System

Abstract

To provide systems.SOLUTION: A system includes the means of: selecting an education institution users aim at; acquiring, by a server, trend data on the selected education institution; based on the trend data on the education institution the server acquires, inputting a prompt sentence to a generative AI model; based on the prompt sentence, generating, by the generative AI model, generating questions; providing, by the server, the user with the generated question; and integrating an individual curriculum and an update analysis, in which the means of integrating the individual curriculum and the update analysis is configured to review the individual curriculum on the basis of a score point of the question suggested to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional exam preparation methods are limited to questions from the past few years, making it difficult to provide questions that match the trends and level of the university you are aiming for. Furthermore, there is no system that integrates individual curriculum and progress analysis to provide students with a chance of passing their desired university with minimal study. [Means for solving the problem]

[0005] Utilizing AI that generates past exam questions, we provide preparation tailored to the university of your choice. We automatically generate questions that are in line with the trends and level of each university, and integrate individual curriculum and progress analysis. This gives you the chance to pass your desired university with minimal study, without being restricted by past years' exams. Furthermore, by accurately grasping the needs of test takers and utilizing innovative technology, we maximize the effectiveness of their studies and make their dream of passing their desired school a reality. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 is equipped with 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, sound 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 sound in accordance with instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] It's a camera.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] The present invention is an exam preparation system that utilizes AI to generate past exam questions. This system provides preparation tailored to the university of your choice. Specifically, it is equipped with AI that automatically generates questions tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, this system will automatically generate long-form English questions tailored to University A.

[0030] "Example 2"

[0031] Furthermore, this embodiment of the present invention has the function of integrating individualized curriculum and progress analysis. This allows students to manage their learning progress in a centralized manner, providing them with a chance to pass the entrance exam for their desired university with minimal study. For example, if a student has weaknesses in a particular area of ​​mathematics, this system can provide an individualized curriculum that focuses on that area.

[0032] "Example 3"

[0033] Furthermore, this embodiment of the present invention has the function of accurately grasping the needs of test takers and maximizing the effectiveness of learning by utilizing innovative technology. This allows test takers to be provided with the optimal learning method that suits their learning style and level of understanding, helping them realize their dream of passing the school of their choice. For example, if a test taker is good at visual learning, this system will provide visual learning materials and questions.

[0034] The processing flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: The student enters the university they are aiming for into the system.

[0037] Step 2: The system uses AI to generate past exam questions and automatically generate questions that are tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, the system will automatically generate long-form English questions for University A.

[0038] Step 3: The generated questions are provided to test takers and used for study.

[0039] "Example 2"

[0040] Step 1: Candidates enter their learning progress into the system.

[0041] Step 2: The system generates a personalized curriculum based on the learning progress entered. For example, if a student has weaknesses in a particular area of ​​mathematics, the system will provide a personalized curriculum focused on that area.

[0042] Step 3: The generated individual curriculum is provided to the student and used for study.

[0043] "Example 3"

[0044] Step 1: The candidate enters their learning style and level of understanding into the system.

[0045] Step 2: The system will provide the most suitable learning method based on the input information. For example, if the test-taker is a visual learner, the system will provide visual learning materials and questions.

[0046] Step 3: The provided learning methods are provided to the candidate and used for studying.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0049] With conventional test preparation systems, it was difficult to efficiently generate questions that matched the trends of specific educational institutions, making it difficult to tailor preparation to suit the educational institution that test takers were aiming for. Furthermore, they lacked functionality to integrate individualized curricula and progress analysis, making it impossible to maximize test takers' learning effectiveness. Furthermore, there was a need for a method that would not be limited by data from the past few years and would provide test takers with a chance of passing their desired educational institution with minimal study.

[0050] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for the user to select an educational institution to which the user aspires, a means for the server to acquire trend data for the selected educational institution, a means for the server to input a prompt sentence to the generative AI model based on the trend data acquired by the server, a means for the generative AI model to generate questions based on the prompt sentence, a means for the server to provide the generated questions to the user, and a means for integrating an individual curriculum and progress analysis. This enables the user to efficiently study preparation questions tailored to the educational institution to which the user aspires.

[0051] "User" refers to an individual who uses the system to study practice questions tailored to the educational institution they are aiming for.

[0052] "Server" refers to a computer system that processes data in response to user requests, generates questions using a generative AI model, and provides them to users.

[0053] "Educational Institution" refers to a particular school, university, or other learning institution that a user is pursuing.

[0054] "Trend data" refers to information about past entrance examination questions and question trends of a particular educational institution.

[0055] A "generative AI model" refers to an artificial intelligence model that automatically generates questions tailored to a specific educational institution based on a prompt.

[0056] A "prompt" refers to text that provides specific instructions for generating questions to a generative AI model.

[0057] "Individualized curriculum" refers to a customized learning plan based on a user's learning progress and goals.

[0058] "Progress analysis" refers to the process of evaluating a user's learning status and analyzing the effectiveness and progress of their learning.

[0059] "Problem" refers to a learning task that the user must solve, generated by a generative AI model.

[0060] This invention is an exam preparation system that utilizes past exam question generation AI, and aims to enable users to efficiently study exam questions tailored to the educational institution they are aiming for. This system involves a series of processes in which the user selects the educational institution they are aiming for, a server obtains trend data for the selected educational institution, inputs prompts into a generative AI model to generate questions, and provides the generated questions to the user.

[0061] Hardware and software used

[0062] Server: Database Management System (DBMS), generative AI model, HTTP server

[0063] Device: Web browser or dedicated application

[0064] User: The device used to access the system (PC, tablet, smartphone, etc.)

[0065] Data processing and calculation

[0066] 1. The user selects the educational institution they wish to attend

[0067] A user logs in to the system and selects the educational institution they are interested in. For example, to select "University A," the user selects "University A" from the drop-down menu and clicks the "Select" button.

[0068] 2. The server retrieves the institution's trend data.

[0069] The server retrieves data about past entrance exam questions and question trends for the educational institution selected by the user from the database. For example, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'University A'" to extract the required data.

[0070] 3. The server inputs a prompt to the generative AI model.

[0071] The server inputs a prompt to the generative AI model based on the acquired trend data. The prompt is text that gives the generative AI model specific instructions for generating questions. For example, it generates a prompt such as "Please generate a long-answer English question for University A."

[0072] 4. Generative AI models generate problems

[0073] Based on the prompt, the generative AI model generates questions that are in line with the trends of each educational institution. The generative AI model uses natural language processing technology to analyze the prompt and generate appropriate questions. For example, it generates long-form English questions for University A.

[0074] 5. The server provides the generated questions to the user.

[0075] The server sends the generated questions to the user's device so that the user can solve them. The server also sends the generated questions to the user's device as an HTTP response, which is then displayed in the user's browser or application. For example, a long-form English question for University A is displayed on the user's device.

[0076] Examples of concrete examples and prompts

[0077] Specific examples

[0078] If the user selects "University B," the server retrieves past math problem data from University B and inputs the prompt "Please generate math problems for University B" into the generative AI model. The generative AI model generates math problems for University B, and the server provides them to the user.

[0079] Prompt Sentence Examples

[0080] "Generate long-form English questions for University A."

[0081] "Generate math problems for University B"

[0082] "Generate physics problems from University C"

[0083] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[0084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0085] Step 1:

[0086] Users select the educational institution they wish to pursue

[0087] A user logs into the system and selects the educational institution of interest. Specifically, the user selects the educational institution using a drop-down menu or search function and clicks the "Select" button. The input is the name of the educational institution selected by the user, and the output is the name of the selected educational institution being sent to the server.

[0088] Step 2:

[0089] The server retrieves the institution's trend data.

[0090] The server retrieves data on past entrance exam questions and question trends for the educational institution selected by the user from the database. Specifically, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'selected educational institution'" to extract the required data. The input is the name of the selected educational institution, and the output is the trend data for that educational institution.

[0091] Step 3:

[0092] The server inputs a prompt to the generative AI model.

[0093] The server inputs a prompt to the generative AI model based on the acquired trend data. Specifically, the server generates a prompt such as "Please generate questions for a specific subject at the selected educational institution" and sends an HTTP POST request to the API endpoint of the generative AI model. The input is the trend data and the prompt, and the output is the prompt sent to the generative AI model.

[0094] Step 4:

[0095] Generative AI models generate problems

[0096] The generative AI model generates questions based on the prompt sentence, tailored to the trends of each educational institution. Specifically, the generative AI model analyzes the prompt sentence using natural language processing technology and generates appropriate questions. The input is the prompt sentence, and the output is the generated question.

[0097] Step 5:

[0098] The server provides the generated questions to the user.

[0099] The server sends the generated problem to the user's device so that the user can solve it. Specifically, the server sends the generated problem to the user's device as an HTTP response and displays it in the user's browser or application. The input is the generated problem, and the output is the problem displayed on the user's device.

[0100] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[0101] (Application example 1)

[0102] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] Conventional exam preparation systems have difficulty efficiently generating questions that are in line with the question trends of specific educational institutions, and are unable to integrate curriculum and progress analysis tailored to the individual needs of test takers. Furthermore, there is a lack of systems that can be easily used on mobile devices such as smartphones, making it difficult for test takers to study efficiently. This has made it difficult to maximize the effectiveness of test takers' learning in order to pass the entrance exams for their desired schools.

[0104] 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.

[0105] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest; a means for automatically generating questions tailored to the trends and level of each educational institution; a means for integrating individual curricula and progress analysis; a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user; and a means for displaying the generated questions on a smartphone. This enables test-takers to efficiently study questions tailored to the question trends of specific educational institutions, maximize their learning effectiveness through curricula and progress analysis tailored to their individual needs, and easily advance their studies to pass their desired schools.

[0106] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0107] "Target educational institution" refers to the specific school or university that the candidate is aiming to get into.

[0108] "Means of providing countermeasures" refers to methods of providing study methods and materials that will help students pass the entrance exams for the educational institutions they are aiming for.

[0109] "Trends and levels at each educational institution" refers to the characteristics and difficulty of the questions asked by each educational institution.

[0110] "Means for automatically generating questions" refers to a method for automatically creating test questions based on specific conditions using artificial intelligence.

[0111] "Individual curriculum" refers to a study plan tailored to each student's learning progress and goals.

[0112] "Progress analysis" is a method of assessing and analyzing a student's learning progress.

[0113] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[0114] "User-selected educational institutions and subjects" refers to the specific school or university that the candidate has chosen to study at, and the specific subjects that will be tested at that school or university.

[0115] "Means for displaying on a smartphone" refers to a method for displaying the generated test questions and learning content on a smartphone screen.

[0116] A system for implementing this invention includes a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest, a means for automatically generating questions that are in line with the trends and level of each educational institution, a means for integrating individual curriculums and progress analysis, a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user, and a means for displaying the generated questions on a smartphone.

[0117] Program processing explanation

[0118] Hardware used:

[0119] Smartphone

[0120] Software used:

[0121] OpenAI(R) API

[0122] Python

[0123] Data processing and calculation:

[0124] 1. User input: Users input the educational institution and subject they wish to study through a smartphone application.

[0125] 2. Prompt generation: The server generates a prompt based on the information entered by the user. For example, it generates a prompt such as "Please generate a long-answer English question for University A."

[0126] 3. Request to the AI ​​model: Send the generated prompt sentence to the OpenAI API and have the generative AI model (GPT-3 (registered trademark)) generate a problem.

[0127] 4. Problem retrieval: The server receives the problem returned by the generative AI model and formats it appropriately.

[0128] 5. Display on smartphone: The formatted questions are displayed on a smartphone application.

[0129] Specific examples

[0130] For example, if a user selects "Long-form English questions from University A," the following prompt sentence will be sent to the generative AI model.

[0131] Example prompt sentence:

[0132] Please generate long-form English questions for University A.

[0133] Based on this prompt, the generative AI model generates a long-form English question that matches the question trends of University A and returns it to the server. The server receives the question and displays it on the smartphone application.

[0134] In this way, users can efficiently study questions that match the exam trends of the educational institution they are aiming for through their smartphones. This allows students to maximize their learning effectiveness through a curriculum tailored to their individual needs and progress analysis, making it easy to study for admission to their desired school.

[0135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0136] Step 1:

[0137] Users launch the smartphone application and enter the educational institution and subject they wish to attend.

[0138] Input: Name of educational institution, subject name

[0139] Output: User input data (educational institution name, subject name)

[0140] Specific operation: The user enters the name of the educational institution and the name of the subject in the application's input form and presses the submit button.

[0141] Step 2:

[0142] The terminal transmits the user input data to the server.

[0143] Input: User-entered data (educational institution name, subject name)

[0144] Output: User-entered data sent to the server

[0145] Specific operation: The smartphone sends user input data to a server via the Internet.

[0146] Step 3:

[0147] The server generates a prompt sentence based on the received user input data.

[0148] Input: User-entered data (educational institution name, subject name)

[0149] Output: Generated prompt statement

[0150] Specific operation: The server generates a prompt such as "Please generate a long-answer English question for University A."

[0151] Step 4:

[0152] The server sends the generated prompt text to the OpenAI API and requests the generative AI model to generate a question.

[0153] Input: Generated prompt text

[0154] Output: The problem data returned by the generative AI model

[0155] Specific operation: The server sends a prompt to the OpenAI API, and the generative AI model (GPT-3) generates and returns a problem.

[0156] Step 5:

[0157] The server receives the problem data returned by the generative AI model and formats it appropriately.

[0158] Input: Problem data returned by the generative AI model

[0159] Output: Formatted problem data

[0160] Specific operation: The server analyzes the problem data received and converts it into a format that can be displayed on a smartphone.

[0161] Step 6:

[0162] The server sends the formatted question data to the terminal.

[0163] Input: Formatted question data

[0164] Output: Problem data sent to the terminal

[0165] Specific operation: The server sends the formatted problem data to the smartphone via the Internet.

[0166] Step 7:

[0167] The terminal displays the received question data to the user.

[0168] Input: Problem data sent to the terminal

[0169] Output: Problem data displayed on a smartphone screen

[0170] Specific operation: The smartphone displays the received problem data on the screen, allowing the user to solve the problem.

[0171] Example 2

[0172] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0173] With conventional learning support systems, it was difficult to accurately grasp each student's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, feedback on learning progress and curriculum updates were often done manually, making it difficult to provide efficient learning support. Furthermore, the system was limited in its ability to generate past exam questions and provide questions tailored to the trends of each university, failing to fully meet the needs of students.

[0174] 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: a means for a user to input learning progress and weaknesses; a means for a terminal to transmit the input data to the server; a means for the server to analyze the data using a generation AI model; a means for the server to generate an individual curriculum based on the analysis results; a means for the server to transmit the generated curriculum to the terminal and provide it to the user; a means for the user to periodically input learning progress and for the server to analyze progress data and update the curriculum; a means for integrating the individual curriculum and progress analysis; a means for utilizing past exam question generation AI to provide strategies tailored to the target university; a means for automatically generating questions tailored to the trends and level of each university; a means for providing a chance to pass the desired university with minimal study; and a means for accurately grasping the needs of test takers, maximizing the effectiveness of learning using innovative technology, and helping them realize their dream of passing the desired school. This makes it possible to accurately grasp each test taker's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, automatic feedback on learning progress and curriculum updates enable efficient learning support. In addition, the system has a wide range of features, including the generation of past exam questions and questions tailored to the trends of each university, allowing it to fully meet the needs of test takers.

[0175] "User" refers to a test-taker who uses the system to input their learning progress and weaknesses and receive an individualized curriculum.

[0176] "Terminal" refers to a device that allows a user to input their learning progress and weaknesses and communicate with the server.

[0177] "Server" refers to a computer system that receives data sent by users, analyzes the data using a generative AI model, and generates and provides an individual curriculum.

[0178] A "generative AI model" refers to an artificial intelligence model that analyzes a user's learning progress and weaknesses and generates an optimal individual curriculum.

[0179] "Study progress" refers to the progress and achievement of a user as they progress through their studies.

[0180] "Weakness" refers to a part in which the user has difficulty with a particular learning area or problem.

[0181] "Individualized curriculum" refers to a learning plan optimized for each individual user, generated based on the user's learning progress and weaknesses.

[0182] "Progress data" refers to data regarding the progress and achievement of learning that is periodically entered by the user.

[0183] "Past exam question generation AI" refers to an artificial intelligence model that automatically generates practice questions tailored to the university you are aiming for based on past exam questions.

[0184] "Trends and levels at each university" refers to the characteristics and difficulty of each university's exam questions.

[0185] "Feedback" refers to evaluation and advice on the user's learning progress.

[0186] "Curriculum update" refers to reevaluating an existing individual curriculum based on the user's progress data and changing the content as necessary.

[0187] The present invention is a system for managing the learning progress of test takers in an integrated manner and integrating individual curricula and progress analysis. Specific embodiments of this system are described below.

[0188] System Overview

[0189] This system allows users (test takers) to input their learning progress and weaknesses, and provides an optimal individual curriculum based on that. The system is primarily composed of a server, a terminal, and a generative AI model.

[0190] Hardware and software used

[0191] Server: A high-performance computer system that receives and analyzes data, generates and provides curriculum.

[0192] Device: A device used by a user (e.g., PC, tablet, smartphone) to input learning progress and weaknesses and display the curriculum.

[0193] Generative AI models: For example, advanced artificial intelligence models such as OpenAI's GPT-4 (registered trademark) are used to analyze user data and generate optimal curriculum.

[0194] Program processing

[0195] 1. User learning data input:

[0196] The user uses the terminal to input their learning progress and weaknesses, for example, "I can't solve calculus problems."

[0197] 2. Sending data to the server:

[0198] The device sends the input learning data to the server. Specifically, the device sends the data to the server using an HTTP request.

[0199] 3. Data Analysis:

[0200] The server inputs the received data into the generative AI model, which analyzes the user's learning progress and weaknesses. For example, the generative AI model might output an analysis result such as "The user has a weakness in differential and integral calculus."

[0201] 4. Creating a personalized curriculum:

[0202] Based on the analysis results of the generative AI model, the server generates an individual curriculum that focuses on the user's weaknesses. For example, the server generates a curriculum that covers calculus from the basics to applications.

