problem set to the user, and displays the problems and options on the user interface.

[1315] Enter your answer

[1316] Step 7:

[1317] The user can enter answers to the questions displayed, either by selecting options or by entering a written answer.

[1318] Step 8:

[1319] The terminal sends the user's answer data to the server, which includes the question ID, the choice number or written answer, and the answer time.

[1320] Answer analysis and feedback

[1321] Step 9:

[1322] The server analyzes the received answer data, determines whether the answer is correct, and records the time it took to answer.

[1323] Step 10:

[1324] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[1325] Generation and presentation of next questions

[1326] Step 11:

[1327] The server generates the next set of questions based on the latest user data, using a generative AI model to select questions that are specific to the user's weak areas.

[1328] Step 12:

[1329] The server sends the newly generated problem set to the terminal.

[1330] Step 13:

[1331] The terminal displays a new set of questions to the user, who then answers the questions again to continue the cycle.

[1332] Feedback and progress management

[1333] Step 14:

[1334] The server periodically compiles the user's learning progress and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[1335] Step 15:

[1336] The device displays a feedback report to the user, who can then use the feedback to further their learning.

[1337] The above are the specific processing steps of this system, which makes it possible to maximize the user's learning efficiency.

[1338] Example 1

[1339] 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."

[1340] Conventional learning systems have difficulty maximizing individual users' learning efficiency, and have not been able to dynamically generate questions that correspond to a user's strengths and weaknesses. It has also been difficult to analyze a user's learning progress in real time and provide optimal feedback.

[1341] 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.

[1342] In this invention, the server includes means for receiving information entered by a user at initial login, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, means for recording answer times, and means for generating feedback based on user progress data. This maximizes the learning efficiency of each user and enables effective learning progress management and feedback provision.

[1343] "User" refers to an individual who uses the system to learn.

[1344] "First login" refers to the moment when a user accesses the system for the first time, enters authentication information, and begins use.

[1345] "Terminal" refers to an electronic device such as a computer or smartphone that a user uses to input or display data.

[1346] "Server" refers to the central computer system on the network that processes and stores user information and performs problem generation and analysis.

[1347] "Database" refers to a storage device or system in which user information, question sets, answer data, etc. are structured and stored.

[1348] A "problem set" refers to a collection of multiple study questions provided to a user.

[1349] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a user's answering tendencies and areas of weakness and generates the optimal set of questions.

[1350] "Answer information" refers to the content of the answer entered by the user to the question and related data such as the answer time.

[1351] "Analysis" refers to the process by which the server evaluates the answer information received, determines whether each question is correct, and analyzes the user's learning tendencies.

[1352] "Optimization" refers to the process of adjusting the next question based on the user's progress and tendencies.

[1353] "Feedback" refers to providing users with analysis and advice on their learning results and progress.

[1354] The system of the present invention is designed to maximize the learning efficiency of each individual user. A specific embodiment of the program of this system will be described in detail below.

[1355] Entering and receiving user information

[1356] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is entered via a web form or a dedicated mobile application. The entered information is sent to the server via the device. The server receives this information and stores it in a database.

[1357] Generating the initial problem set

[1358] The server generates an initial set of questions based on the user's profile. The server randomly selects questions from a database of questions, focusing on subjects the user is weak at. A generative AI model is used to select the questions, and the AI ​​model adjusts the difficulty and content of the questions.

[1359] Displaying questions and entering answers

[1360] The generated problem set is sent to the terminal and displayed to the user. The user inputs answers to the displayed problems. The answer format can be multiple choice or written, and the terminal records the answer data and the answer time.

[1361] Sending and analyzing answer data

[1362] The device sends the user's answer data to the server. The server analyzes the received data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The analysis results are saved in the user's progress database and are used to generate the next set of questions.

[1363] Dynamic problem generation and feedback

[1364] The server generates the next set of questions based on the user's latest progress data. This process uses a generative AI model, taking into account the user's answering tendencies and the accuracy rates of other users. The optimized set of questions is then sent back to the device and provided to the user. The server also periodically generates a report that provides feedback on the user's learning progress and displays it on the user's device. This report includes the user's achievement level, areas for improvement, and advice on the next study plan.

[1365] Specific examples

[1366] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set that includes many basic math problems. This includes calculation problems, formula transformations, and basic geometry problems. After the user solves the problems, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1367] Prompt Sentence Examples

[1368] Here are some examples of prompts for generative AI models:

[1369] "User's answer:

[1370] - Calculation problem: 90 points (answer time: average 30 seconds)

[1371] - Mathematical transformation: 60 points (answer time: 90 seconds on average)

[1372] Problems to include in the next problem set:

[1373] 1. Add basic problems on formula transformation

[1374] 2. Include calculation questions as appropriate

[1375] 3. Add new geometry problems.

[1376] The AI ​​model then generates an optimized set of questions for the next problem based on this prompt. This completes the concrete implementation of the present invention, allowing users to study efficiently and focus on overcoming their weak areas.