[0203] 5. Curriculum Delivery:

[0204] The server sends the generated individual curriculum to the terminal. The terminal displays the received curriculum to the user. For example, the terminal displays a "Basic Calculus Problem Set" to the user.

[0205] 6. Learning progress feedback and updates:

[0206] The user periodically inputs their learning progress using the terminal. The terminal then sends the input progress data to the server. The server analyzes the progress data and updates the curriculum as necessary. For example, the server generates a curriculum that advances to advanced problems, since the user has cleared basic problems.

[0207] Specific examples

[0208] The user uses a device to input "I can't solve the basic calculus problems." The device sends this data to the server. The server analyzes the data using a generative AI model and determines that "the user has weaknesses in the basics of calculus." The server generates a "curriculum covering calculus from basic to advanced" and sends it to the device. The device displays this curriculum to the user. The user studies according to the curriculum and periodically inputs their progress. The server analyzes the progress data, and if it determines that the user has cleared the basic problems, it generates a curriculum to move on to advanced problems.

[0209] Prompt Sentence Examples

[0210] "Analyze the user's learning progress data and generate a personalized curriculum covering everything from the basics to advanced calculus."

[0211] In this way, a system is constructed in which the server, terminals, and users work together to support the learning of test takers.

[0212] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0213] Step 1:

[0214] The user uses the device to input their learning progress and weak points. Specifically, the user inputs "I can't solve calculus problems." The input data is information about the user's learning progress and weak points. The device temporarily stores this input data.

[0215] Step 2:

[0216] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP request to send data about the user's learning progress and weaknesses to the server. The input is the user's learning progress data, and the output is data sent to the server.

[0217] Step 3:

[0218] The server inputs the received data into the generative AI model. Specifically, the server passes the user's learning progress data to the generative AI model for analysis. The input is the user's learning progress data, and the output is the analysis results by the generative AI model. The generative AI model identifies the user's weaknesses and outputs an analysis result such as "The user has a weakness in differential calculus."

[0219] Step 4:

[0220] The server generates an individual curriculum based on the analysis results of the generative AI model. Specifically, the server receives the analysis results and creates a curriculum that focuses on the user's weaknesses. The input is the analysis results of the generative AI model, and the output is an individual curriculum. For example, the server generates a "curriculum from the basics to applications of calculus."

[0221] Step 5:

[0222] The server sends the generated individual curriculum to the terminal. Specifically, the server uses an HTTP response to send the generated curriculum to the terminal. The input is the individual curriculum, and the output is data sent to the terminal. The terminal displays the received curriculum to the user. For example, the terminal displays a "Basic Calculus Problem Set" to the user.

[0223] Step 6:

[0224] The user periodically inputs their learning progress using the device. Specifically, the user inputs "I have completed the basic calculus problems." The input data is information about the user's learning progress. The device temporarily stores this input data.

[0225] Step 7:

[0226] The terminal sends the input progress data to the server. Specifically, the terminal uses an HTTP request to send the user's learning progress data to the server. The input is the user's learning progress data, and the output is data sent to the server.

[0227] Step 8:

[0228] The server analyzes the progress data and updates the curriculum as necessary. Specifically, the server passes the progress data to a generative AI model for reanalysis. The input is the user's learning progress data, and the output is the updated curriculum. For example, the server generates a curriculum that moves on to advanced problems, since the user has cleared the basic problems.

[0229] Step 9:

[0230] The server sends the updated curriculum to the terminal. Specifically, the server uses an HTTP response to send the updated curriculum to the terminal. The input is the updated curriculum, and the output is data sent to the terminal. The terminal displays the received updated curriculum to the user. For example, the terminal displays "Application Problems for Calculus" to the user.

[0231] (Application example 2)

[0232] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0233] Conventional learning support systems have difficulty accurately analyzing each student's weaknesses and providing an optimal learning plan based on that analysis. Furthermore, they lacked the functionality to centrally manage learning progress and provide real-time feedback, making efficient learning difficult. Furthermore, there were limited ways to provide an immersive learning experience, preventing the effectiveness of learning from being maximized.

[0234] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for utilizing a past exam question generation AI to provide preparation tailored to the target university; means for automatically generating questions in line with the trends and level of each university; means for integrating individual curricula and progress analysis; means for centrally managing learning progress; means for automatically analyzing the weak points of test takers and generating curricula that focus on those areas; means for providing real-time feedback; means for proposing an optimal study plan using a generative AI model; means for storing and accessing data using a cloud database; and means for providing an immersive learning experience using a head-mounted display. This enables efficient learning that addresses the individual weaknesses of test takers, maximizing learning effectiveness.

[0235] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0236] "Measures tailored to the university you are aiming for" means providing the most appropriate study plan based on the entrance exam trends and level of the university you are aiming for.

[0237] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[0238] An "individual curriculum" is a customized study plan based on each student's learning progress and weaknesses.

[0239] "Progress analysis" is the process of evaluating a test-taker's learning progress and analyzing how far they have progressed.

[0240] "Means for centrally managing learning progress" refers to a method for managing test-takers' learning data in an integrated manner in a single system.

[0241] "Means for automatically analyzing test-taker's weaknesses" refers to a method for automatically identifying areas or items in which test-taker's weaknesses exist based on the test-taker's learning data.

[0242] "Means for generating a curriculum that focuses on that area" refers to a method for creating a curriculum that focuses learning on the identified weaknesses.

[0243] "Means of providing real-time feedback" are methods that provide immediate assessment and advice to test-takers as they progress through their studies.

[0244] A "generative AI model" is a model that uses artificial intelligence to generate optimal learning plans and questions from data.

[0245] A "cloud database" is a database that can be accessed via the Internet and is a system for storing and managing data.

[0246] A "head-mounted display" is a display device worn on the head that provides an immersive visual experience.

[0247] As an embodiment of the present invention, the following system is constructed.

[0248] System Overview

[0249] This system supports efficient learning by centrally managing students' learning progress and providing individualized curricula. The system is composed of a combination of technologies such as past exam question generation AI, generation AI models, cloud databases, and head-mounted displays.

[0250] Hardware and software used

[0251] Hardware: Smartphone, head-mounted display

[0252] Software: Cloud database (Firebase), generative AI model (GPT-4), real-time feedback system

[0253] Data processing and calculation

[0254] 1. Data Collection:

[0255] As test takers study using smartphones or head-mounted displays, data on their learning content and progress is collected.

[0256] The collected data is stored in a cloud database (Firebase).

[0257] 2. Data Analysis:

[0258] The server uses a generative AI model (GPT-4) based on the collected data to analyze the test-takers' weaknesses.

[0259] Generate a personalized curriculum based on weaknesses.

[0260] 3. Curriculum Delivery:

[0261] The server provides the generated curriculum to the test-taker's smartphone or head-mounted display.

[0262] Track learning progress in real time and provide feedback.

[0263] 4. Immersive learning experience:

[0264] The use of head-mounted displays provides test takers with an immersive learning experience.

[0265] This allows the learning effect to be maximized.

[0266] Specific examples

[0267] For example, if a test-taker has a weakness in calculus, the system operates as follows:

[0268] As test takers study using smartphones or head-mounted displays, their progress data is stored in a cloud database.

[0269] The server uses a generative AI model to analyze the data and identify the test-taker's weak points in calculus.

[0270] The server generates and provides to the test-taker a personalized curriculum that focuses on the identified weaknesses.

[0271] Provide real-time feedback and check understanding as you learn.

[0272] The use of head-mounted displays provides an immersive learning experience, maximizing learning effectiveness.

[0273] Prompt Sentence Examples

[0274] Below are some example prompts to input to the generative AI model:

[0275] "Based on the student's learning progress data, please analyze their weak points in calculus and propose the optimal study plan."

[0276] In this way, students can study efficiently and maximize their chances of being accepted into their desired university.

[0277] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0278] Step 1:

[0279] The user begins learning using a smartphone or head-mounted display. As input, the user's learning content and progress data are collected. The device sends this data to a cloud database (Firebase). As output, the learning content and progress data are stored in the cloud database.

[0280] Step 2:

[0281] The server retrieves learning progress data from the cloud database. The learning progress data stored in the cloud database is used as input. The server performs data analysis using a generative AI model (GPT-4) based on this data. The output identifies the test-taker's weaknesses.

[0282] Step 3:

[0283] The server generates an individualized curriculum based on the identified weaknesses. As input, the weakness data identified by the generative AI model is used. The server uses the generative AI model to propose an optimal learning plan. As output, an individualized curriculum is generated.

[0284] Step 4:

[0285] The server sends the generated individual curriculum to the user's smartphone or head-mounted display. The generated individual curriculum is used as input. The device receives this curriculum and displays it to the user. As output, the user can proceed with their studies based on the individual curriculum.

[0286] Step 5:

[0287] As the user progresses, feedback is provided in real time. As input, the user's learning progress data is again collected. The device sends this data to a server, which uses a generative AI model to generate feedback in real time. As output, the user is given an immediate assessment and advice.

[0288] Step 6:

[0289] It uses a head-mounted display to provide users with an immersive learning experience. The generated personalized curriculum and real-time feedback are used as input. The device uses this data to display visually rich learning content to the user. The output is an immersive learning experience for the user.

[0290] Example 3

[0291] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0292] Conventional learning systems have had difficulty providing optimal learning materials and questions tailored to each student's individual learning style and level of understanding. Furthermore, learning methods that rely on past exam questions have had problems keeping up with the latest trends and the needs of test-takers. Furthermore, the lack of an integrated individual curriculum and progress analysis makes it difficult to maximize the effectiveness of learning. There is a need to solve these issues and provide optimal learning methods that will help test-takers pass the entrance exams for their desired schools.

[0293] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0294] In this invention, the server includes means for saving basic information entered by the user in a database, means for collecting data on questions answered and learning materials viewed by the user as they study and transmitting the data to the server in real time, means for evaluating the user's learning style and level of comprehension using a generative AI model based on the collected learning data, means for generating learning materials and questions optimal for the user using the generative AI model based on the evaluation results, means for providing the generated learning materials and questions to the user, and means for reevaluating the user's learning style and level of comprehension based on the user's answers and reflecting this in the next study. This makes it possible to provide the test-taker with an optimal learning method tailored to their individual learning style and level of comprehension, maximizing the effectiveness of their learning.

[0295] "Means for saving basic information entered by the user in a database" refers to a function that saves basic information such as name, age, preferred school, favorite subjects, and least favorite subjects that the user enters when accessing the system for the first time in a database.

[0296] "Means for collecting data on questions answered by users and learning materials viewed as users progress through their studies, and sending the data to a server in real time" refers to a function that collects information on questions answered by users and learning materials viewed while they are studying, and immediately sends the data to a server.

[0297] "Means for assessing a user's learning style and level of comprehension using a generative AI model based on collected learning data" refers to a function that analyzes collected learning data and assesses a user's learning style (e.g., visual, auditory, text-based, etc.) and level of comprehension using a generative AI model.

[0298] "Means for generating optimal teaching materials and questions for a user using a generative AI model based on the evaluation results" refers to a function that automatically generates optimal teaching materials and questions for a user using a generative AI model based on the evaluated learning style and level of comprehension.

[0299] The "means for providing the generated teaching materials and questions to the user" is a function for displaying the generated teaching materials and questions on the user's terminal and providing an interface for progressing with learning.

[0300] "Means of re-evaluating the user's learning style and level of understanding based on the user's answers and reflecting this in the next lesson" is a function that analyzes the user's answers, re-evaluates the user's learning style and level of understanding based on this data, and reflects this in the content of the next lesson.

[0301] The present invention is a system that provides an optimal study method based on the test-taker's learning style and level of understanding. A specific embodiment of this system will be described below.

[0302] System Overview

[0303] This system consists of three main elements: a server, a terminal, and a user. The server plays a central role in collecting, analyzing, and generating data, while the terminal provides an interface for users to advance their learning. Users learn through their terminal and send the results to the server.

[0304] Hardware and software used

[0305] Server: A server with a high-performance database server and the computing resources to run the generative AI model. Specifically, a cloud-based server (e.g., Amazon Web Services, Google Cloud Platform) is used.

[0306] Terminal: A device used by a user, such as a PC, tablet, or smartphone. These terminals are capable of connecting to the Internet and communicate with the server through a browser or dedicated application.

[0307] Generative AI model: For example, OpenAI's GPT-4 is used as a generative AI model. This model is used to evaluate the user's learning style and level of understanding and generate optimal learning materials and questions.

[0308] Program processing

[0309] Server Processing

[0310] The server stores the basic information entered by the user in a database. As the user progresses with their studies, data on the questions they answer and the learning materials they view is collected and sent to the server in real time. A generative AI model is used based on the collected learning data to evaluate the user's learning style and level of understanding. Based on the evaluation results, the generative AI model is used to generate learning materials and questions that are optimal for the user. The generated learning materials and questions are stored on the server and sent to the user's device.

[0311] Terminal handling

[0312] The terminal provides the user with the most suitable learning materials and questions sent from the server. The user browses these learning materials and answers the questions through the terminal. The terminal provides an interface for smooth user operation and sends the answer results to the server.

[0313] User Action

[0314] Users study the learning materials and questions provided through their devices. They select learning materials that suit their learning style and solve the questions. Their answers are sent to the server via their devices and are reflected in their next study session.

[0315] Specific examples

[0316] For example, if test-taker A prefers visual learning, the server uses a generative AI model to generate visual learning materials (materials that make extensive use of charts and illustrations). The device displays these, and User A uses the visual learning materials to study. After studying, the results of User A's answers to the questions are sent to the server and reflected in the next study session.

[0317] Prompt Sentence Examples

[0318] "Test-taker A prefers visual learning. Please generate the best visual materials for him."

[0319] In this way, the system can provide the most suitable learning method to suit the student's learning style and level of understanding, maximizing the effectiveness of the learning. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0320] Step 1:

[0321] User registration and initial settings

[0322] When a user accesses the system for the first time, they enter basic information such as their name, age, preferred school, favorite subjects, and weak subjects. The server stores this basic information in a database. The entered basic information is used to later evaluate the user's learning style and level of understanding.

[0323] Step 2:

[0324] Collecting training data

[0325] As the user progresses with their studies, the device collects data on the questions they have answered and the learning materials they have viewed. This data is sent to the server in real time. The server stores the collected data in a database for later analysis. The input is the user's learning behavior data, and the output is the learning data stored in the database.

[0326] Step 3:

[0327] Learning Style and Comprehension Assessment

[0328] The server uses a generative AI model based on the collected learning data to evaluate the user's learning style and level of comprehension. Specifically, it analyzes what format of learning materials the user prefers (text, diagrams, videos, etc.) and in which areas the user has a deep understanding. The input is the learning data, and the output is the evaluation results of the user's learning style and level of comprehension.

[0329] Step 4:

[0330] Generating optimal teaching materials and questions

[0331] The server uses a generative AI model based on the evaluation results to generate optimal learning materials and questions for each user. For example, for users who prefer visual learning, it generates learning materials that make extensive use of diagrams and illustrations. The input is the evaluation results, and the output is the generated learning materials and questions.

[0332] Step 5:

[0333] Providing study materials and questions

[0334] The terminal provides the user with the most suitable learning materials and questions sent from the server. The user browses these learning materials and answers the questions through the terminal. The input is the generated learning materials and questions, and the output is the learning content provided to the user.

[0335] Step 6:

[0336] Feedback on learning results

[0337] The user studies the provided learning materials and answers the questions. The answers are sent to the server via the terminal. The server then re-evaluates the user's learning style and level of understanding based on these results and reflects them in the next study session. The input is the user's answers, and the output is the updated evaluation results of the learning style and level of understanding.

[0338] (Application example 3)

[0339] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0340] Conventional learning support systems have difficulty providing optimal learning methods tailored to each student's individual learning style and level of understanding. Furthermore, they lack real-time feedback based on learning progress, preventing students from studying efficiently. Furthermore, they lack the ability to customize learning plans using generative AI models, making it impossible to fully meet the needs of test takers.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0342] In this invention, the server includes a means for utilizing past exam question generation AI to provide strategies tailored to the university of interest, a means for automatically generating questions tailored to the trends and level of each university, a means for integrating individual curricula and progress analysis, a means for diagnosing the student's learning style and generating an optimal study plan, a means for customizing the study plan using a generative AI model, and a means for providing real-time feedback according to the student's learning progress. This makes it possible to provide the optimal study method tailored to the individual needs of each student and maximize the effectiveness of their learning.

[0343] "Past exam question generation AI" is an artificial intelligence technology that analyzes past exam questions and automatically generates practice questions tailored to the university you are aiming for.

[0344] "Measures tailored to the university you are aiming for" means providing the most appropriate study content and questions based on the question trends and difficulty level of the university you are applying to.

[0345] "Questions that are in line with the trends and level of each university" are questions created based on the past question trends and difficulty level of each university.

[0346] An "individual curriculum" is a customized study plan based on each student's learning progress and level of understanding.

[0347] "Progress analysis" is a means of assessing a test-taker's learning situation in real time and understanding their progress.

[0348] "Assessing learning style" means assessing whether a candidate has a visual, auditory, or tactile learning style.

[0349] "Generating the optimal study plan" means creating a study plan that is most suitable for each test-taker based on the diagnostic results.

[0350] A "generative AI model" is a model that uses artificial intelligence technology to generate optimal study plans and feedback for test takers.

[0351] "Customized study plans" means using generative AI models to create study plans tailored to each test-taker's individual needs.

[0352] "Providing real-time feedback" means providing instant assessment and advice based on the test-taker's learning progress.

[0353] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The specific functions and processing of each element will be explained below.

[0354] server

[0355] The server runs multiple software modules, including the past exam question generation AI, the generation AI model, and the database. The server has the following functions:

[0356] 1. Past exam question generation AI: Analyzes past exam questions and automatically generates practice questions tailored to the university of their choice. This allows test-takers to solve questions that are in line with the exam trends of their desired university.

[0357] 2. Generative AI model: Generates an optimal study plan based on the results of the student's learning style assessment. The generative AI model uses advanced natural language processing techniques such as OpenAI's GPT-3.

[0358] 3. Database: Stores data such as students' learning progress, diagnostic results, and generated learning plans.

[0359] Terminal

[0360] A device is a device used by a test-taker, such as a smartphone or tablet. A device has the following features:

[0361] 1. Learning Style Assessment: Provides an interface to assess whether a candidate has a visual, auditory, or tactile learning style.

[0362] 2. Displaying the study plan: The generated study plan is displayed to the candidate, providing guidance for progressing through the study.

[0363] 3. Real-time feedback: Feedback provided by the server is displayed in real time according to the learning progress.

[0364] User

[0365] The user is a student taking the exam. The user performs the following actions:

[0366] 1. Complete the Learning Style Assessment: Use your device to complete the Learning Style Assessment.

[0367] 2. Implementing the learning plan: Proceed with your studies according to the generated learning plan.

[0368] 3. Review your feedback: Review the feedback you receive as you progress and adjust your learning methods.

[0369] Specific examples

[0370] For example, for a test-taker with a visual learning style, the following prompts could be fed into the generative AI model:

[0371] Example prompt sentence:

[0372] Create a learning plan for a visual learner preparing for university entrance exams. The plan should include visual aids, diagrams, and interactive exercises.

[0373] By inputting this prompt into a generative AI model, a learning plan optimized for a visual learning style is generated. The generated learning plan is then provided to the test-taker via their device, allowing them to proceed with their studies accordingly.

[0374] As described above, the present invention can provide an optimum study method that meets the individual needs of each examinee, thereby maximizing the learning effect.

[0375] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0376] Step 1:

[0377] The user answers the learning style assessment using the terminal.

[0378] Input: The user answers the learning style assessment questions.

[0379] Data processing: The terminal collects the user's answers and sends them to a database.

[0380] Output: The results of the user's learning style diagnosis are saved in a database.

[0381] Step 2:

[0382] The server analyzes the learning style diagnosis results and identifies the user's learning style.

[0383] Input: User's learning style assessment results stored in the database.

[0384] Data Computation: The server analyzes the diagnostic results and identifies whether the user has a visual, auditory, or tactile learning style.

[0385] Output: The user's learning style is identified.

[0386] Step 3:

[0387] The server uses the generative AI model to generate a learning plan based on the user's learning style.

[0388] Input: User's learning style.

[0389] Data calculation: The server inputs prompt sentences into the generative AI model and generates a learning plan that is optimal for the user's learning style.

[0390] Output: The generated learning plan is saved in a database.

[0391] Step 4:

[0392] The device displays the generated learning plan to the user.

[0393] Input: Learning plans stored in the database.

[0394] Data processing: The device retrieves the study plan and displays it visually to the user.

[0395] Output: User can check the learning plan.

[0396] Step 5:

[0397] The user progresses through the learning process according to the learning plan.

[0398] Input: The generated lesson plan.

[0399] Specific operations: The user studies according to the study plan and enters their progress into the device.

[0400] Output: The user's learning progress data is saved in a database.

[0401] Step 6:

[0402] The server analyzes the user's learning progress and generates feedback in real time.

[0403] Input: User learning progress data stored in a database.

[0404] Data calculation: The server analyzes the learning progress data and generates feedback using a generative AI model.

[0405] Output: The generated feedback is stored in a database.

[0406] Step 7:

[0407] The terminal displays the generated feedback to the user.

[0408] Input: Feedback stored in the database.

[0409] Data processing: The device obtains the feedback and displays it visually to the user.

[0410] Output: User can see the feedback.

[0411] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0412] "Example 1"

[0413] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes a user's emotions and adjusts the learning content and progress speed accordingly. Specifically, if the system recognizes that the user is feeling stressed about learning, it simplifies the learning content and slows down the progress speed to reduce the user's stress. Furthermore, if the system recognizes that the user is highly motivated to learn, it provides more advanced learning content and speeds up the progress speed to maximize the user's learning efficiency.

[0414] "Example 2"

[0415] Another embodiment of the present invention is a system in which an emotion engine recognizes a user's emotions and provides an optimal learning method based on the user's emotions. Specifically, if the system recognizes that the user is excited about learning, it provides a problem-solving learning method. This is because an excited user can understand the learning content more deeply by challenging themselves with new problems. On the other hand, if the system recognizes that the user is relaxed about learning, it provides a reading-based learning method. This is because a relaxed user can absorb a wider range of knowledge by quietly reading texts.

[0416] "Example 3"

[0417] In a further embodiment of the present invention, there is a system in which an emotion engine recognizes a user's emotions and adjusts the learning environment based on the emotions. Specifically, if the system recognizes that the user is feeling impatient about studying, it calms the learning environment by playing quiet music, for example. On the other hand, if the system recognizes that the user is feeling lethargic about studying, it energizes the learning environment by providing bright lighting and lively music, for example. This makes it possible to provide an optimal learning environment according to the user's emotions and maximize learning effectiveness.

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

[0419] "Example 1"

[0420] Step 1: The emotion engine recognizes the user's emotion.

[0421] Step 2: Adjust the learning content and pace based on the emotions recognized by the system.

[0422] Step 3: Prompt the user to proceed with their learning based on the adjusted learning content and progress rate.

[0423] "Example 2"

[0424] Step 1: The emotion engine recognizes the user's emotion.

[0425] Step 2: The system determines the optimal learning method based on the emotions it recognizes.

[0426] Step 3: Based on the determined learning method, the user is instructed to proceed with the learning.

[0427] "Example 3"

[0428] Step 1: The emotion engine recognizes the user's emotion.

[0429] Step 2: Adjust the learning environment based on the emotions recognized by the system.

[0430] Step 3: Prompt the user to proceed with their learning in the tailored learning environment.

[0431] Example 1

[0432] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0433] Conventional exam preparation systems have difficulty automatically generating questions that match the question trends and level of a specific educational institution, and lack the functionality to adjust the learning content and progress speed according to the user's emotions, resulting in poor learning efficiency. Furthermore, they lack the functionality to quickly and accurately grade users' answers and provide the results. A system that can solve these problems and provide efficient and effective exam preparation is needed.

[0434] 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.

[0435] In this invention, the server includes: means for utilizing a past exam question generation AI to provide preparation tailored to the educational institution of interest; means for automatically generating questions tailored to the trends and level of each educational institution; means for integrating individual curricula and progress analysis; means for recognizing a user's emotions and adjusting the learning content and progress rate according to those emotions; means for generating questions using a generative AI model; means for recognizing a user's emotions using an emotion engine; and means for scoring the user's answers and providing the results. This makes it possible to automatically generate questions tailored to a specific educational institution and adjust the learning content and progress rate according to the user's emotions, thereby providing efficient and effective exam preparation.

[0436] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam question data.

[0437] An "educational institution" is an institution that provides a specific education, such as a university or vocational school.

[0438] "Trends" refer to the patterns and characteristics of questions that a particular educational institution has asked in the past.

[0439] "Level" is an indicator of the difficulty and complexity of the question.

[0440] An "individual curriculum" is a learning plan customized to suit each user's learning progress and goals.

[0441] "Progress analysis" is the process of evaluating and analyzing a user's learning progress.

[0442] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions, voice, etc.

[0443] A "generative AI model" is a model that uses artificial intelligence to generate new data and information.

[0444] "Scoring answers" is the process of evaluating and scoring user-submitted answers.

[0445] "Providing the results" means notifying the user of the scoring results and feedback.

[0446] This invention is a system that utilizes AI to generate past exam questions and provides strategies tailored to the educational institution of interest. The system operates in cooperation with the server, the terminal, and the user.

[0447] The server uses a past exam generation AI to collect and analyze past exam data from specific educational institutions. Specifically, it retrieves past exam questions from a database and uses an analytical algorithm to understand question trends and difficulty levels. Next, it uses a generative AI model (such as OpenAI's GPT-4) to generate new questions. This generative AI model automatically generates questions tailored to the trends and level of each educational institution based on the collected and analyzed data.

[0448] The terminal receives requests from the user and sends them to the server. For example, if a user requests questions from a specific educational institution, the terminal sends that information to the server. The server receives the request and returns the generated questions to the terminal. The terminal then displays the received questions to the user.

[0449] The user solves the displayed problem through the terminal. After entering the answer and pressing the send button, the terminal sends the answer data to the server. The server grades the received answer and generates a result. The result data is then sent to the terminal, which displays it to the user.

[0450] Furthermore, the system uses an emotion engine (e.g., Affectiva's SDK) to recognize the user's emotions. If the user feels stressed while learning, the server will simplify the learning content and slow down the progress. Conversely, if the user is highly motivated, the server will provide more advanced learning content and speed up the progress.

[0451] As a concrete example, consider the case of generating long-form English questions for University A. When a user requests a long-form English question from University A, the server uses a generative AI model to generate new questions based on past data on long-form English questions from University A. The generated questions are then displayed on the user's device.

[0452] Example prompt sentence:

[0453] "Please generate long-form English questions for University A. Please create questions that are in line with the university's trends based on past question data."

[0454] In this way, a system is realized in which the server, terminals, and users work together to provide efficient and effective exam preparation.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] The user selects the educational institution they wish to attend.

[0458] The user uses the terminal interface to select the educational institution of interest, for example, University A. The input is the user's selection information, and the output is the ID and name of the selected educational institution.

[0459] Step 2:

[0460] The terminal transmits the selection information to the server.

[0461] The terminal sends information about the educational institution selected by the user to the server. Specifically, it sends data including the ID and name of the selected educational institution. The input is the user's selection information, and the output is the data sent to the server.

[0462] Step 3:

[0463] The server collects and analyzes past exam data from educational institutions.

[0464] The server collects past exam data from the selected educational institution from the database. It then analyzes the collected data to understand the educational institution's question trends and difficulty level. The input is the educational institution's ID and name, and the output is the analysis results.

[0465] Step 4:

[0466] The server generates questions using a generative AI model.

[0467] The server generates new questions using a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results. For example, it generates long-form English questions for University A. The input is the analysis results, and the output is the generated questions.

[0468] Step 5:

[0469] The server sends the generated questions to the device.

[0470] The server sends the generated questions to the terminal. Specifically, it includes data such as the question text and answer options. The input is the generated question, and the output is the data sent to the terminal.

[0471] Step 6:

[0472] The terminal displays the problem to the user.

[0473] The terminal displays the received questions to the user, who can check the questions on the screen. The input is the question data received from the server, and the output is the display to the user.

[0474] Step 7:

[0475] The user solves the problem.

[0476] The user solves the displayed problem, inputs the answer, and presses the send button. The input is the user's answer, and the output is the answer data sent to the terminal.

[0477] Step 8:

[0478] The terminal sends the user's answer to the server.

[0479] The terminal transmits the user's answer to the server. Specifically, the answer data is included. The input is the user's answer data, and the output is the data to be transmitted to the server.

[0480] Step 9:

[0481] The server grades the answers and sends the results to the device.

[0482] The server grades the received answers and generates a result. Then, it sends the result data to the terminal. The input is the user's answer data, and the output is the graded result.

[0483] Step 10:

[0484] The terminal displays the results to the user.

[0485] The terminal displays the received results to the user, who can check their score and correct answer rate. The input is the result data received from the server, and the output is what is displayed to the user.

[0486] Step 11:

[0487] The emotion engine recognizes the user's emotions.

[0488] An emotion engine (e.g., Affectiva's SDK) analyzes the user's facial expressions and voice to recognize emotions. For example, it determines whether the user is feeling stressed. The input is the user's facial expressions and voice data, and the output is the emotion recognition result.

[0489] Step 12:

[0490] The server adjusts the learning content and progress speed according to the emotion.

[0491] The server adjusts the learning content and progress speed based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the difficulty of the questions will be reduced and the progress speed will be slowed down. Conversely, if the user is highly motivated, more difficult questions will be provided and the progress speed will be increased. The input is the emotion recognition results, and the output is the adjusted learning content and progress speed.

[0492] (Application example 1)

[0493] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0494] Conventional exam preparation systems have difficulty providing questions tailored to the trends and levels of each university, and do not adjust the learning content according to the user's emotional state. As a result, test takers often feel stressed and lose motivation. Furthermore, they do not offer a personalized learning experience using devices such as smartphones.

[0495] 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.

[0496] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the university the student is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the user's emotions and adjusting the learning content and progress speed in accordance with those emotions; a means for adjusting the difficulty of the learning content based on the user's emotional state as an application installed on a smartphone; and a means for generating questions based on prompt sentences using a generative AI model. This allows test-takers to study efficiently without feeling stressed and while maintaining motivation.

[0497] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0498] "Measures tailored to the university you are aiming for" means providing study plans and questions that are tailored to the entrance exam trends and level of a specific university.

[0499] "Questions that are in line with the trends and level of each university" are questions created based on the characteristics and difficulty of each university's entrance examination questions.

[0500] An "individual curriculum" is a study plan customized to each test-taker's learning progress and level of understanding.

[0501] A "progress analysis" is an analysis to evaluate a candidate's learning progress and determine the next learning step.

[0502] "Means for recognizing user emotions" refers to technology that identifies a user's emotional state by analyzing the user's facial expressions, tone of voice, etc.

[0503] The "means for adjusting the learning content and progress speed" is a function for changing the learning content and progress speed according to the user's emotional state.

[0504] An "application installed on a smartphone" is a software program that runs on a smartphone.

[0505] The "means for adjusting the difficulty level of the learning content based on the emotional state of the user" is a function for changing the difficulty level of the learning content in consideration of the emotional state of the user.

[0506] A "generative AI model" is an artificial intelligence model that generates new questions or content based on a given prompt.

[0507] A "prompt" is an instruction given to a generative AI model to generate a specific problem or content.

[0508] The system for implementing this invention uses a past exam question generation AI, an emotion recognition engine, a smartphone application, and a generation AI model. The specific configuration and operation of the system are described below.

[0509] System configuration

[0510] 1. AI for generating past exam questions

[0511] This is an artificial intelligence technology that automatically generates new questions based on past exam questions. This technology is used to generate questions that are in line with the trends and level of each university.

[0512] 2. Emotion Recognition Engine

[0513] This technology identifies the user's emotional state by analyzing their facial expressions and tone of voice. The engine uses the smartphone's camera and microphone to recognize the user's emotions in real time.

[0514] 3. Smartphone Applications

[0515] It is a software program that runs on smartphones. The application adjusts the difficulty of learning content based on the user's emotional state and integrates a personalized curriculum and progress analysis.

[0516] 4. Generative AI Models

[0517] This is an artificial intelligence model that generates new questions and content based on a given prompt. This model works in conjunction with the past exam question generation AI.

[0518] System Operation

[0519] 1. User Emotion Recognition

[0520] Using the smartphone's camera and microphone, the emotion recognition engine analyzes the user's emotional state in real time, identifying, for example, when the user is feeling stressed or highly motivated.

[0521] 2. Adjusting learning content

[0522] The smartphone application adjusts the difficulty and pace of the learning content based on the emotional state identified by the emotion recognition engine. For example, it lowers the difficulty of the questions if the user is stressed, and increases the difficulty if the user is highly motivated.

[0523] 3. Problem Generation

[0524] The generative AI model generates new questions based on the prompt. Examples of prompts include "Please generate a long-form English question for University A. The difficulty level is easy" and "Please generate a long-form English question for University A. The difficulty level is difficult."

[0525] 4. Learning Progression

[0526] The smartphone application provides the generated questions to the user, who then solves them. The application records the user's answers and performs progress analysis.

[0527] Specific examples

[0528] For example, if a user is aiming for "University A," and the emotion recognition engine identifies the user's emotional state as "stressed," the smartphone application sends a prompt to the generative AI model: "Please generate long-answer English questions for University A. The difficulty level is easy." The generated questions are then provided to the user. After the user solves the questions, the application records the answers and determines the next learning step.

[0529] In this way, a personalized learning experience can be provided that responds to the user's emotional state.

[0530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0531] Step 1:

[0532] User Emotion Recognition

[0533] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice in real time. An emotion recognition engine does this to identify the user's emotional state (e.g., stress, motivation, etc.). The input is video and audio data from the camera and microphone, and the output is data indicating the user's emotional state.

[0534] Step 2:

[0535] Adjusting learning content

[0536] The server uses an emotion recognition engine to determine the user's emotional state, and the smartphone application adjusts the difficulty and progress of the learning content based on that state. For example, if the user is feeling stressed, the difficulty of the questions is lowered, and if the user is highly motivated, the difficulty is increased. The input is the user's emotional state data, and the output is the adjusted difficulty setting for the learning content.

[0537] Step 3:

[0538] Generate prompt statement

[0539] The server generates a prompt to be sent to the generative AI model based on the adjusted difficulty settings of the learning content. For example, it generates a prompt such as "Please generate a long-answer English question for University A. The difficulty level is easy." The input is the difficulty setting of the learning content, and the output is the prompt to be sent to the generative AI model.

[0540] Step 4:

[0541] Problem Generation

[0542] The server sends a prompt to the generative AI model to generate a new problem. The generative AI model generates a problem based on the prompt and returns it to the server. The input is the prompt, and the output is the generated problem.

[0543] Step 5:

[0544] Providing a problem

[0545] The server provides the generated questions to the user through a smartphone application. The user solves the questions and inputs the answers into the application. The input is the generated questions, and the output is the user's answers.

[0546] Step 6:

[0547] Progress Analysis

[0548] The server records the user's answers and performs a progress analysis. A progress analysis engine performs this and evaluates the user's learning progress. The input is the user's answer data, and the output is the progress analysis results.

[0549] Step 7:

[0550] Determining the next learning step

[0551] The server determines the next learning step based on the progress analysis results. This updates the user's learning plan and determines the next learning content. The input is the progress analysis results, and the output is the setting for the next learning step.

[0552] Example 2

[0553] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0554] Conventional learning support systems have difficulty providing optimal learning methods tailored to each student's individual learning progress and emotional state. Furthermore, there is a lack of systems for centrally managing learning history and progress data to efficiently advance learning. This has led to problems such as students being unable to effectively overcome their weaknesses and not maximizing the effectiveness of their learning.