[1377] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1378] Step 1: Enter and submit your user information

[1379] When a user logs in for the first time, they enter information into the terminal, such as their preferred school, current academic level, strong and weak subjects, etc. The input data is saved on the terminal and later sent to the server.

[1380] Specific behavior:

[1381] A user fills out a web form or mobile application.

[1382] The input data is converted to JSON format.

[1383] The terminal transmits the data to the server.

[1384] Input: desired school, academic level, strong subjects, weak subjects

[1385] Output: User information sent to the server

[1386] Step 2: Server receives information and creates profile

[1387] The server receives the information sent by the user and stores it in a database, which creates a profile for each user.

[1388] Specific behavior:

[1389] The server receives an HTTP request from the device.

[1390] The received data is stored in a database and a user profile is generated.

[1391] Input: User information sent from the device

[1392] Output: User profile stored in the database

[1393] Step 3: Generate the initial problem set

[1394] The server generates an initial problem set based on the user profile, selects relevant problems from a problem database, and generates an optimal problem set using a generative AI model.

[1395] Specific behavior:

[1396] The server looks up the user profile.

[1397] Query the issues database to get a list of issues.

[1398] A generative AI model selects and refines the problems to generate an initial set of problems.

[1399] Input: User profile information

[1400] Output: The generated initial problem set

[1401] Step 4: View the question and enter your answer

[1402] The terminal displays the problem set received from the server to the user, who then inputs the answers to the problems. The answers are recorded along with the answer time.

[1403] Specific behavior:

[1404] The device parses the JSON formatted problem data it receives and formats it for display.

[1405] The user enters the answer and the terminal records it.

[1406] Input: Generated initial problem set

[1407] Output: Answer data entered on the terminal and answer time

[1408] Step 5: Submit your answers

[1409] The terminal transmits the user's answer data and answer time to the server.

[1410] Specific behavior:

[1411] The device converts the answer data into JSON format.

[1412] Send the data to the server.

[1413] Input: Answer data and answer time entered into the terminal

[1414] Output: Answer data and answer time sent to the server

[1415] Step 6: Answer analysis and feedback generation

[1416] The server analyzes the received answer data and determines whether it is correct or incorrect. It also evaluates the answer time and answer tendency to identify the user's weak areas. The analysis results are saved in a progress database and used to generate the next problem set.

[1417] Specific behavior:

[1418] The server inputs the answer data into the analysis engine.

[1419] The answers are judged to be correct or incorrect, and the evaluation results are stored in a database.

[1420] Input: Answer data and answer time sent to the server

[1421] Output: Analysis results and updated user profile

[1422] Step 7: Dynamic question generation and distribution

[1423] The server generates the next set of problems based on the user's latest progress data. The generative AI model optimizes the problems by taking into account the user's learning habits and other user data. The optimized set of problems is then sent to the device.

[1424] Specific behavior:

[1425] The server references the user's progress data.

[1426] The generative AI model generates the next set of problems.

[1427] Send the problem set to the device.

[1428] Input: Updated user profile and progress data

[1429] Output: The next optimized problem set

[1430] Step 8: Feedback on learning progress

[1431] The server periodically generates a report that provides feedback on the user's learning progress and sends it to the user's device, including the user's achievement level, areas for improvement, and advice on the next learning plan.

[1432] Specific behavior:

[1433] The server analyzes the progress data and generates a feedback report.

[1434] The feedback report is formatted in PDF or HTML format and sent to the device.

[1435] Input: Updated user profile and progress data

[1436] Output: A feedback report that is displayed to the user

[1437] (Application example 1)

[1438] 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."

[1439] Conventional learning systems have the problem of reducing learning efficiency because they are unable to provide questions tailored to each user's academic ability or specific areas of interest.In addition, they lack the technology to dynamically optimize and provide questions based on a detailed analysis of the user's progress and answer trends, making it difficult to maximize the user's learning proficiency.

[1440] 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.

[1441] In this invention, the server includes means for receiving information entered by the user when logging in for the first time, means for generating an initial problem set based on the information entered by the user, means for displaying problems on the user's terminal and prompting the user to enter answers, means for receiving and analyzing the user's answer information, means for optimizing and generating subsequent problems based on the user's answers, means for transmitting the optimized problem set to the user's terminal, and means for generating and providing a report that provides feedback on the user's learning progress based on the user's answers. This allows the user's learning progress to be dynamically optimized, enabling efficient learning that focuses on specific areas of interest or weak areas.

[1442] "Information entered by the user at the time of initial login" refers to data such as personal information, learning goals, areas of strength and weakness, etc., provided by the system user at the time of initial login.

[1443] "Generating an initial problem set" refers to the process of creating problems that correspond to the current knowledge level and interests of each individual learner based on the received user information.

[1444] A "user device" is an electronic device used by a user to solve problems and input answers, including a smartphone, tablet, or PC.