[0555] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0556] In this invention, the server includes means for acquiring user learning history data, means for generating an individual curriculum using a generative AI model, means for collecting learning progress data, means for generating a progress report, means for acquiring user emotional data, means for determining the emotional state, and means for providing an optimal learning method. This allows the server to provide an optimal learning method according to the user's learning progress and emotional state, thereby enabling efficient learning.

[0557] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0558] "Measures tailored to the university you are aiming for" is a method of providing test takers with study plans and questions that are optimally tailored to the entrance exam trends and level of a specific university.

[0559] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[0560] An "individual curriculum" is a customized study plan based on each candidate's learning progress and weaknesses.

[0561] "Progress analysis" is a data analysis method for evaluating a test-taker's learning situation and visualizing their progress.

[0562] "User learning history data" is data relating to the content and grades that the user has studied in the past.

[0563] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate new information and plans.

[0564] "Study progress data" is data related to the user's current study, including the study time, the number of questions answered, and the percentage of correct answers.

[0565] A "progress report" is a report created based on learning progress data, and visually indicates the user's learning situation.

[0566] "User emotion data" refers to data relating to emotions acquired from the user's facial expressions, voice, and the like.

[0567] "Emotional state" indicates the user's current emotional state, and includes an excited state, a relaxed state, and the like.

[0568] The "optimal learning method" refers to the most effective learning technique depending on the user's learning progress and emotional state.

[0569] This invention is a system for efficiently supporting the learning of test-takers, and integrates the provision of an individual curriculum, progress analysis, and emotion recognition. Specific embodiments of this system will be described below.

[0570] Hardware and software used

[0571] Server: Database management system (e.g., MySQL (registered trademark)), Web server (e.g., Apache (registered trademark))

[0572] Device: PC or smartphone used by the user

[0573] Software: Learning Management Systems (LMS), emotion recognition software (e.g., Affectiva)

[0574] Data processing and calculation

[0575] 1. Obtaining user learning history data

[0576] The server obtains the user's learning history data from the database.

[0577] Specifically, past learning content and grade data are extracted using a query using the user ID as a key.

[0578] Example: "SELECT FROM Learning History WHERE User ID = '12345';"

[0579] 2. Creating an individual curriculum

[0580] The server generates an individual curriculum using a generative AI model (e.g., GPT-4) based on the acquired learning history data.

[0581] Specifically, we analyze the user's weaknesses and create a curriculum that focuses on those areas.

[0582] For example: "If a user has a weakness in calculus, generate a personalized curriculum that focuses on that area."

[0583] 3. Collecting learning progress data

[0584] The device collects real-time progress data as the user progresses through their studies.

[0585] Specifically, data such as study time, number of questions answered, and accuracy rate are collected.

[0586] Example: "User studied for 1 hour and answered 40 out of 50 questions correctly."

[0587] 4. Generate progress reports

[0588] The server analyzes the collected learning progress data and generates a progress report.

[0589] Specifically, learning progress and achievement levels are visualized using graphs and tables.

[0590] For example: "User is 80% complete and 20% away from achieving their goal."

[0591] 5. Acquiring user emotion data

[0592] The device analyzes the user's facial expressions and voice data using emotion recognition software (e.g., Affectiva).

[0593] Specifically, it uses cameras and microphones to collect data in real time and analyzes emotional states.

[0594] Example: "The user is smiling, so they are perceived as excited."

[0595] 6. Judging emotional states

[0596] The server receives the emotion data sent from the terminal and determines the user's emotional state.

[0597] Specifically, based on the analysis results, it is determined whether the user is in an excited state or a relaxed state.

[0598] Example: "The user is determined to be in an excited state."

[0599] 7. Providing optimal learning methods

[0600] The server uses a generative AI model to provide the optimal learning method based on the emotional state.

[0601] Specifically, a problem-solving learning method is provided when the student is excited, and a reading-based learning method is provided when the student is relaxed.

[0602] For example: "If the user is in an excited state, provide them with a problem-based learning method."

[0603] In this way, the system provides an efficient learning environment by linking the server, terminals, and users.

[0604] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0605] Step 1:

[0606] Obtaining user learning history data

[0607] Input: User ID

[0608] Specific operation: The server retrieves the user's learning history data from the database. Specifically, it uses the user ID as a key to query past learning content and grade data.

[0609] Data processing: Execute a database query to obtain the relevant learning history data.

[0610] Output: Learning history data (e.g., "SELECT FROM Learning History WHERE User ID = '12345';")

[0611] Step 2:

[0612] Creating an individual curriculum

[0613] Input: Learning history data

[0614] Specific operation: The server generates an individual curriculum using a generative AI model (e.g., GPT-4) based on the acquired learning history data. Specifically, it analyzes the user's weaknesses and creates a curriculum that focuses on those areas.

[0615] Data processing: Analyze learning history data to identify user weaknesses. Input prompts into the generative AI model to generate a curriculum.

[0616] Output: Personalized curriculum (e.g., "If the user has a weakness in calculus, generate a personalized curriculum that focuses on that area.")

[0617] Step 3:

[0618] Collecting learning progress data

[0619] Input: User's learning activity data (study time, number of questions answered, correct answer rate, etc.)

[0620] What it does: The device collects real-time progress data as the user learns.

[0621] Data processing: Collect learning activity data and send it to the server.

[0622] Output: Learning progress data (e.g., "User studied for 1 hour and answered 40 out of 50 questions correctly.")

[0623] Step 4:

[0624] Generate progress reports

[0625] Input: Learning progress data

[0626] Specific operation: The server analyzes the collected learning progress data and generates a progress report, specifically visualizing the learning progress and achievement level in graphs and tables.

[0627] Data processing: Analyze learning progress data and generate data for visualization.

[0628] Output: Progress report (e.g. "User is 80% done and 20% away from achieving goal.")

[0629] Step 5:

[0630] Obtaining user emotion data

[0631] Input: User facial and voice data

[0632] How it works: The device analyzes the user's facial expressions and voice data using emotion recognition software (e.g., Affectiva). Specifically, it uses a camera and microphone to collect data in real time and analyzes the user's emotional state.

[0633] Data processing: Analyze facial expressions and voice data to identify emotional states.

[0634] Output: Emotion data (e.g., "The user is smiling, so they are recognized as excited.")

[0635] Step 6:

[0636] Judging emotional states

[0637] Input: Emotion data

[0638] Specific operation: The server receives the emotion data sent from the device and judges the user's emotional state. Specifically, based on the analysis results, it determines whether the user is excited or relaxed.

[0639] Data processing: Analyze emotional data and determine emotional states.

[0640] Output: Emotional state (e.g., "The user is judged to be in an excited state.")

[0641] Step 7:

[0642] Providing optimal learning methods

[0643] Input: Emotional state

[0644] Specific operation: The server uses a generative AI model to provide the optimal learning method according to the emotional state. Specifically, it provides a problem-solving learning method when the user is excited, and a reading-based learning method when the user is relaxed.

[0645] Data processing: Based on the emotional state, prompt sentences are input into the generative AI model to generate the optimal learning method.

[0646] Output: Optimal learning method (e.g., "If the user is excited, provide a problem-solving learning method.")

[0647] (Application example 2)

[0648] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0649] Conventional learning management systems have difficulty providing optimal learning methods that take into account each student's individual learning progress and emotional state. Furthermore, they lack systems that maximize learning efficiency and increase the chances of passing the university of their choice. This has led to problems such as students being unable to study efficiently and not fully realizing the benefits of their studies.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0651] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the university the examinee is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the user's emotional state and providing an optimal study method based thereon; and a means for analyzing the user's study progress data and generating an individual curriculum focusing on weak areas. This makes it possible to provide the examinee with an optimal study method based on their study progress and emotional state, maximizing their study efficiency.

[0652] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0653] "Measures tailored to the university you are aiming for" is a method of providing optimal study plans and questions based on the entrance exam trends and level of the university you are aiming for.

[0654] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[0655] An "individual curriculum" is a customized study plan based on each candidate's learning progress and weaknesses.

[0656] "Progress analysis" is a method of evaluating a test-taker's learning progress and analyzing how far they have progressed.

[0657] "Recognizing the user's emotional state" refers to a technology that determines the user's current emotions from their facial expressions and behavior.

[0658] The "optimal learning method" is the learning technique that is most suitable for maximizing the user's learning efficiency.

[0659] "Study progress data" is data that indicates how far a test-taker has progressed in their studies.

[0660] "Weak areas" are areas of study or subjects in which a candidate is particularly weak.

[0661] "Generating an individual curriculum" refers to creating an optimal study plan based on the student's learning progress and weaknesses.

[0662] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a means for utilizing past exam question generation AI to provide strategies tailored to the university the user is aiming for, a means for automatically generating questions tailored to the trends and level of each university, a means for integrating individualized curricula and progress analysis, a means for recognizing the user's emotional state and providing the optimal learning method based on that, and a means for analyzing the user's learning progress data and generating an individualized curriculum that focuses on weak areas.

[0663] Hardware and Software Configuration

[0664] 1. Hardware:

[0665] Server: A server with high-performance computing power is required.

[0666] Device: The device used by the user, such as a smartphone or head-mounted display.

[0667] Camera: The device is equipped with a camera to recognize the user's emotional state.

[0668] 2. Software:

[0669] Past exam question generation AI: An artificial intelligence model for generating new questions based on past exam questions.

[0670] Emotion recognition software: Software that recognizes emotions from a user's facial expressions and behavior.

[0671] Curriculum generation software: Software for generating individualized curricula based on the user's learning progress data and emotional state.

[0672] Data analysis tools: Tools for analyzing learning progress data (e.g., scikit-learn).

[0673] Processing flow

[0674] 1. Learning progress analysis:

[0675] The server collects the user's learning progress data and evaluates the progress using a data analysis tool. Specifically, it builds a linear regression model based on the time spent studying and the score, and predicts the user's learning progress.

[0676] 2. Emotion Recognition:

[0677] The device's built-in camera captures the user's facial expressions, which are then analyzed using emotion recognition software to determine whether the user is excited or relaxed.

[0678] 3. Creating a personalized curriculum:

[0679] The server uses curriculum generation software to create an optimal learning plan based on the user's learning progress data and emotional state. For example, if a user has weaknesses in a particular area of ​​math, it will provide a set of problems that focus on that area.

[0680] 4. Provision of learning materials:

[0681] The server then distributes the most suitable learning materials to the user's terminal based on the generated individual curriculum, allowing the user to study efficiently.

[0682] Specific examples

[0683] For example, if a user has a weakness in a particular area of ​​mathematics, the server can generate a set of problems that focus on that area and provide it to the user.Also, if the server recognizes that the user is excited, it can provide a problem-solving learning method that challenges the user with new problems.

[0684] Prompt Sentence Examples

[0685] Develop an application that analyzes a user's learning progress data and provides optimal learning methods based on their emotional state. Recognize emotions from the user's image and generate a personalized curriculum that focuses on weak areas. The data used includes time spent studying, scores, user image, and weak areas.

[0686] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0687] Step 1:

[0688] The server collects the user's learning progress data. As input, it receives data on the time spent by the user on learning and the score. Based on this data, it uses a data analysis tool (e.g., scikit-learn) to evaluate the progress. Specifically, it builds a linear regression model to predict the user's learning progress. As output, it obtains the evaluation results of the user's learning progress.

[0689] Step 2:

[0690] The device captures the user's facial expression with a camera. The user's facial image is acquired as input. Emotion recognition software is used to analyze the user's emotions from their facial expression. Specifically, image processing technology is used to extract facial features and determine the user's emotional state. The output is the user's emotional state (excited or relaxed).

[0691] Step 3:

[0692] The server generates an individualized curriculum based on the user's learning progress data and emotional state. It receives the learning progress assessment results and emotional state as input. It uses the curriculum generation software to create an optimal learning plan that focuses on the user's weak areas. Specifically, it selects questions related to the user's weak areas and incorporates them into the learning plan. It obtains the individualized curriculum as output.

[0693] Step 4:

[0694] The server delivers the most suitable learning materials to the user's device based on the generated individual curriculum. The server receives the individual curriculum as input. It selects learning materials and sends them to the device. Specifically, it selects problem sets and reference materials included in the curriculum and delivers them to the user's device. The learning materials are provided to the user's device as output.

[0695] Step 5:

[0696] The user progresses with their studies using the learning materials delivered to their device. As input, they receive the learning materials displayed on their device. They study and record progress data, specifically by solving problems and reading reference materials. As output, new learning progress data is generated.

[0697] Step 6:

[0698] The server collects new learning progress data for the user again and repeats the process from step 1. It receives the new learning progress data as input. It analyzes the data again and evaluates the learning progress. Specifically, it compares the previous progress data with the new data and evaluates the learning effectiveness. It obtains an updated learning progress evaluation result as output.

[0699] Example 3

[0700] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0701] Conventional learning systems have difficulty providing an optimal learning environment that matches each student's individual learning style and emotional state. Furthermore, they are unable to accurately meet the needs of students when generating past exam questions or providing individualized curricula, making it difficult to maximize learning effectiveness. Furthermore, there is a lack of means to analyze learning progress in real time and provide appropriate feedback.

[0702] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0703] In this invention, the server includes a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution the student is aiming for, a means for automatically generating questions tailored to the trends and level of each educational institution, a means for integrating individual curricula and progress analysis, a means for diagnosing the user's learning style, a means for providing optimal learning materials based on the diagnosis results, and a means for recognizing the user's emotions and adjusting the learning environment. This makes it possible to provide the optimal learning method and environment according to the individual needs of each student, maximizing the learning effect.

[0704] "Past exam question generation AI" is an artificial intelligence technology that analyzes past exam questions and automatically generates practice questions tailored to the educational institution you are aiming for.

[0705] "Educational institutions" are institutions that provide higher education, such as universities and vocational schools.

[0706] An "individual curriculum" is a study plan customized to each student's learning style and progress.

[0707] "Progress analysis" is the process of assessing a student's learning progress in real time and providing appropriate feedback.

[0708] A "learning style assessment" is a diagnostic tool used to evaluate a test-taker's learning methods and level of understanding and identify the most suitable learning style.

[0709] "Optimal teaching materials" are study materials and problem sets that are best suited to the test-taker's learning style and level of understanding.

[0710] "Emotion recognition" is a technology that analyzes data such as a test-taker's facial expressions and voice to identify their current emotional state.

[0711] "Adjusting the learning environment" is the process of optimizing the learning environment, such as music and lighting, according to the test-taker's emotional state.

[0712] MODE FOR CARRYING OUT THE INVENTION

[0713] This invention is a system for maximizing the learning effect of test-takers, and includes AI for generating past exam questions, diagnosing learning styles, recognizing emotions, and adjusting the learning environment. Specific embodiments of this system are described below.

[0714] Hardware and software used

[0715] Hardware: Servers, devices (PCs, tablets, smartphones)

[0716] Software: Generative AI models (e.g., GPT-4), emotion recognition engines (e.g., Affectiva), learning management systems (LMS)

[0717] System Overview

[0718] This system provides optimal learning methods and environments according to the student's learning style and emotional state. Specifically, it has the following functions:

[0719] 1. Past exam question generation AI: The server analyzes past exam questions and automatically generates practice questions tailored to the educational institution the student is aiming for.

[0720] 2. Learning style diagnosis: The user takes a learning style diagnosis test using their device, and the server analyzes the diagnosis results using the generated AI model.

[0721] 3. Providing optimal learning materials: The server selects the optimal learning materials based on the diagnostic results and delivers them to the device.

[0722] 4. Emotion recognition: The device uses a camera and microphone to collect the user's facial expressions and voice, and the server analyzes them using an emotion recognition engine.

[0723] 5. Adjusting the learning environment: The server generates instructions to adjust the learning environment based on the user's emotional state, and the device adjusts the environment according to those instructions.

[0724] Specific examples

[0725] For visual learners:

[0726] The user takes a learning style diagnostic test on the device and is diagnosed as a "visual learner."

[0727] The server selects educational materials for visual learners (e.g., infographics, videos) and delivers them to the device.

[0728] If a user feels impatient while studying, the device will capture their facial expression with a camera, and the server will use an emotion recognition engine to analyze the "impatience."

[0729] The server sends an instruction to the terminal to "play quiet music," and the terminal plays quiet classical music.

[0730] If you're lethargic:

[0731] If the user is recognized as being lethargic, the device will capture their facial expression with a camera, and the server will analyze the "lethargy" using an emotion recognition engine.

[0732] The server sends an instruction to the terminal to "provide bright lights and uplifting music," and the terminal brightens the lights and plays uplifting music.

[0733] Prompt Sentence Examples

[0734] "Provide materials that are best suited to students with visual learning styles."

[0735] "Please suggest a suitable learning environment for users who are feeling impatient."

[0736] "How can we invigorate learning environments for disengaged users?"

[0737] The above is an embodiment of the present invention. This system provides optimal learning methods and environments tailored to the individual needs of test-takers, maximizing learning effectiveness. The flow of the specific processing in the third embodiment will be explained with reference to FIG. 21.

[0738] Program processing flow

[0739] Step 1: Assess your user's learning style

[0740] Input: The user starts the learning style assessment test on their device.

[0741] How it works: A user clicks a button on their device to start a "Learning Styles Test." The device then presents the user with a series of questions, and the user enters their answers.

[0742] Data processing: The device collects the user's answers and sends them to the server, which then analyzes the answers using a generative AI model to diagnose the user's learning style.

[0743] Output: The server sends the diagnostic results to the device and displays something like "You are a visual learner" to the user.

[0744] Step 2: Deliver learning content

[0745] Input: The server receives the user's learning style assessment results.

[0746] How it works: The server selects educational materials for visual learners (e.g., infographics, videos). The server then sends the selected educational materials to the device.

[0747] Data processing: The server selects the most suitable learning materials based on the learning style and delivers them to the device.

[0748] Output: The device displays the learning material to the user, and the user begins learning.

[0749] Step 3: Recognizing user emotions

[0750] Input: The device uses the camera and microphone to collect the user's facial expressions and voice.

[0751] How it works: The device uses a camera to capture the user's facial expressions and a microphone to record their voice. The device then sends the collected data to a server.

[0752] Data processing: The server analyzes the user's emotions using an emotion recognition engine.

[0753] Output: The server sends the analysis results to the terminal and displays a message such as "You are feeling impatient" to the user.

[0754] Step 4: Adjust your learning environment

[0755] Input: The server receives the user's emotional state.

[0756] Operation: The server generates an instruction to "play quiet music for users who are feeling impatient." The server sends the instruction to the terminal.

[0757] Data processing: The server generates instructions to adjust the learning environment based on the user's emotional state.

[0758] Output: The device plays quiet classical music to create a calming learning environment for the user.

[0759] The above is a concrete explanation of the program processing of this system.

[0760] (Application example 3)

[0761] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0762] Conventional learning systems do not fully consider the individual needs and emotional states of test takers, which means that learning effectiveness is not maximized. Furthermore, in factories, there is a lack of means to recognize the emotions and states of workers in real time and optimize the work environment based on that, which leads to issues such as reduced work efficiency and safety. To solve these issues, a system is needed that recognizes the emotions and states of test takers and workers in real time and provides an optimal environment based on that information.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0764] In this invention, the server includes: a means for utilizing a past exam question generation AI to provide preparation tailored to the university the candidate is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the emotions and state of workers in real time and optimizing the work environment based on the emotions; a means for analyzing emotions from the worker's facial expressions and tone of voice using an emotion recognition engine; a means for adjusting the work environment based on the emotion data using a data processing algorithm; and a means for adjusting lighting and music using a control system. This makes it possible to maximize the learning effect of test takers and improve the work efficiency and safety of workers.

[0765] "Past exam question generation AI" is an artificial intelligence that automatically generates practice questions tailored to the university you are aiming for based on past exam questions.

[0766] "Means for providing measures" are methods or devices for providing students with study plans and study materials tailored to the university they are aiming for.

[0767] "Means for automatically generating questions" refers to a method or device for automatically creating questions that are in line with the trends and level of each university.

[0768] "Means for integrating individualized curriculum and progress analysis" refers to methods and devices for analyzing a candidate's learning progress and creating and integrating an individualized learning plan based on that analysis.

[0769] "Means for recognizing a worker's emotions and state in real time and optimizing the work environment based on that" refers to a method or device for detecting a worker's emotions and physical state in real time and adjusting the work environment accordingly.

[0770] An "emotion recognition engine" is software or hardware that analyzes emotions from a worker's facial expressions and tone of voice.

[0771] The "data processing algorithm" is a computational method for generating instructions to optimize the work environment based on data obtained from the emotion recognition engine.

[0772] A "control system" is the hardware and software that controls the lighting and music.

[0773] The embodiments of the present invention will be described in detail below.

[0774] System Overview

[0775] The system is designed to maximize the learning effect of test takers and improve the work efficiency and safety of factory workers. It consists of multiple components, including a past exam question generation AI, an emotion recognition engine, a data processing algorithm, and a control system.

[0776] Hardware and software used

[0777] Camera: Captures the worker's facial expressions in real time.

[0778] Microphone: Analyzes the tone and volume of a worker's voice.

[0779] Speaker: Outputs music and voice instructions.

[0780] Lighting system: Adjust the brightness and color of the lights.

[0781] Emotion recognition engine: Analyzes emotions from the worker's facial expressions and tone of voice. Specifically, it uses a general emotion recognition API.

[0782] Data processing algorithm: Generates instructions to optimize the work environment based on data obtained from the emotion recognition engine.

[0783] Control system: A control program for adjusting lighting and music. Uses a microcontroller such as Arduino or Raspberry Pi.

[0784] Program processing explanation

[0785] 1. Cameras and microphones capture workers' facial expressions and voices:

[0786] A camera captures the worker's face in real time, and a microphone collects their voice.

[0787] 2. Emotion recognition engine analyzes the data:

[0788] An emotion recognition engine is used to recognize emotions from the worker's facial expressions.

[0789] Analyze emotions from tone of voice.

[0790] 3. Data processing algorithms generate the optimal environment:

[0791] Based on data obtained from the emotion recognition engine, it is determined whether the worker is feeling fatigued or stressed.

[0792] Choose some relaxing music and play it through the speakers.

[0793] Adjust your lighting system to a warmer tone.

[0794] 4. The control system regulates the environment:

[0795] Use Arduino or Raspberry Pi to control lighting color and music playback.

[0796] Specific examples

[0797] Example prompts to input to the generative AI model

[0798] Analyze workers' facial expressions and tone of voice, and if they appear tired or stressed, play relaxing music and adjust the lighting to warmer colors.

[0799] In this way, the system can maximize the learning effect of test takers and improve the work efficiency and safety of factory workers.

[0800] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0801] Step 1:

[0802] The server uses a camera and microphone to capture the worker's facial expressions and voice in real time. The input is the worker's facial video and voice audio data, and the output is to send this data to an emotion recognition engine. Specifically, the camera captures the worker's face and the microphone collects their voice.

[0803] Step 2:

[0804] The server uses an emotion recognition engine to analyze the captured facial and voice data. The input is the video and audio data obtained in step 1, and the output is the worker's emotional state (e.g., fatigue, stress, relaxation). Specifically, the emotion recognition engine analyzes facial expressions from the video data and tone of voice from the audio data.

[0805] Step 3:

[0806] The server uses a data processing algorithm to generate instructions for optimizing the work environment based on the emotional state data obtained from the emotion recognition engine. The input is the emotional state data obtained in step 2, and the output is the optimal work environment settings (e.g., music selection, lighting adjustment). Specifically, the data processing algorithm calculates the optimal environment settings according to the emotional state.

[0807] Step 4:

[0808] The server uses a control system to adjust the work environment based on the generated instructions. The input is the environmental setting data obtained in step 3, and the output is the actual change to the work environment (e.g., playing music, adjusting the color and brightness of the lighting). Specific actions include the control system playing relaxing music from the speakers and adjusting the lighting system to a warmer color.

[0809] Step 5:

[0810] The server again captures the state of the work environment after the change using a camera and microphone and sends it to the emotion recognition engine. The input is the video of the worker's face after the change and audio data of his / her voice, and the output is data for analyzing the emotional state again. Specifically, the camera and microphone capture the worker's state again and send it to the emotion recognition engine.

[0811] Step 6:

[0812] The server again uses the emotion recognition engine to analyze the impact of the changed work environment on the worker's emotional state. The input is the video and audio data obtained in step 5, and the output is the changed emotional state data. Specifically, the emotion recognition engine again analyzes facial expressions from the video data and tone of voice from the audio data.

[0813] Step 7:

[0814] The server adjusts the work environment again as necessary based on the changed emotional state data. The input is the emotional state data obtained in step 6, and the output is the optimal work environment settings again. Specifically, the data processing algorithm calculates the optimal environment settings again according to the emotional state, and the control system makes the necessary adjustments.

[0815] 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.

[0816] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0818] 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.

[0819] [Second embodiment]

[0820] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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).

[0826] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0832] "Example 1"

[0833] The present invention is an exam preparation system that utilizes AI to generate past exam questions. This system provides preparation tailored to the university of your choice. Specifically, it is equipped with AI that automatically generates questions tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, this system will automatically generate long-form English questions tailored to University A.

[0834] "Example 2"

[0835] Furthermore, this embodiment of the present invention has the function of integrating individualized curriculum and progress analysis. This allows students to manage their learning progress in a centralized manner, providing them with a chance to pass the entrance exam for their desired university with minimal study. For example, if a student has weaknesses in a particular area of ​​mathematics, this system can provide an individualized curriculum that focuses on that area.

[0836] "Example 3"

[0837] Furthermore, this embodiment of the present invention has the function of accurately grasping the needs of test takers and maximizing the effectiveness of learning by utilizing innovative technology. This allows test takers to be provided with the optimal learning method that suits their learning style and level of understanding, helping them realize their dream of passing the school of their choice. For example, if a test taker is good at visual learning, this system will provide visual learning materials and questions.

[0838] The processing flow of each embodiment will be described below.

[0839] "Example 1"

[0840] Step 1: The student enters the university they are aiming for into the system.

[0841] Step 2: The system uses AI to generate past exam questions and automatically generate questions that are tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, the system will automatically generate long-form English questions for University A.

[0842] Step 3: The generated questions are provided to test takers and used for study.

[0843] "Example 2"

[0844] Step 1: Candidates enter their learning progress into the system.

[0845] Step 2: The system generates a personalized curriculum based on the learning progress entered. For example, if a student has weaknesses in a particular area of ​​mathematics, the system will provide a personalized curriculum focused on that area.

[0846] Step 3: The generated individual curriculum is provided to the student and used for study.

[0847] "Example 3"

[0848] Step 1: The candidate enters their learning style and level of understanding into the system.

[0849] Step 2: The system will provide the most suitable learning method based on the input information. For example, if the test-taker is a visual learner, the system will provide visual learning materials and questions.

[0850] Step 3: The provided learning methods are provided to the candidate and used for studying.

[0851] Example 1

[0852] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0853] With conventional test preparation systems, it was difficult to efficiently generate questions that matched the trends of specific educational institutions, making it difficult to tailor preparation to suit the educational institution that test takers were aiming for. Furthermore, they lacked functionality to integrate individualized curricula and progress analysis, making it impossible to maximize test takers' learning effectiveness. Furthermore, there was a need for a method that would not be limited by data from the past few years and would provide test takers with a chance of passing their desired educational institution with minimal study.

[0854] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for the user to select an educational institution to which the user aspires, a means for the server to acquire trend data for the selected educational institution, a means for the server to input a prompt sentence to the generative AI model based on the trend data acquired by the server, a means for the generative AI model to generate questions based on the prompt sentence, a means for the server to provide the generated questions to the user, and a means for integrating an individual curriculum and progress analysis. This enables the user to efficiently study preparation questions tailored to the educational institution to which the user aspires.

[0855] "User" refers to an individual who uses the system to study practice questions tailored to the educational institution they are aiming for.

[0856] "Server" refers to a computer system that processes data in response to user requests, generates questions using a generative AI model, and provides them to users.

[0857] "Educational Institution" refers to a particular school, university, or other learning institution that a user is pursuing.

[0858] "Trend data" refers to information about past entrance examination questions and question trends of a particular educational institution.

[0859] A "generative AI model" refers to an artificial intelligence model that automatically generates questions tailored to a specific educational institution based on a prompt.

[0860] A "prompt" refers to text that provides specific instructions for generating questions to a generative AI model.

[0861] "Individualized curriculum" refers to a customized learning plan based on a user's learning progress and goals.

[0862] "Progress analysis" refers to the process of evaluating a user's learning status and analyzing the effectiveness and progress of their learning.

[0863] "Problem" refers to a learning task that the user must solve, generated by a generative AI model.

[0864] This invention is an exam preparation system that utilizes past exam question generation AI, and aims to enable users to efficiently study exam questions tailored to the educational institution they are aiming for. This system involves a series of processes in which the user selects the educational institution they are aiming for, a server obtains trend data for the selected educational institution, inputs prompts into a generative AI model to generate questions, and provides the generated questions to the user.

[0865] Hardware and software used

[0866] Server: Database Management System (DBMS), generative AI model, HTTP server

[0867] Device: Web browser or dedicated application

[0868] User: The device used to access the system (PC, tablet, smartphone, etc.)

[0869] Data processing and calculation

[0870] 1. The user selects the educational institution they wish to attend

[0871] A user logs in to the system and selects the educational institution they are interested in. For example, to select "University A," the user selects "University A" from the drop-down menu and clicks the "Select" button.

[0872] 2. The server retrieves the institution's trend data.

[0873] The server retrieves data about past entrance exam questions and question trends for the educational institution selected by the user from the database. For example, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'University A'" to extract the required data.

[0874] 3. The server inputs a prompt to the generative AI model.

[0875] The server inputs a prompt to the generative AI model based on the acquired trend data. The prompt is text that gives the generative AI model specific instructions for generating questions. For example, the server generates a prompt such as "Please generate a long-answer English question for University A."

[0876] 4. Generative AI models generate problems

[0877] Based on the prompt, the generative AI model generates questions that are in line with the trends of each educational institution. The generative AI model uses natural language processing technology to analyze the prompt and generate appropriate questions. For example, it generates long-form English questions for University A.

[0878] 5. The server provides the generated questions to the user.

[0879] The server sends the generated questions to the user's device so that the user can solve them. The server also sends the generated questions to the user's device as an HTTP response, which is then displayed in the user's browser or application. For example, a long-form English question for University A is displayed on the user's device.

[0880] Examples of concrete examples and prompts

[0881] Specific examples

[0882] If the user selects "University B," the server retrieves past math problem data from University B and inputs the prompt "Please generate math problems for University B" into the generative AI model. The generative AI model generates math problems for University B, and the server provides them to the user.

[0883] Prompt Sentence Examples

[0884] "Generate long-form English questions for University A."

[0885] "Generate math problems for University B"

[0886] "Generate physics problems from University C"

[0887] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[0888] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0889] Step 1:

[0890] Users select the educational institution they wish to pursue

[0891] A user logs into the system and selects the educational institution of interest. Specifically, the user selects the educational institution using a drop-down menu or search function and clicks the "Select" button. The input is the name of the educational institution selected by the user, and the output is the name of the selected educational institution being sent to the server.

[0892] Step 2:

[0893] The server retrieves the institution's trend data.

[0894] The server retrieves data on past entrance exam questions and question trends for the educational institution selected by the user from the database. Specifically, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'selected educational institution'" to extract the required data. The input is the name of the selected educational institution, and the output is the trend data for that educational institution.

[0895] Step 3:

[0896] The server inputs a prompt to the generative AI model.

[0897] The server inputs a prompt to the generative AI model based on the acquired trend data. Specifically, the server generates a prompt such as "Please generate questions for a specific subject at the selected educational institution" and sends an HTTP POST request to the API endpoint of the generative AI model. The input is the trend data and the prompt, and the output is the prompt sent to the generative AI model.

[0898] Step 4:

[0899] Generative AI models generate problems

[0900] The generative AI model generates questions based on the prompt sentence, tailored to the trends of each educational institution. Specifically, the generative AI model analyzes the prompt sentence using natural language processing technology and generates appropriate questions. The input is the prompt sentence, and the output is the generated question.

[0901] Step 5:

[0902] The server provides the generated questions to the user.

[0903] The server sends the generated problem to the user's device so that the user can solve it. Specifically, the server sends the generated problem to the user's device as an HTTP response and displays it in the user's browser or application. The input is the generated problem, and the output is the problem displayed on the user's device.

[0904] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[0905] (Application example 1)

[0906] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0907] Conventional exam preparation systems have difficulty efficiently generating questions that are in line with the question trends of specific educational institutions, and are unable to integrate curriculum and progress analysis tailored to the individual needs of test takers. Furthermore, there is a lack of systems that can be easily used on mobile devices such as smartphones, making it difficult for test takers to study efficiently. This has made it difficult to maximize the effectiveness of test takers' learning in order to pass the entrance exams for their desired schools.

[0908] 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.

[0909] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest; a means for automatically generating questions tailored to the trends and level of each educational institution; a means for integrating individual curricula and progress analysis; a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user; and a means for displaying the generated questions on a smartphone. This enables test-takers to efficiently study questions tailored to the question trends of specific educational institutions, maximize their learning effectiveness through curricula and progress analysis tailored to their individual needs, and easily advance their studies to pass their desired schools.

[0910] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[0911] "Target educational institution" refers to the specific school or university that the candidate is aiming to get into.

[0912] "Means of providing countermeasures" refers to methods of providing study methods and materials that will help students pass the entrance exams for the educational institutions they are aiming for.

[0913] "Trends and levels at each educational institution" refers to the characteristics and difficulty of the questions asked by each educational institution.

[0914] "Means for automatically generating questions" refers to a method for automatically creating test questions based on specific conditions using artificial intelligence.

[0915] "Individual curriculum" refers to a study plan tailored to each student's learning progress and goals.

[0916] "Progress analysis" is a method of assessing and analyzing a student's learning progress.

[0917] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[0918] "User-selected educational institutions and subjects" refers to the specific school or university that the candidate has chosen to study at, and the specific subjects that will be tested at that school or university.

[0919] "Means for displaying on a smartphone" refers to a method for displaying the generated test questions and learning content on a smartphone screen.

[0920] A system for implementing this invention includes a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest, a means for automatically generating questions that are in line with the trends and level of each educational institution, a means for integrating individual curriculums and progress analysis, a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user, and a means for displaying the generated questions on a smartphone.

[0921] Program processing explanation

[0922] Hardware used:

[0923] Smartphone

[0924] Software used:

[0925] OpenAI API

[0926] Python

[0927] Data processing and calculation:

[0928] 1. User input: Users input the educational institution and subject they wish to study through a smartphone application.

[0929] 2. Prompt generation: The server generates a prompt based on the information entered by the user. For example, it generates a prompt such as "Please generate a long-answer English question for University A."

[0930] 3. Request to AI model: Send the generated prompt sentence to the OpenAI API and have the generative AI model (GPT-3) generate a problem.

[0931] 4. Problem retrieval: The server receives the problem returned by the generative AI model and formats it appropriately.

[0932] 5. Display on smartphone: The formatted questions are displayed on a smartphone application.

[0933] Specific examples

[0934] For example, if a user selects "Long-form English questions from University A," the following prompt sentence will be sent to the generative AI model.

[0935] Example prompt sentence:

[0936] Please generate long-form English questions for University A.

[0937] Based on this prompt, the generative AI model generates a long-form English question that matches the question trends of University A and returns it to the server. The server receives the question and displays it on the smartphone application.

[0938] In this way, users can efficiently study questions that match the exam trends of the educational institution they are aiming for through their smartphones. This allows students to maximize their learning effectiveness through a curriculum tailored to their individual needs and progress analysis, making it easy to study for admission to their desired school.

[0939] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0940] Step 1:

[0941] Users launch the smartphone application and enter the educational institution and subject they wish to attend.

[0942] Input: Name of educational institution, subject name

[0943] Output: User input data (educational institution name, subject name)

[0944] Specific operation: The user enters the name of the educational institution and the name of the subject in the application's input form and presses the submit button.

[0945] Step 2:

[0946] The terminal transmits the user input data to the server.