[1445] "Receiving and analyzing answer information" refers to the process in which the server receives the answers to the questions entered by the user and evaluates whether they are correct or not and the tendency of the answers.

[1446] "Generating optimal questions for the next test" means dynamically generating new questions that address the user's specific needs and weak areas based on the analyzed answer information.

[1447] "Sending the optimized problem set to the user's terminal" means delivering the generated new problem set to the user's learning device.

[1448] "Generating and providing a report that provides feedback on learning progress" refers to the process of creating a report that visually shows the user's learning situation and progress, and supporting the user with instruction and future learning plans.

[1449] The present invention is a system that dynamically generates and provides questions to maximize the learning efficiency of each user. This system functions in cooperation with the user, the terminal, and the server.

[1450] 1. User information registration

[1451] When a user logs in for the first time, they enter information such as their preferred school, current academic level, strong and weak subjects, etc. This information is sent to the server via the user's terminal.

[1452] 2. Generating the initial problem set

[1453] Based on the received information, the server generates an initial problem set that is tailored to the learner's current level of knowledge and specific areas of interest, with a particular focus on subjects in which the user is weak.

[1454] 3. Displaying and answering questions

[1455] The generated question set is displayed on the user's device, and the user inputs answers to the questions. Answers can be in various formats, such as multiple choice or written answers. The answers entered by the user are sent to the server via the device.

[1456] 4. Answer Analysis

[1457] The server analyzes the received answer data and determines whether each question is correct. It also evaluates answer times and answer trends to identify the user's weak areas. The results of this analysis are stored in the user's progress database.

[1458] 5. Generation of the next problem set

[1459] The server generates the next set of questions based on the user's latest progress. This process uses a generative AI model that takes into account the user's answering habits and the accuracy rates of other users. The optimized set of questions is then sent back to the user's device and presented to them.

[1460] 6. Feedback and progress management

[1461] The server periodically generates a report that provides feedback on the user's learning progress. This report includes the user's learning status, areas for improvement, goals achieved, and advice on future learning plans. The device displays this report to the user to support their learning.

[1462] Specific examples

[1463] For example, if a user wants to learn something specific in a particular field or area of ​​interest, the first time the system generates questions such as "calculating the optimal number of inventory orders" or "simulating handling complaints." Once the user solves these, the server analyzes the answers and evaluates their performance in that particular field. Based on this result, the next time the system presents questions tailored to the user's progress and areas of weakness.

[1464] The hardware used includes "user devices" such as smartphones, tablets, and PCs, as well as "servers" that connect to these devices. The software uses programming languages ​​such as Python to implement generative AI models.

[1465] Prompt Sentence Examples

[1466] "What are some effective ways to improve customer satisfaction?"

[1467] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1468] Step 1:

[1469] When a user logs in for the first time, they enter information such as their preferred school, current academic ability, and strong and weak subjects into their device. The server receives this information and stores it in a database. The input data includes the user's personal information, and a user profile is created based on this information.

[1470] Input: Information such as desired school, current academic ability, strong subjects, weak subjects, etc. entered by the user into the device.

[1471] Output: The user profile stored on the server.

[1472] Step 2:

[1473] The server generates an initial problem set based on the user's profile. Using a generative AI model, it selects problems from a variety of areas, focusing on the user's weak areas. This problem set is then sent to the device and displayed to the user.

[1474] Input: User profile, problem database.

[1475] Output: The initial problem set displayed on the user's device.

[1476] Step 3:

[1477] The user inputs answers to the questions displayed on the terminal. Answers can be in multiple formats, such as multiple choice or written format, and the terminal records the user's answers and the time it took to answer them, and sends them to the server.

[1478] Input: The answer to the question that the user types into the terminal.

[1479] Output: Answer data sent to the server (answer content, answer time).

[1480] Step 4:

[1481] The server analyzes the received answer data, determines whether each question is correct, and evaluates the answer time and answer trends. Based on the analysis results, the user's progress database is updated.

[1482] Input: The answer data sent to the server.

[1483] Output: Correct / incorrect result, update of user's progress database.

[1484] Step 5:

[1485] The server generates the next set of problems based on the latest progress data. Using a generative AI model, it creates optimized problems that take into account the user's answering tendencies and the accuracy rates of other users, and sends them to the device.

[1486] Input: User progress database, question database.

[1487] Output: The optimized next problem set, the problem set sent to the device.

[1488] Step 6:

[1489] The server periodically generates a report that provides feedback on the user's learning progress. The report includes the user's learning status, areas for improvement, achievement goals, and advice on future learning plans, and is sent to the user's terminal and displayed to the user.

[1490] Input: User progress database.

[1491] Output: Feedback report, report displayed on terminal.

[1492] Step 7:

[1493] The user can check the feedback report through their device and reflect it in their next study. This makes it easier to study efficiently and continue. For example, if a user receives feedback that they are "strong at calculation problems but weak at formula transformations," the next problem set will include many formula transformation problems. This will allow them to improve their weak areas.