[0947] Input: User-entered data (educational institution name, subject name)

[0948] Output: User-entered data sent to the server

[0949] Specific operation: The smartphone sends user input data to a server via the Internet.

[0950] Step 3:

[0951] The server generates a prompt sentence based on the received user input data.

[0952] Input: User-entered data (educational institution name, subject name)

[0953] Output: Generated prompt statement

[0954] Specific operation: The server generates a prompt such as "Please generate a long-answer English question for University A."

[0955] Step 4:

[0956] The server sends the generated prompt text to the OpenAI API and requests the generative AI model to generate a question.

[0957] Input: Generated prompt text

[0958] Output: The problem data returned by the generative AI model

[0959] Specific operation: The server sends a prompt to the OpenAI API, and the generative AI model (GPT-3) generates and returns a problem.

[0960] Step 5:

[0961] The server receives the problem data returned by the generative AI model and formats it appropriately.

[0962] Input: Problem data returned by the generative AI model

[0963] Output: Formatted problem data

[0964] Specific operation: The server analyzes the problem data received and converts it into a format that can be displayed on a smartphone.

[0965] Step 6:

[0966] The server sends the formatted question data to the terminal.

[0967] Input: Formatted question data

[0968] Output: Problem data sent to the terminal

[0969] Specific operation: The server sends the formatted problem data to the smartphone via the Internet.

[0970] Step 7:

[0971] The terminal displays the received question data to the user.

[0972] Input: Problem data sent to the terminal

[0973] Output: Problem data displayed on a smartphone screen

[0974] Specific operation: The smartphone displays the received problem data on the screen, allowing the user to solve the problem.

[0975] Example 2

[0976] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0977] With conventional learning support systems, it was difficult to accurately grasp each student's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, feedback on learning progress and curriculum updates were often done manually, making it difficult to provide efficient learning support. Furthermore, the system was limited in its ability to generate past exam questions and provide questions tailored to the trends of each university, failing to fully meet the needs of students.

[0978] 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: a means for a user to input learning progress and weaknesses; a means for a terminal to transmit the input data to the server; a means for the server to analyze the data using a generation AI model; a means for the server to generate an individual curriculum based on the analysis results; a means for the server to transmit the generated curriculum to the terminal and provide it to the user; a means for the user to periodically input learning progress and for the server to analyze progress data and update the curriculum; a means for integrating the individual curriculum and progress analysis; a means for utilizing past exam question generation AI to provide strategies tailored to the target university; a means for automatically generating questions tailored to the trends and level of each university; a means for providing a chance to pass the desired university with minimal study; and a means for accurately grasping the needs of test takers, maximizing the effectiveness of learning using innovative technology, and helping them realize their dream of passing the desired school. This makes it possible to accurately grasp each test taker's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, automatic feedback on learning progress and curriculum updates enable efficient learning support. In addition, the system has a wide range of features, including the generation of past exam questions and questions tailored to the trends of each university, allowing it to fully meet the needs of test takers.

[0979] "User" refers to a test-taker who uses the system to input their learning progress and weaknesses and receive an individualized curriculum.

[0980] "Terminal" refers to a device that allows a user to input their learning progress and weaknesses and communicate with the server.

[0981] "Server" refers to a computer system that receives data sent by users, analyzes the data using a generative AI model, and generates and provides an individual curriculum.

[0982] A "generative AI model" refers to an artificial intelligence model that analyzes a user's learning progress and weaknesses and generates an optimal individual curriculum.

[0983] "Study progress" refers to the progress and achievement of a user as they progress through their studies.

[0984] "Weakness" refers to a part in which the user has difficulty with a particular learning area or problem.

[0985] "Individualized curriculum" refers to a learning plan optimized for each individual user, generated based on the user's learning progress and weaknesses.

[0986] "Progress data" refers to data regarding the progress and achievement of learning that is periodically entered by the user.

[0987] "Past exam question generation AI" refers to an artificial intelligence model that automatically generates practice questions tailored to the university you are aiming for based on past exam questions.

[0988] "Trends and levels at each university" refers to the characteristics and difficulty of each university's exam questions.

[0989] "Feedback" refers to evaluation and advice on the user's learning progress.

[0990] "Curriculum update" refers to reevaluating an existing individual curriculum based on the user's progress data and changing the content as necessary.

[0991] The present invention is a system for managing the learning progress of test takers in an integrated manner and integrating individual curricula and progress analysis. Specific embodiments of this system are described below.

[0992] System Overview

[0993] This system allows users (test takers) to input their learning progress and weaknesses, and provides an optimal individual curriculum based on that. The system is primarily composed of a server, a terminal, and a generative AI model.

[0994] Hardware and software used

[0995] Server: A high-performance computer system that receives and analyzes data, generates and provides curriculum.

[0996] Device: A device used by a user (e.g., PC, tablet, smartphone) to input learning progress and weaknesses and display the curriculum.

[0997] Generative AI models: For example, advanced artificial intelligence models such as OpenAI's GPT-4 are used to analyze user data and generate optimal curriculum.

[0998] Program processing

[0999] 1. User learning data input:

[1000] The user uses the terminal to input their learning progress and weaknesses, for example, "I can't solve calculus problems."

[1001] 2. Sending data to the server:

[1002] The device sends the input learning data to the server. Specifically, the device sends the data to the server using an HTTP request.

[1003] 3. Data Analysis:

[1004] The server inputs the received data into the generative AI model, which analyzes the user's learning progress and weaknesses. For example, the generative AI model might output an analysis result such as "The user has a weakness in differential and integral calculus."

[1005] 4. Creating a personalized curriculum:

[1006] Based on the analysis results of the generative AI model, the server generates an individual curriculum that focuses on the user's weaknesses. For example, the server generates a curriculum that covers calculus from the basics to applications.

[1007] 5. Curriculum Delivery:

[1008] The server sends the generated individual curriculum to the terminal. The terminal displays the received curriculum to the user. For example, the terminal displays a "Basic Calculus Problem Set" to the user.

[1009] 6. Learning progress feedback and updates:

[1010] The user periodically inputs their learning progress using the terminal. The terminal then sends the input progress data to the server. The server analyzes the progress data and updates the curriculum as necessary. For example, the server generates a curriculum that advances to advanced problems, since the user has cleared basic problems.

[1011] Specific examples

[1012] The user uses a device to input "I can't solve the basic calculus problems." The device sends this data to the server. The server analyzes the data using a generative AI model and determines that "the user has weaknesses in the basics of calculus." The server generates a "curriculum covering calculus from basic to advanced" and sends it to the device. The device displays this curriculum to the user. The user studies according to the curriculum and periodically inputs their progress. The server analyzes the progress data, and if it determines that the user has cleared the basic problems, it generates a curriculum to move on to advanced problems.

[1013] Prompt Sentence Examples

[1014] "Analyze the user's learning progress data and generate a personalized curriculum covering everything from the basics to advanced calculus."

[1015] In this way, a system is constructed in which the server, terminals, and users work together to support the learning of test takers.

[1016] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1017] Step 1:

[1018] The user uses the device to input their learning progress and weak points. Specifically, the user inputs "I can't solve calculus problems." The input data is information about the user's learning progress and weak points. The device temporarily stores this input data.

[1019] Step 2:

[1020] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP request to send data about the user's learning progress and weaknesses to the server. The input is the user's learning progress data, and the output is data sent to the server.

[1021] Step 3:

[1022] The server inputs the received data into the generative AI model. Specifically, the server passes the user's learning progress data to the generative AI model for analysis. The input is the user's learning progress data, and the output is the analysis results by the generative AI model. The generative AI model identifies the user's weaknesses and outputs an analysis result such as "The user has a weakness in differential calculus."

[1023] Step 4:

[1024] The server generates an individual curriculum based on the analysis results of the generative AI model. Specifically, the server receives the analysis results and creates a curriculum that focuses on the user's weaknesses. The input is the analysis results of the generative AI model, and the output is an individual curriculum. For example, the server generates a "curriculum from the basics to applications of calculus."

[1025] Step 5:

[1026] The server sends the generated individual curriculum to the terminal. Specifically, the server uses an HTTP response to send the generated curriculum to the terminal. The input is the individual curriculum, and the output is data sent to the terminal. The terminal displays the received curriculum to the user. For example, the terminal displays a "Basic Calculus Problem Set" to the user.

[1027] Step 6:

[1028] The user periodically inputs their learning progress using the device. Specifically, the user inputs "I have completed the basic calculus problems." The input data is information about the user's learning progress. The device temporarily stores this input data.

[1029] Step 7:

[1030] The terminal sends the input progress data to the server. Specifically, the terminal uses an HTTP request to send the user's learning progress data to the server. The input is the user's learning progress data, and the output is data sent to the server.

[1031] Step 8:

[1032] The server analyzes the progress data and updates the curriculum as necessary. Specifically, the server passes the progress data to a generative AI model for reanalysis. The input is the user's learning progress data, and the output is the updated curriculum. For example, the server generates a curriculum that moves on to advanced problems, since the user has cleared the basic problems.

[1033] Step 9:

[1034] The server sends the updated curriculum to the terminal. Specifically, the server uses an HTTP response to send the updated curriculum to the terminal. The input is the updated curriculum, and the output is data sent to the terminal. The terminal displays the received updated curriculum to the user. For example, the terminal displays "Application Problems for Calculus" to the user.

[1035] (Application example 2)

[1036] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1037] Conventional learning support systems have difficulty accurately analyzing each student's weaknesses and providing an optimal learning plan based on that analysis. Furthermore, they lacked the functionality to centrally manage learning progress and provide real-time feedback, making efficient learning difficult. Furthermore, there were limited ways to provide an immersive learning experience, preventing the effectiveness of learning from being maximized.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for utilizing a past exam question generation AI to provide preparation tailored to the target university; means for automatically generating questions in line with the trends and level of each university; means for integrating individual curricula and progress analysis; means for centrally managing learning progress; means for automatically analyzing the weak points of test takers and generating curricula that focus on those areas; means for providing real-time feedback; means for proposing an optimal study plan using a generative AI model; means for storing and accessing data using a cloud database; and means for providing an immersive learning experience using a head-mounted display. This enables efficient learning that addresses the individual weaknesses of test takers, maximizing learning effectiveness.

[1039] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[1040] "Measures tailored to the university you are aiming for" means providing the most appropriate study plan based on the entrance exam trends and level of the university you are aiming for.

[1041] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[1042] An "individual curriculum" is a customized study plan based on each student's learning progress and weaknesses.

[1043] "Progress analysis" is the process of evaluating a test-taker's learning progress and analyzing how far they have progressed.

[1044] "Means for centrally managing learning progress" refers to a method for managing test-takers' learning data in an integrated manner in a single system.

[1045] "Means for automatically analyzing test-taker's weaknesses" refers to a method for automatically identifying areas or items in which test-taker's weaknesses exist based on the test-taker's learning data.

[1046] "Means for generating a curriculum that focuses on that area" refers to a method for creating a curriculum that focuses learning on the identified weaknesses.

[1047] "Means of providing real-time feedback" are methods that provide immediate assessment and advice to test-takers as they progress through their studies.

[1048] A "generative AI model" is a model that uses artificial intelligence to generate optimal learning plans and questions from data.

[1049] A "cloud database" is a database that can be accessed via the Internet and is a system for storing and managing data.

[1050] A "head-mounted display" is a display device worn on the head that provides an immersive visual experience.

[1051] As an embodiment of the present invention, the following system is constructed.

[1052] System Overview

[1053] This system supports efficient learning by centrally managing students' learning progress and providing individualized curricula. The system is composed of a combination of technologies such as past exam question generation AI, generation AI models, cloud databases, and head-mounted displays.

[1054] Hardware and software used

[1055] Hardware: Smartphone, head-mounted display

[1056] Software: Cloud database (Firebase), generative AI model (GPT-4), real-time feedback system

[1057] Data processing and calculation

[1058] 1. Data Collection:

[1059] As test takers study using smartphones or head-mounted displays, data on their learning content and progress is collected.

[1060] The collected data is stored in a cloud database (Firebase).

[1061] 2. Data Analysis:

[1062] The server uses a generative AI model (GPT-4) based on the collected data to analyze the test-takers' weaknesses.

[1063] Generate a personalized curriculum based on weaknesses.

[1064] 3. Curriculum Delivery:

[1065] The server provides the generated curriculum to the test-taker's smartphone or head-mounted display.

[1066] Track learning progress in real time and provide feedback.

[1067] 4. Immersive learning experience:

[1068] The use of head-mounted displays provides test takers with an immersive learning experience.

[1069] This allows the learning effect to be maximized.

[1070] Specific examples

[1071] For example, if a test-taker has a weakness in calculus, the system operates as follows:

[1072] As test takers study using smartphones or head-mounted displays, their progress data is stored in a cloud database.

[1073] The server uses a generative AI model to analyze the data and identify the test-taker's weak points in calculus.

[1074] The server generates and provides to the test-taker a personalized curriculum that focuses on the identified weaknesses.

[1075] Provide real-time feedback and check understanding as you learn.

[1076] The use of head-mounted displays provides an immersive learning experience, maximizing learning effectiveness.

[1077] Prompt Sentence Examples

[1078] Below are some example prompts to input to the generative AI model:

[1079] "Based on the student's learning progress data, please analyze their weak points in calculus and propose the optimal study plan."

[1080] In this way, students can study efficiently and maximize their chances of being accepted into their desired university.

[1081] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1082] Step 1:

[1083] The user begins learning using a smartphone or head-mounted display. As input, the user's learning content and progress data are collected. The device sends this data to a cloud database (Firebase). As output, the learning content and progress data are stored in the cloud database.

[1084] Step 2:

[1085] The server retrieves learning progress data from the cloud database. The learning progress data stored in the cloud database is used as input. The server performs data analysis using a generative AI model (GPT-4) based on this data. The output identifies the test-taker's weaknesses.

[1086] Step 3:

[1087] The server generates an individualized curriculum based on the identified weaknesses. As input, the weakness data identified by the generative AI model is used. The server uses the generative AI model to propose an optimal learning plan. As output, an individualized curriculum is generated.

[1088] Step 4:

[1089] The server sends the generated individual curriculum to the user's smartphone or head-mounted display. The generated individual curriculum is used as input. The device receives this curriculum and displays it to the user. As output, the user can proceed with their studies based on the individual curriculum.

[1090] Step 5:

[1091] As the user progresses, feedback is provided in real time. As input, the user's learning progress data is again collected. The device sends this data to a server, which uses a generative AI model to generate feedback in real time. As output, the user is given an immediate assessment and advice.

[1092] Step 6:

[1093] It uses a head-mounted display to provide users with an immersive learning experience. The generated personalized curriculum and real-time feedback are used as input. The device uses this data to display visually rich learning content to the user. The output is an immersive learning experience for the user.

[1094] Example 3

[1095] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1096] Conventional learning systems have had difficulty providing optimal learning materials and questions tailored to each student's individual learning style and level of understanding. Furthermore, learning methods that rely on past exam questions have had problems keeping up with the latest trends and the needs of test-takers. Furthermore, the lack of an integrated individual curriculum and progress analysis makes it difficult to maximize the effectiveness of learning. There is a need to solve these issues and provide optimal learning methods that will help test-takers pass the entrance exams for their desired schools.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1098] In this invention, the server includes means for saving basic information entered by the user in a database, means for collecting data on questions answered and learning materials viewed by the user as they study and transmitting the data to the server in real time, means for evaluating the user's learning style and level of comprehension using a generative AI model based on the collected learning data, means for generating learning materials and questions optimal for the user using the generative AI model based on the evaluation results, means for providing the generated learning materials and questions to the user, and means for reevaluating the user's learning style and level of comprehension based on the user's answers and reflecting this in the next study. This makes it possible to provide the test-taker with an optimal learning method tailored to their individual learning style and level of comprehension, maximizing the effectiveness of their learning.

[1099] "Means for saving basic information entered by the user in a database" refers to a function that saves basic information such as name, age, preferred school, favorite subjects, and least favorite subjects that the user enters when accessing the system for the first time in a database.

[1100] "Means for collecting data on questions answered by users and learning materials viewed as users progress through their studies, and sending the data to a server in real time" refers to a function that collects information on questions answered by users and learning materials viewed while they are studying, and immediately sends the data to a server.

[1101] "Means for assessing a user's learning style and level of comprehension using a generative AI model based on collected learning data" refers to a function that analyzes collected learning data and assesses a user's learning style (e.g., visual, auditory, text-based, etc.) and level of comprehension using a generative AI model.

[1102] "Means for generating optimal teaching materials and questions for a user using a generative AI model based on the evaluation results" refers to a function that automatically generates optimal teaching materials and questions for a user using a generative AI model based on the evaluated learning style and level of comprehension.

[1103] The "means for providing the generated teaching materials and questions to the user" is a function for displaying the generated teaching materials and questions on the user's terminal and providing an interface for progressing with learning.

[1104] "Means of re-evaluating the user's learning style and level of understanding based on the user's answers and reflecting this in the next lesson" is a function that analyzes the user's answers, re-evaluates the user's learning style and level of understanding based on this data, and reflects this in the content of the next lesson.

[1105] The present invention is a system that provides an optimal study method based on the test-taker's learning style and level of understanding. A specific embodiment of this system will be described below.

[1106] System Overview

[1107] This system consists of three main elements: a server, a terminal, and a user. The server plays a central role in collecting, analyzing, and generating data, while the terminal provides an interface for users to advance their learning. Users learn through their terminal and send the results to the server.

[1108] Hardware and software used

[1109] Server: A server with a high-performance database server and the computing resources to run the generative AI model. Specifically, we use cloud-based servers (e.g., Amazon Web Services, Google Cloud Platform).

[1110] Terminal: A device used by a user, such as a PC, tablet, or smartphone. These terminals are capable of connecting to the Internet and communicate with the server through a browser or dedicated application.

[1111] Generative AI model: For example, OpenAI's GPT-4 is used as a generative AI model. This model is used to evaluate the user's learning style and level of understanding and generate optimal learning materials and questions.

[1112] Program processing

[1113] Server Processing

[1114] The server stores the basic information entered by the user in a database. As the user progresses with their studies, data on the questions they answer and the learning materials they view is collected and sent to the server in real time. A generative AI model is used based on the collected learning data to evaluate the user's learning style and level of understanding. Based on the evaluation results, the generative AI model is used to generate learning materials and questions that are optimal for the user. The generated learning materials and questions are stored on the server and sent to the user's device.

[1115] Terminal handling

[1116] The terminal provides the user with the most suitable learning materials and questions sent from the server. The user browses these learning materials and answers the questions through the terminal. The terminal provides an interface for smooth user operation and sends the answer results to the server.

[1117] User Action

[1118] Users study the learning materials and questions provided through their devices. They select learning materials that suit their learning style and solve the questions. Their answers are sent to the server via their devices and are reflected in their next study session.

[1119] Specific examples

[1120] For example, if test-taker A prefers visual learning, the server uses a generative AI model to generate visual learning materials (materials that make extensive use of charts and illustrations). The device displays these, and User A uses the visual learning materials to study. After studying, the results of User A's answers to the questions are sent to the server and reflected in the next study session.

[1121] Prompt Sentence Examples

[1122] "Test-taker A prefers visual learning. Please generate the best visual materials for him."

[1123] In this way, the system can provide the most suitable learning method to suit the student's learning style and level of understanding, maximizing the effectiveness of the learning. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1124] Step 1:

[1125] User registration and initial settings

[1126] When a user accesses the system for the first time, they enter basic information such as their name, age, preferred school, favorite subjects, and weak subjects. The server stores this basic information in a database. The entered basic information is used later to evaluate the user's learning style and level of understanding.

[1127] Step 2:

[1128] Collecting training data

[1129] As the user progresses with their studies, the device collects data on the questions they have answered and the learning materials they have viewed. This data is sent to the server in real time. The server stores the collected data in a database for later analysis. The input is the user's learning behavior data, and the output is the learning data stored in the database.

[1130] Step 3:

[1131] Learning Style and Comprehension Assessment

[1132] The server uses a generative AI model based on the collected learning data to evaluate the user's learning style and level of comprehension. Specifically, it analyzes what format of learning materials the user prefers (text, diagrams, videos, etc.) and in which areas the user has a deep understanding. The input is the learning data, and the output is the evaluation results of the user's learning style and level of comprehension.

[1133] Step 4:

[1134] Generating optimal teaching materials and questions

[1135] The server uses a generative AI model based on the evaluation results to generate optimal learning materials and questions for each user. For example, for users who prefer visual learning, it generates learning materials that make extensive use of diagrams and illustrations. The input is the evaluation results, and the output is the generated learning materials and questions.

[1136] Step 5:

[1137] Providing study materials and questions

[1138] The terminal provides the user with the most suitable learning materials and questions sent from the server. The user browses these learning materials and answers the questions through the terminal. The input is the generated learning materials and questions, and the output is the learning content provided to the user.

[1139] Step 6:

[1140] Feedback on learning results

[1141] The user studies the provided learning materials and answers the questions. The answers are sent to the server via the terminal. The server then re-evaluates the user's learning style and level of understanding based on these results and reflects them in the next study session. The input is the user's answers, and the output is the updated evaluation results of the learning style and level of understanding.

[1142] (Application example 3)

[1143] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1144] Conventional learning support systems have difficulty providing optimal learning methods tailored to each student's individual learning style and level of understanding. Furthermore, they lack real-time feedback based on learning progress, preventing students from studying efficiently. Furthermore, they lack the ability to customize learning plans using generative AI models, making it impossible to fully meet the needs of test takers.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1146] In this invention, the server includes a means for utilizing past exam question generation AI to provide strategies tailored to the university of interest, a means for automatically generating questions tailored to the trends and level of each university, a means for integrating individual curricula and progress analysis, a means for diagnosing the student's learning style and generating an optimal study plan, a means for customizing the study plan using a generative AI model, and a means for providing real-time feedback according to the student's learning progress. This makes it possible to provide the optimal study method tailored to the individual needs of each student and maximize the effectiveness of their learning.

[1147] "Past exam question generation AI" is an artificial intelligence technology that analyzes past exam questions and automatically generates practice questions tailored to the university you are aiming for.

[1148] "Measures tailored to the university you are aiming for" means providing the most appropriate study content and questions based on the question trends and difficulty level of the university you are applying to.

[1149] "Questions that are in line with the trends and level of each university" are questions created based on the past question trends and difficulty level of each university.

[1150] An "individual curriculum" is a customized study plan based on each student's learning progress and level of understanding.

[1151] "Progress analysis" is a means of assessing a test-taker's learning situation in real time and understanding their progress.

[1152] "Assessing learning style" means assessing whether a candidate has a visual, auditory, or tactile learning style.

[1153] "Generating the optimal study plan" means creating a study plan that is most suitable for each test-taker based on the diagnostic results.

[1154] A "generative AI model" is a model that uses artificial intelligence technology to generate optimal study plans and feedback for test takers.

[1155] "Customized study plans" means using generative AI models to create study plans tailored to each test-taker's individual needs.

[1156] "Providing real-time feedback" means providing instant assessment and advice based on the test-taker's learning progress.

[1157] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The specific functions and processing of each element will be explained below.

[1158] server

[1159] The server runs multiple software modules, including the past exam question generation AI, the generation AI model, and the database. The server has the following functions:

[1160] 1. Past exam question generation AI: Analyzes past exam questions and automatically generates practice questions tailored to the university of their choice. This allows test-takers to solve questions that are in line with the exam trends of their desired university.

[1161] 2. Generative AI model: Generates an optimal study plan based on the results of the student's learning style assessment. The generative AI model uses advanced natural language processing techniques such as OpenAI's GPT-3.

[1162] 3. Database: Stores data such as students' learning progress, diagnostic results, and generated learning plans.

[1163] Terminal

[1164] A device is a device used by a test-taker, such as a smartphone or tablet. A device has the following features:

[1165] 1. Learning Style Assessment: Provides an interface to assess whether a candidate has a visual, auditory, or tactile learning style.

[1166] 2. Displaying the study plan: The generated study plan is displayed to the candidate, providing guidance for progressing through the study.

[1167] 3. Real-time feedback: Feedback provided by the server is displayed in real time according to the learning progress.

[1168] User

[1169] The user is a student taking the exam. The user performs the following actions:

[1170] 1. Complete the Learning Style Assessment: Use your device to complete the Learning Style Assessment.

[1171] 2. Implementing the learning plan: Proceed with your studies according to the generated learning plan.

[1172] 3. Review your feedback: Review the feedback you receive as you progress and adjust your learning methods.

[1173] Specific examples

[1174] For example, for a test-taker with a visual learning style, the following prompts could be fed into the generative AI model:

[1175] Example prompt sentence:

[1176] Create a learning plan for a visual learner preparing for university entrance exams. The plan should include visual aids, diagrams, and interactive exercises.

[1177] By inputting this prompt into a generative AI model, a learning plan optimized for a visual learning style is generated. The generated learning plan is then provided to the test-taker via their device, allowing them to proceed with their studies accordingly.

[1178] As described above, the present invention can provide an optimum study method that meets the individual needs of each examinee, thereby maximizing the learning effect.

[1179] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1180] Step 1:

[1181] The user answers the learning style assessment using the terminal.

[1182] Input: The user answers the learning style assessment questions.

[1183] Data processing: The terminal collects the user's answers and sends them to a database.

[1184] Output: The results of the user's learning style diagnosis are saved in a database.

[1185] Step 2:

[1186] The server analyzes the learning style diagnosis results and identifies the user's learning style.

[1187] Input: User's learning style assessment results stored in the database.

[1188] Data Computation: The server analyzes the diagnostic results and identifies whether the user has a visual, auditory, or tactile learning style.

[1189] Output: The user's learning style is identified.

[1190] Step 3:

[1191] The server uses the generative AI model to generate a learning plan based on the user's learning style.

[1192] Input: User's learning style.

[1193] Data calculation: The server inputs prompt sentences into the generative AI model and generates a learning plan that is optimal for the user's learning style.

[1194] Output: The generated learning plan is saved in a database.

[1195] Step 4:

[1196] The device displays the generated learning plan to the user.

[1197] Input: Learning plans stored in the database.

[1198] Data processing: The device retrieves the study plan and displays it visually to the user.

[1199] Output: User can check the learning plan.

[1200] Step 5:

[1201] The user progresses through the learning process according to the learning plan.

[1202] Input: The generated lesson plan.

[1203] Specific operations: The user studies according to the study plan and enters their progress into the device.

[1204] Output: The user's learning progress data is saved in a database.

[1205] Step 6:

[1206] The server analyzes the user's learning progress and generates feedback in real time.

[1207] Input: User learning progress data stored in a database.

[1208] Data calculation: The server analyzes the learning progress data and generates feedback using a generative AI model.

[1209] Output: The generated feedback is stored in a database.

[1210] Step 7:

[1211] The terminal displays the generated feedback to the user.

[1212] Input: Feedback stored in the database.

[1213] Data processing: The device obtains the feedback and displays it visually to the user.

[1214] Output: User can see the feedback.

[1215] 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.

[1216] "Example 1"

[1217] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes a user's emotions and adjusts the learning content and progress speed accordingly. Specifically, if the system recognizes that the user is feeling stressed about learning, it simplifies the learning content and slows down the progress speed to reduce the user's stress. Furthermore, if the system recognizes that the user is highly motivated to learn, it provides more advanced learning content and speeds up the progress speed to maximize the user's learning efficiency.

[1218] "Example 2"

[1219] Another embodiment of the present invention is a system in which an emotion engine recognizes a user's emotions and provides an optimal learning method based on the user's emotions. Specifically, if the system recognizes that the user is excited about learning, it provides a problem-solving learning method. This is because an excited user can understand the learning content more deeply by challenging themselves with new problems. On the other hand, if the system recognizes that the user is relaxed about learning, it provides a reading-based learning method. This is because a relaxed user can absorb a wider range of knowledge by quietly reading texts.

[1220] "Example 3"

[1221] In a further embodiment of the present invention, there is a system in which an emotion engine recognizes a user's emotions and adjusts the learning environment based on the emotions. Specifically, if the system recognizes that the user is feeling impatient about studying, it calms the learning environment by playing quiet music, for example. On the other hand, if the system recognizes that the user is feeling lethargic about studying, it energizes the learning environment by providing bright lighting and lively music, for example. This makes it possible to provide an optimal learning environment according to the user's emotions and maximize learning effectiveness.

[1222] The processing flow of each embodiment will be described below.

[1223] "Example 1"

[1224] Step 1: The emotion engine recognizes the user's emotion.

[1225] Step 2: Adjust the learning content and pace based on the emotions recognized by the system.

[1226] Step 3: Prompt the user to proceed with their learning based on the adjusted learning content and progress rate.

[1227] "Example 2"

[1228] Step 1: The emotion engine recognizes the user's emotion.

[1229] Step 2: The system determines the optimal learning method based on the emotions it recognizes.

[1230] Step 3: Based on the determined learning method, the user is instructed to proceed with the learning.

[1231] "Example 3"

[1232] Step 1: The emotion engine recognizes the user's emotion.

[1233] Step 2: Adjust the learning environment based on the emotions recognized by the system.

[1234] Step 3: Prompt the user to proceed with their learning in the tailored learning environment.

[1235] Example 1

[1236] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1237] Conventional exam preparation systems have difficulty automatically generating questions that match the question trends and level of a specific educational institution, and lack the functionality to adjust the learning content and progress speed according to the user's emotions, resulting in poor learning efficiency. Furthermore, they lack the functionality to quickly and accurately grade users' answers and provide the results. A system that can solve these problems and provide efficient and effective exam preparation is needed.

[1238] 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.

[1239] In this invention, the server includes: means for utilizing a past exam question generation AI to provide preparation tailored to the educational institution of interest; means for automatically generating questions tailored to the trends and level of each educational institution; means for integrating individual curricula and progress analysis; means for recognizing a user's emotions and adjusting the learning content and progress rate according to those emotions; means for generating questions using a generative AI model; means for recognizing a user's emotions using an emotion engine; and means for scoring the user's answers and providing the results. This makes it possible to automatically generate questions tailored to a specific educational institution and adjust the learning content and progress rate according to the user's emotions, thereby providing efficient and effective exam preparation.

[1240] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam question data.

[1241] An "educational institution" is an institution that provides a specific education, such as a university or vocational school.

[1242] "Trends" refer to the patterns and characteristics of questions that a particular educational institution has asked in the past.

[1243] "Level" is an indicator of the difficulty and complexity of the question.

[1244] An "individual curriculum" is a learning plan customized to suit each user's learning progress and goals.

[1245] "Progress analysis" is the process of evaluating and analyzing a user's learning progress.

[1246] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions, voice, etc.

[1247] A "generative AI model" is a model that uses artificial intelligence to generate new data and information.

[1248] "Scoring answers" is the process of evaluating and scoring user-submitted answers.

[1249] "Providing the results" means notifying the user of the scoring results and feedback.

[1250] This invention is a system that utilizes AI to generate past exam questions and provides strategies tailored to the educational institution of interest. The system operates in cooperation with the server, the terminal, and the user.

[1251] The server uses a past exam generation AI to collect and analyze past exam data from specific educational institutions. Specifically, it retrieves past exam questions from a database and uses an analytical algorithm to understand question trends and difficulty levels. Next, it uses a generative AI model (such as OpenAI's GPT-4) to generate new questions. This generative AI model automatically generates questions tailored to the trends and level of each educational institution based on the collected and analyzed data.

[1252] The terminal receives requests from the user and sends them to the server. For example, if a user requests questions from a specific educational institution, the terminal sends that information to the server. The server receives the request and returns the generated questions to the terminal. The terminal then displays the received questions to the user.

[1253] The user solves the displayed problem through the terminal. After entering the answer and pressing the send button, the terminal sends the answer data to the server. The server grades the received answer and generates a result. The result data is then sent to the terminal, which displays it to the user.

[1254] Furthermore, the system uses an emotion engine (e.g., Affectiva's SDK) to recognize the user's emotions. If the user feels stressed while learning, the server will simplify the learning content and slow down the progress. Conversely, if the user is highly motivated, the server will provide more advanced learning content and speed up the progress.

[1255] As a concrete example, consider the case of generating long-form English questions for University A. When a user requests a long-form English question from University A, the server uses a generative AI model to generate new questions based on past data on long-form English questions from University A. The generated questions are then displayed on the user's device.

[1256] Example prompt sentence:

[1257] "Please generate long-form English questions for University A. Please create questions that are in line with the university's trends based on past question data."

[1258] In this way, a system is realized in which the server, terminals, and users work together to provide efficient and effective exam preparation.

[1259] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1260] Step 1:

[1261] The user selects the educational institution they wish to attend.

[1262] The user uses the terminal interface to select the educational institution of interest, for example, University A. The input is the user's selection information, and the output is the ID and name of the selected educational institution.

[1263] Step 2:

[1264] The terminal transmits the selection information to the server.

[1265] The terminal sends information about the educational institution selected by the user to the server. Specifically, it sends data including the ID and name of the selected educational institution. The input is the user's selection information, and the output is the data sent to the server.

[1266] Step 3:

[1267] The server collects and analyzes past exam data from educational institutions.

[1268] The server collects past exam data from the selected educational institution from the database. It then analyzes the collected data to understand the educational institution's question trends and difficulty level. The input is the educational institution's ID and name, and the output is the analysis results.

[1269] Step 4:

[1270] The server generates questions using a generative AI model.

[1271] The server generates new questions using a generative AI model (e.g., OpenAI's GPT-4) based on the analysis results. For example, it generates long-form English questions for University A. The input is the analysis results, and the output is the generated questions.

[1272] Step 5:

[1273] The server sends the generated questions to the device.

[1274] The server sends the generated questions to the terminal. Specifically, it includes data such as the question text and answer options. The input is the generated question, and the output is the data sent to the terminal.

[1275] Step 6:

[1276] The terminal displays the problem to the user.

[1277] The terminal displays the received questions to the user, who can check the questions on the screen. The input is the question data received from the server, and the output is the display to the user.

[1278] Step 7:

[1279] The user solves the problem.

[1280] The user solves the displayed problem, inputs the answer, and presses the send button. The input is the user's answer, and the output is the answer data sent to the terminal.

[1281] Step 8:

[1282] The terminal sends the user's answer to the server.

[1283] The terminal transmits the user's answer to the server. Specifically, the answer data is included. The input is the user's answer data, and the output is the data to be transmitted to the server.

[1284] Step 9:

[1285] The server grades the answers and sends the results to the device.

[1286] The server grades the received answers and generates a result. Then, it sends the result data to the terminal. The input is the user's answer data, and the output is the graded result.

[1287] Step 10:

[1288] The terminal displays the results to the user.

[1289] The terminal displays the received results to the user, who can check their score and correct answer rate. The input is the result data received from the server, and the output is what is displayed to the user.

[1290] Step 11:

[1291] The emotion engine recognizes the user's emotions.

[1292] An emotion engine (e.g., Affectiva's SDK) analyzes the user's facial expressions and voice to recognize emotions. For example, it determines whether the user is feeling stressed. The input is the user's facial expressions and voice data, and the output is the emotion recognition result.

[1293] Step 12:

[1294] The server adjusts the learning content and progress speed according to the emotion.

[1295] The server adjusts the learning content and progress speed based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the difficulty of the questions will be reduced and the progress speed will be slowed down. Conversely, if the user is highly motivated, more difficult questions will be provided and the progress speed will be increased. The input is the emotion recognition results, and the output is the adjusted learning content and progress speed.

[1296] (Application example 1)

[1297] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1298] Conventional exam preparation systems have difficulty providing questions tailored to the trends and levels of each university, and do not adjust the learning content according to the user's emotional state. As a result, test takers often feel stressed and lose motivation. Furthermore, they do not offer a personalized learning experience using devices such as smartphones.

[1299] 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.

[1300] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the university the student is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the user's emotions and adjusting the learning content and progress speed in accordance with those emotions; a means for adjusting the difficulty of the learning content based on the user's emotional state as an application installed on a smartphone; and a means for generating questions based on prompt sentences using a generative AI model. This allows test-takers to study efficiently without feeling stressed and while maintaining motivation.