[1494] Input: Feedback report.

[1495] Output: Next lesson plan, user progress improvement.

[1496] 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.

[1497] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can further maximize individual learning efficiency and improve the user's learning experience.

[1498] System Overview

[1499] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. This problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[1500] Emotion engine integration

[1501] The present invention incorporates an emotion engine that recognizes the emotions of users when answering questions. The emotion engine detects user emotions using facial recognition, voice tone analysis, and even biometric data (such as heart rate).

[1502] Initial setup and receiving information

[1503] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, and strong and weak subjects. This information is sent to the server via the terminal. The server stores the received information in a database and creates a user profile based on it.

[1504] Problem set generation

[1505] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. In addition, the server also performs initial settings to match the emotion engine.

[1506] Answer to the question

[1507] The user enters the answer to the displayed question. At this time, the emotion engine installed in the device analyzes the user's face and voice in real time to obtain emotional data. This emotional data is sent to the server along with the answer data.

[1508] Answer analysis and feedback

[1509] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the time it takes to answer and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. These analysis results are stored in the user's progress database and are used to generate the next set of questions to be presented.

[1510] Dynamic Problem Generation

[1511] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[1512] Specific examples

[1513] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these, the server analyzes the answers and identifies a tendency that the user is "good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1514] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[1515] Feedback and progress management

[1516] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes areas for improvement, achieved goals, and advice on the next learning plan. The device displays this feedback report to the user to support their learning.

[1517] The above is a specific embodiment of the system of the present invention, which allows users to focus on strengthening their weak areas and study efficiently while receiving emotional support.

[1518] The processing flow will be explained below.

[1519] Step 1:

[1520] When a user logs in for the first time, they enter information such as their preferred school, current academic level, and weak subjects.

[1521] Step 2:

[1522] The device sends the entered information to the server, which includes the user ID and data in JSON format.

[1523] Step 3:

[1524] The server stores the received user information in a database and creates a user profile.

[1525] Step 4:

[1526] The server generates an initial problem set based on the user profile. The server selects a wide range of problems from the problem database and provides the user with a set that includes cross-disciplinary problems.

[1527] Step 5:

[1528] The server sends the generated question set to the terminal, which includes the question ID, question text, and choice data.

[1529] Step 6:

[1530] The terminal displays the received problem set on the interface and asks the user questions.

[1531] Step 7:

[1532] The user enters answers to the displayed questions, while the device's built-in camera and microphone simultaneously analyze the user's facial expressions and tone of voice to obtain emotional data.

[1533] Step 8:

[1534] The device simultaneously transmits answer data and emotion data to the server, which includes the question ID, multiple choice or written answer, answer time, and emotion data.

[1535] Step 9:

[1536] The server analyzes the received answer data and emotion data, determining whether the answer was correct or incorrect and evaluating the response time and emotion fluctuations. For example, if there were many emotions indicating anxiety, that evaluation will also be included.

[1537] Step 10:

[1538] The server stores the analysis results in a database and updates the user's progress data, including the percentage of correct answers, the time it takes to complete the test, and the identification of weak areas.

[1539] Step 11:

[1540] The server generates the next set of questions based on the latest user data and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's answering tendencies and emotional data.

[1541] Step 12:

[1542] The server sends the generated problem set to the terminal.

[1543] Step 13:

[1544] The terminal displays the newly generated problem set to the user, who then answers the problems again.

[1545] Step 14:

[1546] The server periodically collects the user's learning progress and emotional data and generates a feedback report, which includes the goals achieved, areas for improvement, and the next learning plan.

[1547] Step 15:

[1548] The device displays the generated feedback report to the user, who can then create a new study plan based on the feedback and begin their next study.

[1549] The above is a description of the specific processing steps of the system. By optimizing the user's learning experience through the analysis of emotion data, users can learn efficiently and effectively.

[1550] Example 2

[1551] 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."

[1552] Current educational systems struggle to fully consider each user's individual academic ability, learning attitude, and emotional state, making it difficult to maximize individual learning efficiency. Furthermore, they lack the ability to present adaptive questions based on the user's progress and emotions, resulting in a lack of improvement in the user's learning experience.

[1553] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for acquiring and receiving the user's emotional data, means for optimizing and generating the next problem to be posed based on the user's answer results and emotional data, and means for transmitting the optimized problem set to the user's terminal. This enables more personalized learning that takes into account the user's individual academic ability and emotional state.

[1554] "User" refers to an individual who uses this system to advance their learning.

[1555] "Terminal" refers to an electronic device that is operated by a user to display questions and input answers.

[1556] "Server" refers to a central processing unit that receives and analyzes data sent from terminals, and generates and sends problem sets.

[1557] "Input information" refers to information related to learning that a user provides when logging in for the first time, and specifically includes personal information, learning goals, desired schools, strong subjects, weak subjects, etc.

[1558] A "problem set" refers to a series of questions that are presented to a user.

[1559] "Answer information" refers to the data of the answer entered by the user to the question.

[1560] "Emotional data" refers to data on the emotional state obtained by analyzing information such as facial recognition, voice tone, and heart rate obtained when the user answers questions.

[1561] "Progress data" refers to data that indicates the user's learning progress and results.

[1562] A "generative AI model" refers to an artificial intelligence model used to analyze a user's answering tendencies and areas of weakness, and optimize the next questions to be asked.

[1563] This invention is a dynamic question generation system for improving the user's learning experience, and aims to maximize the user's learning efficiency by utilizing an emotion engine and a generative AI model. This system comprehensively covers a series of processes, from initial setup to question generation, answer analysis, next question generation, and feedback.

[1564] Hardware and software used

[1565] The system uses the following main hardware and software:

[1566] Server: Receives data, analyzes it, generates questions, and provides feedback. Specifically, it uses Python scripts, a SQL database, and generative AI models.

[1567] Terminal: A device (PC, tablet, smartphone) operated by the user that displays questions, inputs answers, and acquires emotional data. It has a built-in camera and microphone, and analyzes the user's face and voice tone in real time.

[1568] Emotion Engine: Analyzes user emotions based on biometric data such as facial recognition, voice tone analysis, and heart rate. Provides an API for sending data to the server.

[1569] Initial setup and receiving information

[1570] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. This information is sent to the server via their device. The server stores the received information in a database and creates a user profile based on it.

[1571] Problem set generation

[1572] The server generates an initial set of questions based on the user's profile, randomly selects questions from the question database, and focuses on subjects the user is weak in. It also initializes the emotion engine.

[1573] Answering questions and obtaining emotion data

[1574] The user inputs their answers to the displayed questions. The device uses a built-in camera and microphone to recognize the user's face and analyze their voice tone in real time to obtain emotional data. This data is then sent to the server along with the answer data.

[1575] Answer analysis and feedback

[1576] The server receives the answer data and emotion data and begins analysis using a Python script. It determines whether the answer is correct, evaluates the answer time, analyzes emotional fluctuations, and generates appropriate feedback. If the user feels stressed by a particular problem, it adjusts the difficulty and content of the problem. The analysis results are saved in a progress database and are used to generate the next set of problems.

[1577] Dynamic Problem Generation

[1578] The server generates the next set of questions based on the latest progress and emotional data. It uses a generative AI model to select the most appropriate questions, taking into account the user's weak areas and emotional state. The optimized set of questions is then sent to the device, where it is presented to the user again.

[1579] Providing feedback

[1580] The server periodically collects the user's progress and emotion data and generates a feedback report, which includes areas for improvement, achieved goals, and advice for the next learning plan. The device displays this feedback report to the user to support their learning.

[1581] Specific examples

[1582] For example, consider a case where a user wants to go to university but is not good at math when logging in for the first time. The server generates a problem set containing many basic math problems and presents it to the user. This set includes calculation problems, formula transformations, and basic geometry problems. When the user answers these, the server analyzes the answers and identifies tendencies such as "the user is good at calculations but takes a long time to transform formulas." Based on the results of this analysis, the next problem set will include more formula transformation problems.

[1583] Furthermore, if the emotion engine determines that the user feels anxious when solving mathematical transformation problems, the server generates a set of problems that include problems of gradually increasing difficulty and problems with many hints in order to alleviate the anxiety.

[1584] Prompt Sentence Examples

[1585] For example, by inputting a prompt such as, "Give a third-year high school student who is not good at transforming mathematical formulas some problems that require them to transform mathematical formulas. Gradually increase the difficulty so that the student does not feel stressed when solving the problems. Add hints to each problem and provide feedback after the student answers," into a generative AI model, a problem set optimal for specific learning needs and emotional state can be generated.

[1586] The above is a specific embodiment of the present invention. By using this system, users can obtain an optimal learning experience that takes into account their individual academic ability and emotional state.

[1587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1588] Divide the processing flow of the system program into processing steps

[1589] Step 1:

[1590] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, favorite subjects, and favorite subjects. The input data is saved on the device in JSON format and then sent to the server.

[1591] Step 2:

[1592] When the device receives the user's input data, it sends it to the server using the HTTPS protocol. The server receives the data and stores it in a MySQL database, which creates a user profile.

[1593] Step 3:

[1594] The server generates an initial set of questions based on the user's profile, randomly selects questions from a database of questions using SQL queries, and sends the resulting set of questions to the device in JSON format.

[1595] Step 4:

[1596] The device displays the received problem set to the user, who then enters answers to the displayed problems, and the answer data is saved in JSON format on the device.

[1597] Step 5:

[1598] The emotion engine installed on the device analyzes the user's face, voice tone, and heart rate in real time to obtain emotion data, which is then sent to the server along with the answer data.

[1599] Step 6:

[1600] The server analyzes the answer data and emotion data received. Using a Python script, it determines whether the answer is correct, evaluates the answer time, and analyzes emotional fluctuations, and creates an adjustment plan if the user is feeling stressed by a particular problem. The results of this analysis are stored in a progress database.

[1601] Step 7:

[1602] The server generates the next set of problems based on the user's latest progress and emotional data. It uses a generative AI model to select the most appropriate problems based on the user's weak areas and emotional state. The generated problem set is sent to the device in JSON format.

[1603] Step 8:

[1604] The device displays the optimized problem set to the user, and at the same time, a feedback report is sent from the server and displayed on the device, including areas for improvement, goals achieved, and advice for the next study plan.

[1605] Detailed explanation of each processing step

[1606] Step 1:

[1607] When a user logs in for the first time, they enter their personal information, learning goals, preferred school, strong and weak subjects in a dedicated input form. For example, if a user enters "I'm not good at math," the device converts this into JSON format, saves it, and sends it to the server.

[1608] Step 2:

[1609] Once the device receives the user's input data, it sends it to the server via an HTTPS request. The server receives the data and stores it in a MySQL database. This creates a user profile, including initial settings based on the user's learning goals and preferred schools.

[1610] Step 3:

[1611] The server uses SQL queries to select questions related to the subjects the user is weak at from the question database. It then generates the initial question set and sends it to the device in JSON format. For example, if the user enters "I'm weak at math," a question set containing many basic math questions will be generated.

[1612] Step 4:

[1613] The device displays the received problem set to the user. The user answers the problems, and the answer data is saved on the device. For example, problems involving integer calculations and transformations of basic mathematical expressions are included.

[1614] Step 5:

[1615] The emotion engine installed on the device detects the user's face and voice in real time through facial recognition, voice tone analysis, heart rate, etc. to obtain emotion data. This data is sent to the server along with the answer data. For example, if the user is confused by a mathematical transformation problem, the emotion engine will obtain that data.

[1616] Step 6:

[1617] The server analyzes the answer data and emotion data it receives. A Python script is used to determine whether the answer is correct, and to analyze the time it took to answer and fluctuations in the user's emotions. If it determines that a particular problem is causing stress to the user, the difficulty and content of the next problem can be adjusted. For example, if it takes a long time to transform a mathematical formula, a plan can be made to focus on that part of the problem.

[1618] Step 7:

[1619] The server uses the generative AI model to generate the next set of problems based on the latest progress data and emotion data. An example prompt might be, "For a high school senior who is not good at transforming mathematical formulas, please provide mathematical formula transformation problems with gradually increasing difficulty." This optimizes the generated problem set and sends it to the device in JSON format.

[1620] Step 8:

[1621] The device displays the optimized problem set to the user. At the same time, a feedback report is sent from the server and displayed on the device. The feedback report includes advice such as, "You seemed confused when transforming the formula. Please focus on this part next time."

[1622] These are the specific processing steps of the system according to the present invention, which allows users to have a more efficient and personalized learning experience.

[1623] (Application example 2)

[1624] 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."

[1625] Conventional learning systems generate questions based solely on the user's answers, making it difficult to maximize individual learning efficiency. Furthermore, they generate questions without considering the user's emotional state, which can lead to stress and anxiety, potentially resulting in a poor learning experience. This makes it impossible to provide consistently effective learning support to a diverse range of learners.

[1626] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information entered by the user at the first login, means for generating an initial problem set based on the user's input information, means for displaying problems on the user's terminal and prompting the user to input answers, means for receiving and analyzing the user's answer information, means for optimizing and generating the next problem to be presented based on the user's answer results, means for transmitting the optimized problem set to the user's terminal, emotion recognition means for analyzing the user's emotion data, and means for adjusting the difficulty level of the problems taking the user's emotion data into consideration. This makes it possible to dynamically generate optimal problems based on the individual learning progress while taking the user's emotions into consideration.

[1627] A "user" is an individual who uses this system to study.

[1628] "Information entered at first login" refers to data such as learning goals, current academic level, desired school, strong and weak subjects, etc. that a user enters when using the system for the first time.

[1629] A "problem set" is a collection of multiple problems generated by the server based on the user's academic ability and learning goals.

[1630] A "terminal" is a device that a user uses to answer questions, such as a smartphone, tablet, or computer.

[1631] "Emotion data" is data that indicates the user's emotional state, and is information obtained through facial recognition, voice tone analysis, biological reactions, and the like.

[1632] "Answer information" is data that includes the content of the user's answer and the result of whether it was correct or incorrect.

[1633] The "answer result" is data on whether the answer is correct or incorrect based on the answer entered by the user.

[1634] A "generative AI model" is an algorithm that uses artificial intelligence to analyze a user's answering tendencies and areas of weakness, and then generates new questions.

[1635] "Emotion recognition means" refers to technology and devices for analyzing emotions from a user's facial expressions and voice.

[1636] The "means for adjusting the difficulty level" refers to a method and algorithm for appropriately adjusting the difficulty of questions to be posed, taking into account the user's emotional data.

[1637] The present invention relates to a dynamic question generation system that combines an emotion engine that recognizes the user's emotions, which can maximize individual learning efficiency and improve the user's learning experience.

[1638] System Overview

[1639] First, when a user logs in for the first time, they enter information such as their preferred school, current academic level, and their favorite and least favorite subjects. This information is sent to the server via the user's device. The server generates an initial problem set based on the received information. The problem set is composed of questions selected from a wide range of topics, with the aim of measuring the user's academic ability.

[1640] Emotion engine integration

[1641] The present invention incorporates an emotion engine that recognizes the user's emotions when answering questions. The emotion engine detects the user's emotions using facial recognition, voice tone analysis, and even biological response data (such as heart rate). This makes it possible to present questions that correspond to the user's emotional state.

[1642] Initial setup and receiving information

[1643] The server receives data such as personal information, learning goals, preferred schools, and strong and weak subjects entered by the user when they first logged in. This data is sent to the server and stored in a database. The server then creates a user profile based on this data.

[1644] Problem set generation

[1645] The server generates an initial set of problems based on the user's profile. The server randomly selects problems from a database of problems across a variety of fields, placing emphasis on subjects the user is weak in. It also performs initial settings to match the emotion engine.

[1646] Answer to the question

[1647] The user enters an answer to the displayed question. At this time, the emotion engine installed on the device analyzes the user's face and voice in real time to obtain emotional data. The obtained answer data and emotional data are then sent to the server.

[1648] Answer analysis and feedback

[1649] The server analyzes the received answer data and emotion data. It determines whether each question is correct or incorrect, and evaluates the answer time and the user's emotional state. If it determines that a particular question is causing stress to the user, it adjusts the difficulty and content of the question. The results of this analysis are stored in the user's progress database and are used to generate the next set of questions.

[1650] Dynamic Problem Generation

[1651] The server generates the next set of questions based on the user's latest progress and emotional data. Using a generative AI model, it selects the most appropriate questions, taking into account the user's weak areas and emotions. The optimized set of questions is then sent back to the device and presented to the user.

[1652] Specific examples

[1653] For example, if a user applies to University A and indicates that they are not good at math, the server will initially generate a problem set containing many basic math problems. This set includes calculation problems, formula transformations, and basic geometry problems. When the user solves these problems, the server analyzes the answers and identifies a tendency for the user to be "good at calculations but take a long time to transform formulas." Based on this analysis, the next problem set will include more formula transformation problems. Furthermore, if the emotion engine determines that the user feels anxious about solving formula transformation problems, the server will generate a set that includes problems of gradually increasing difficulty and problems with many hints to alleviate the anxiety.

[1654] Example prompts to input to a generative AI model:

[1655] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[1656] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[1657] Generate a suitable problem set.

[1658] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1659] Step 1:

[1660] When a user logs in for the first time, they enter data such as personal information, learning goals, preferred schools, and strong and weak subjects. When the user enters this information into a dedicated form on their device and presses the send button, the data is sent from the device to the server. The input data includes learning goals, current academic level, preferred schools, strong and weak subjects, etc. The server receives this data and stores it in a database.

[1661] Step 2:

[1662] The server generates an initial problem set based on the received user data. It creates a well-balanced problem set, taking into account the user's strong and weak subjects. It randomly selects problems from a variety of fields from the problem database. It generates the initial problem set, placing particular emphasis on subjects the user is weak in. The generated problem set is sent to the terminal and displayed on the screen.

[1663] Step 3:

[1664] The terminal provides a UI that allows the user to input answers to the displayed problem sets. The user answers the problems and enters the results into the terminal. The input answer information is sent to the server via the terminal.

[1665] Step 4:

[1666] The emotion engine installed on the device captures emotional data in real time while the user answers questions. This is done by using a camera and microphone to recognize faces, analyze voice tones, and capture biometric data. This allows the user's emotional state, such as stress, anxiety, or happiness, to be analyzed. The captured emotional data is sent to the server along with the answer data.

[1667] Step 5:

[1668] The server analyzes the received answer data and emotional data. First, it determines whether each question is correct based on the answer data, and analyzes the user's answering tendencies and areas of strength and weakness. At the same time, it analyzes the emotional data and evaluates fluctuations in the user's emotions. For example, it can detect an increase in stress level in response to a particular question. The analysis results are stored in the user's progress database.

[1669] Step 6:

[1670] The server generates the next set of questions based on the user profile, answers, and emotional data. It uses a generative AI model to generate and apply prompts such as:

[1671] User data: {"desired_school": "University A", "current_level": "Intermediate", "weak_subjects": ["Mathematics"], "strong_subjects": ["English"]}

[1672] Emotion data: {"happiness": 0.1, "confidence": 0.2, "stress": 0.7}

[1673] Generate a suitable problem set.

[1674] The generated problem set is adjusted to include the most appropriate problems, taking into account the user's weak areas and emotional state.

[1675] Step 7:

[1676] The server then sends the optimized problem set to the user's device. The next time the user studies, they can receive the newly generated problem set and continue studying. Through this process, the user can continuously enjoy a personalized learning experience.

[1677] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1678] 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.

[1679] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1680] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1681] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1682] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1683] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1684] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1685] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1686] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1687] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1688] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1689] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1690] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1691] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1692] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1693] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1694] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1695] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1696] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1697] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1698] The following is further disclosed regarding the above embodiment.

[1699] (Claim 1)

[1700] means for receiving information entered by a user at initial login;

[1701] means for generating an initial problem set based on user input;

[1702] a means for displaying questions on a user's terminal and prompting the user to input answers;

[1703] means for receiving and analyzing user answer information;

[1704] A means for optimizing and generating a next question based on the user's answer results;

[1705] means for transmitting the optimized problem set to a user terminal;

[1706] A system including:

[1707] (Claim 2)

[1708] The system of claim 1 uses a generative AI model that analyzes a user's answering tendencies and areas of weakness.

[1709] (Claim 3)

[1710] 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users.

[1711] "Example 1"

[1712] (Claim 1)

[1713] means for receiving information entered by a user at initial login;

[1714] means for generating an initial problem set based on user input;

[1715] a means for displaying questions on a user's terminal and prompting the user to input answers;

[1716] means for receiving and analyzing user answer information;

[1717] A means for optimizing and generating a next question based on the user's answer results;

[1718] means for transmitting the optimized problem set to a user terminal;

[1719] a means for recording answer times;

[1720] means for generating feedback based on user progress data;

[1721] A system including:

[1722] (Claim 2)

[1723] The system of claim 1 uses a generative AI model that analyzes a user's answering tendencies and areas of weakness.

[1724] (Claim 3)

[1725] 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users.

[1726] "Application Example 1"

[1727] (Claim 1)

[1728] means for receiving information entered by a user at initial login;

[1729] means for generating an initial problem set based on user input;

[1730] a means for displaying questions on a user's terminal and prompting the user to input answers;

[1731] means for receiving and analyzing user answer information;

[1732] A means for optimizing and generating a next question based on the user's answer results;

[1733] means for transmitting the optimized problem set to a user terminal;

[1734] means for generating and providing a report that provides feedback on the user's learning progress based on the user's answers;

[1735] A system including:

[1736] (Claim 2)

[1737] The system of claim 1 uses a generative AI model that analyzes a user's answering tendencies and areas of weakness.

[1738] (Claim 3)

[1739] 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users.

[1740] "Example 2: Combining Emotion Engines"

[1741] (Claim 1)

[1742] means for receiving information entered by a user at initial login;

[1743] means for generating an initial problem set based on user input;

[1744] a means for displaying questions on a user's terminal and prompting the user to input answers;

[1745] means for receiving and analyzing user answer information;

[1746] means for acquiring and receiving user emotion data;

[1747] A means for optimizing and generating a next question based on the user's answer results and emotion data;

[1748] means for transmitting the optimized problem set to a user terminal;

[1749] A system including:

[1750] (Claim 2)

[1751] The system of claim 1 uses a generative AI model that analyzes a user's answering tendencies and areas of weakness.

[1752] (Claim 3)

[1753] 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users.

[1754] "Application example 2 when combining emotion engines"

[1755] (Claim 1)

[1756] means for receiving information entered by a user at initial login;

[1757] means for generating an initial problem set based on user input;

[1758] a means for displaying questions on a user's terminal and prompting the user to input answers;

[1759] means for receiving and analyzing user answer information;

[1760] A means for optimizing and generating a next question based on the user's answer results;

[1761] means for transmitting the optimized problem set to a user terminal;

[1762] emotion recognition means for analyzing emotion data of a user;

[1763] a means for adjusting the difficulty of the questions taking into account the user's emotional data;

[1764] A system including:

[1765] (Claim 2)

[1766] The system of claim 1 uses a generative AI model that analyzes a user's answering tendencies and areas of weakness.

[1767] (Claim 3)

[1768] 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users. [Explanation of symbols]

[1769] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving information entered by a user at initial login; means for generating an initial problem set based on user input; a means for displaying questions on a user's terminal and prompting the user to input answers; means for receiving and analyzing user answer information; A means for optimizing and generating a next question based on the user's answer results; means for transmitting the optimized problem set to a user terminal; A system including:

2. The system of claim 1 uses a generative AI model that analyzes the user's answering tendencies and areas of weakness.

3. 2. The system according to claim 1, further comprising means for optimizing questions by taking into consideration the progress data of the user and the accuracy rates of other users.

Images