[1301] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[1302] "Measures tailored to the university you are aiming for" means providing study plans and questions that are tailored to the entrance exam trends and level of a specific university.

[1303] "Questions that are in line with the trends and level of each university" are questions created based on the characteristics and difficulty of each university's entrance examination questions.

[1304] An "individual curriculum" is a study plan customized to each test-taker's learning progress and level of understanding.

[1305] A "progress analysis" is an analysis to evaluate a candidate's learning progress and determine the next learning step.

[1306] "Means for recognizing user emotions" refers to technology that identifies a user's emotional state by analyzing the user's facial expressions, tone of voice, etc.

[1307] The "means for adjusting the learning content and progress speed" is a function for changing the learning content and progress speed according to the user's emotional state.

[1308] An "application installed on a smartphone" is a software program that runs on a smartphone.

[1309] The "means for adjusting the difficulty level of the learning content based on the emotional state of the user" is a function for changing the difficulty level of the learning content in consideration of the emotional state of the user.

[1310] A "generative AI model" is an artificial intelligence model that generates new questions or content based on a given prompt.

[1311] A "prompt" is an instruction given to a generative AI model to generate a specific problem or content.

[1312] The system for implementing this invention uses a past exam question generation AI, an emotion recognition engine, a smartphone application, and a generation AI model. The specific configuration and operation of the system are described below.

[1313] System configuration

[1314] 1. AI for generating past exam questions

[1315] This is an artificial intelligence technology that automatically generates new questions based on past exam questions. This technology is used to generate questions that are in line with the trends and level of each university.

[1316] 2. Emotion Recognition Engine

[1317] This technology identifies the user's emotional state by analyzing their facial expressions and tone of voice. The engine uses the smartphone's camera and microphone to recognize the user's emotions in real time.

[1318] 3. Smartphone Applications

[1319] It is a software program that runs on smartphones. The application adjusts the difficulty of learning content based on the user's emotional state and integrates a personalized curriculum and progress analysis.

[1320] 4. Generative AI Models

[1321] This is an artificial intelligence model that generates new questions and content based on a given prompt. This model works in conjunction with the past exam question generation AI.

[1322] System Operation

[1323] 1. User Emotion Recognition

[1324] Using the smartphone's camera and microphone, the emotion recognition engine analyzes the user's emotional state in real time, identifying, for example, when the user is feeling stressed or highly motivated.

[1325] 2. Adjusting learning content

[1326] The smartphone application adjusts the difficulty and pace of the learning content based on the emotional state identified by the emotion recognition engine. For example, it lowers the difficulty of the questions if the user is stressed, and increases the difficulty if the user is highly motivated.

[1327] 3. Problem Generation

[1328] The generative AI model generates new questions based on the prompt. Examples of prompts include "Please generate a long-form English question for University A. The difficulty level is easy" and "Please generate a long-form English question for University A. The difficulty level is difficult."

[1329] 4. Learning Progression

[1330] The smartphone application provides the generated questions to the user, who then solves them. The application records the user's answers and performs progress analysis.

[1331] Specific examples

[1332] For example, if a user is aiming for "University A," and the emotion recognition engine identifies the user's emotional state as "stressed," the smartphone application sends a prompt to the generative AI model: "Please generate long-answer English questions for University A. The difficulty level is easy." The generated questions are then provided to the user. After the user solves the questions, the application records the answers and determines the next learning step.

[1333] In this way, a personalized learning experience can be provided that responds to the user's emotional state.

[1334] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1335] Step 1:

[1336] User Emotion Recognition

[1337] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice in real time. An emotion recognition engine does this to identify the user's emotional state (e.g., stress, motivation, etc.). The input is video and audio data from the camera and microphone, and the output is data indicating the user's emotional state.

[1338] Step 2:

[1339] Adjusting learning content

[1340] The server uses an emotion recognition engine to determine the user's emotional state, and the smartphone application adjusts the difficulty and progress of the learning content based on that state. For example, if the user is feeling stressed, the difficulty of the questions is lowered, and if the user is highly motivated, the difficulty is increased. The input is the user's emotional state data, and the output is the adjusted difficulty setting for the learning content.

[1341] Step 3:

[1342] Generate prompt statement

[1343] The server generates a prompt to be sent to the generative AI model based on the adjusted difficulty settings of the learning content. For example, it generates a prompt such as "Please generate a long-answer English question for University A. The difficulty level is easy." The input is the difficulty setting of the learning content, and the output is the prompt to be sent to the generative AI model.

[1344] Step 4:

[1345] Problem Generation

[1346] The server sends a prompt to the generative AI model to generate a new problem. The generative AI model generates a problem based on the prompt and returns it to the server. The input is the prompt, and the output is the generated problem.

[1347] Step 5:

[1348] Providing a problem

[1349] The server provides the generated questions to the user through a smartphone application. The user solves the questions and inputs the answers into the application. The input is the generated questions, and the output is the user's answers.

[1350] Step 6:

[1351] Progress Analysis

[1352] The server records the user's answers and performs a progress analysis. A progress analysis engine performs this and evaluates the user's learning progress. The input is the user's answer data, and the output is the progress analysis result.

[1353] Step 7:

[1354] Determining the next learning step

[1355] The server determines the next learning step based on the progress analysis results. This updates the user's learning plan and determines the next learning content. The input is the progress analysis results, and the output is the setting for the next learning step.

[1356] Example 2

[1357] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1358] Conventional learning support systems have difficulty providing optimal learning methods tailored to each student's individual learning progress and emotional state. Furthermore, there is a lack of systems for centrally managing learning history and progress data to efficiently advance learning. This has led to problems such as students being unable to effectively overcome their weaknesses and not maximizing the effectiveness of their learning.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1360] In this invention, the server includes means for acquiring user learning history data, means for generating an individual curriculum using a generative AI model, means for collecting learning progress data, means for generating a progress report, means for acquiring user emotional data, means for determining the emotional state, and means for providing an optimal learning method. This allows the server to provide an optimal learning method according to the user's learning progress and emotional state, thereby enabling efficient learning.

[1361] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[1362] "Measures tailored to the university you are aiming for" is a method of providing test takers with study plans and questions that are optimally tailored to the entrance exam trends and level of a specific university.

[1363] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[1364] An "individual curriculum" is a customized study plan based on each candidate's learning progress and weaknesses.

[1365] "Progress analysis" is a data analysis method for evaluating a test-taker's learning situation and visualizing their progress.

[1366] "User learning history data" is data relating to the content and grades that the user has studied in the past.

[1367] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate new information and plans.

[1368] "Study progress data" is data related to the user's current study, including the study time, the number of questions answered, and the percentage of correct answers.

[1369] A "progress report" is a report created based on learning progress data, and visually indicates the user's learning situation.

[1370] "User emotion data" refers to data relating to emotions acquired from the user's facial expressions, voice, and the like.

[1371] "Emotional state" indicates the user's current emotional state, and includes an excited state, a relaxed state, and the like.

[1372] The "optimal learning method" refers to the most effective learning technique depending on the user's learning progress and emotional state.

[1373] This invention is a system for efficiently supporting the learning of test-takers, and integrates the provision of an individual curriculum, progress analysis, and emotion recognition. Specific embodiments of this system will be described below.

[1374] Hardware and software used

[1375] Server: Database management system (e.g., MySQL), web server (e.g., Apache)

[1376] Device: PC or smartphone used by the user

[1377] Software: Learning Management Systems (LMS), emotion recognition software (e.g., Affectiva)

[1378] Data processing and calculation

[1379] 1. Obtaining user learning history data

[1380] The server obtains the user's learning history data from the database.

[1381] Specifically, past learning content and grade data are extracted using a query using the user ID as a key.

[1382] Example: "SELECT FROM Learning History WHERE User ID = '12345';"

[1383] 2. Creating an individual curriculum

[1384] The server generates an individual curriculum using a generative AI model (e.g., GPT-4) based on the acquired learning history data.

[1385] Specifically, we analyze the user's weaknesses and create a curriculum that focuses on those areas.

[1386] For example: "If a user has a weakness in calculus, generate a personalized curriculum that focuses on that area."

[1387] 3. Collecting learning progress data

[1388] The device collects real-time progress data as the user progresses through their studies.

[1389] Specifically, data such as study time, number of questions answered, and accuracy rate are collected.

[1390] Example: "User studied for 1 hour and answered 40 out of 50 questions correctly."

[1391] 4. Generate progress reports

[1392] The server analyzes the collected learning progress data and generates a progress report.

[1393] Specifically, learning progress and achievement levels are visualized using graphs and tables.

[1394] For example: "User is 80% complete and 20% away from achieving their goal."

[1395] 5. Acquiring user emotion data

[1396] The device analyzes the user's facial expressions and voice data using emotion recognition software (e.g., Affectiva).

[1397] Specifically, it uses cameras and microphones to collect data in real time and analyzes emotional states.

[1398] Example: "The user is smiling, so they are perceived as excited."

[1399] 6. Judging emotional states

[1400] The server receives the emotion data sent from the terminal and determines the user's emotional state.

[1401] Specifically, based on the analysis results, it is determined whether the user is in an excited state or a relaxed state.

[1402] Example: "The user is determined to be in an excited state."

[1403] 7. Providing optimal learning methods

[1404] The server uses a generative AI model to provide the optimal learning method based on the emotional state.

[1405] Specifically, a problem-solving learning method is provided when the student is excited, and a reading-based learning method is provided when the student is relaxed.

[1406] For example: "If the user is in an excited state, provide them with a problem-based learning method."

[1407] In this way, the system provides an efficient learning environment by linking the server, terminals, and users.

[1408] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1409] Step 1:

[1410] Obtaining user learning history data

[1411] Input: User ID

[1412] Specific operation: The server retrieves the user's learning history data from the database. Specifically, it uses the user ID as a key to query past learning content and grade data.

[1413] Data processing: Execute a database query to obtain the relevant learning history data.

[1414] Output: Learning history data (e.g., "SELECT FROM Learning History WHERE User ID = '12345';")

[1415] Step 2:

[1416] Creating an individual curriculum

[1417] Input: Learning history data

[1418] Specific operation: The server generates an individual curriculum using a generative AI model (e.g., GPT-4) based on the acquired learning history data. Specifically, it analyzes the user's weaknesses and creates a curriculum that focuses on those areas.

[1419] Data processing: Analyze learning history data to identify user weaknesses. Input prompts into the generative AI model to generate a curriculum.

[1420] Output: Personalized curriculum (e.g., "If the user has a weakness in calculus, generate a personalized curriculum that focuses on that area.")

[1421] Step 3:

[1422] Collecting learning progress data

[1423] Input: User's learning activity data (study time, number of questions answered, correct answer rate, etc.)

[1424] What it does: The device collects real-time progress data as the user learns.

[1425] Data processing: Collect learning activity data and send it to the server.

[1426] Output: Learning progress data (e.g., "User studied for 1 hour and answered 40 out of 50 questions correctly.")

[1427] Step 4:

[1428] Generate progress reports

[1429] Input: Learning progress data

[1430] Specific operation: The server analyzes the collected learning progress data and generates a progress report, specifically visualizing the learning progress and achievement level in graphs and tables.

[1431] Data processing: Analyze learning progress data and generate data for visualization.

[1432] Output: Progress report (e.g. "User is 80% done and 20% away from achieving goal.")

[1433] Step 5:

[1434] Obtaining user emotion data

[1435] Input: User facial and voice data

[1436] How it works: The device analyzes the user's facial expressions and voice data using emotion recognition software (e.g., Affectiva). Specifically, it uses a camera and microphone to collect data in real time and analyzes the user's emotional state.

[1437] Data processing: Analyze facial expressions and voice data to identify emotional states.

[1438] Output: Emotion data (e.g., "The user is smiling, so they are recognized as excited.")

[1439] Step 6:

[1440] Judging emotional states

[1441] Input: Emotion data

[1442] Specific operation: The server receives the emotion data sent from the device and judges the user's emotional state. Specifically, based on the analysis results, it determines whether the user is excited or relaxed.

[1443] Data processing: Analyze emotional data and determine emotional states.

[1444] Output: Emotional state (e.g., "The user is judged to be in an excited state.")

[1445] Step 7:

[1446] Providing optimal learning methods

[1447] Input: Emotional state

[1448] Specific operation: The server uses a generative AI model to provide the optimal learning method according to the emotional state. Specifically, it provides a problem-solving learning method when the user is excited, and a reading-based learning method when the user is relaxed.

[1449] Data processing: Based on the emotional state, prompt sentences are input into the generative AI model to generate the optimal learning method.

[1450] Output: Optimal learning method (e.g., "If the user is excited, provide a problem-solving learning method.")

[1451] (Application example 2)

[1452] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1453] Conventional learning management systems have difficulty providing optimal learning methods that take into account each student's individual learning progress and emotional state. Furthermore, they lack systems that maximize learning efficiency and increase the chances of passing the university of their choice. This has led to problems such as students being unable to study efficiently and not fully realizing the benefits of their studies.

[1454] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1455] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the university the examinee is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the user's emotional state and providing an optimal study method based thereon; and a means for analyzing the user's study progress data and generating an individual curriculum focusing on weak areas. This makes it possible to provide the examinee with an optimal study method based on their study progress and emotional state, maximizing their study efficiency.

[1456] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[1457] "Measures tailored to the university you are aiming for" is a method of providing optimal study plans and questions based on the entrance exam trends and level of the university you are aiming for.

[1458] "Questions that are in line with the trends and level of each university" are questions that are created to match the characteristics and difficulty of each university's entrance examination questions.

[1459] An "individual curriculum" is a customized study plan based on each candidate's learning progress and weaknesses.

[1460] "Progress analysis" is a method of evaluating a test-taker's learning progress and analyzing how far they have progressed.

[1461] "Recognizing the user's emotional state" refers to a technology that determines the user's current emotions from their facial expressions and behavior.

[1462] The "optimal learning method" is the learning technique that is most suitable for maximizing the user's learning efficiency.

[1463] "Study progress data" is data that indicates how far a test-taker has progressed in their studies.

[1464] "Weak areas" are areas of study or subjects in which a candidate is particularly weak.

[1465] "Generating an individual curriculum" refers to creating an optimal study plan based on the student's learning progress and weaknesses.

[1466] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a means for utilizing past exam question generation AI to provide strategies tailored to the university the user is aiming for, a means for automatically generating questions tailored to the trends and level of each university, a means for integrating individualized curricula and progress analysis, a means for recognizing the user's emotional state and providing the optimal learning method based on that, and a means for analyzing the user's learning progress data and generating an individualized curriculum that focuses on weak areas.

[1467] Hardware and Software Configuration

[1468] 1. Hardware:

[1469] Server: A server with high-performance computing power is required.

[1470] Device: The device used by the user, such as a smartphone or head-mounted display.

[1471] Camera: The device is equipped with a camera to recognize the user's emotional state.

[1472] 2. Software:

[1473] Past exam question generation AI: An artificial intelligence model for generating new questions based on past exam questions.

[1474] Emotion recognition software: Software that recognizes emotions from a user's facial expressions and behavior.

[1475] Curriculum generation software: Software for generating individualized curricula based on the user's learning progress data and emotional state.

[1476] Data analysis tools: Tools for analyzing learning progress data (e.g., scikit-learn).

[1477] Processing flow

[1478] 1. Learning progress analysis:

[1479] The server collects the user's learning progress data and evaluates the progress using a data analysis tool. Specifically, it builds a linear regression model based on the time spent studying and the score, and predicts the user's learning progress.

[1480] 2. Emotion Recognition:

[1481] The device's built-in camera captures the user's facial expressions, which are then analyzed using emotion recognition software to determine whether the user is excited or relaxed.

[1482] 3. Creating a personalized curriculum:

[1483] The server uses curriculum generation software to create an optimal learning plan based on the user's learning progress data and emotional state. For example, if a user has weaknesses in a particular area of ​​math, it will provide a set of problems that focus on that area.

[1484] 4. Provision of learning materials:

[1485] The server then distributes the most suitable learning materials to the user's terminal based on the generated individual curriculum, allowing the user to study efficiently.

[1486] Specific examples

[1487] For example, if a user has a weakness in a particular area of ​​mathematics, the server can generate a set of problems that focus on that area and provide it to the user.Also, if the server recognizes that the user is excited, it can provide a problem-solving learning method that challenges the user with new problems.

[1488] Prompt Sentence Examples

[1489] Develop an application that analyzes a user's learning progress data and provides optimal learning methods based on their emotional state. Recognize emotions from the user's image and generate a personalized curriculum that focuses on weak areas. The data used includes time spent studying, scores, user image, and weak areas.

[1490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1491] Step 1:

[1492] The server collects the user's learning progress data. As input, it receives data on the time spent by the user on learning and the score. Based on this data, it uses a data analysis tool (e.g., scikit-learn) to evaluate the progress. Specifically, it builds a linear regression model to predict the user's learning progress. As output, it obtains the evaluation results of the user's learning progress.

[1493] Step 2:

[1494] The device captures the user's facial expression with a camera. The user's facial image is acquired as input. Emotion recognition software is used to analyze the user's emotions from their facial expression. Specifically, image processing technology is used to extract facial features and determine the user's emotional state. The output is the user's emotional state (excited or relaxed).

[1495] Step 3:

[1496] The server generates an individualized curriculum based on the user's learning progress data and emotional state. It receives the learning progress assessment results and emotional state as input. It uses the curriculum generation software to create an optimal learning plan that focuses on the user's weak areas. Specifically, it selects questions related to the user's weak areas and incorporates them into the learning plan. It obtains the individualized curriculum as output.

[1497] Step 4:

[1498] The server delivers the most suitable learning materials to the user's device based on the generated individual curriculum. The server receives the individual curriculum as input. It selects learning materials and sends them to the device. Specifically, it selects problem sets and reference materials included in the curriculum and delivers them to the user's device. The learning materials are provided to the user's device as output.

[1499] Step 5:

[1500] The user progresses with their studies using the learning materials delivered to their device. As input, they receive the learning materials displayed on their device. They study and record progress data, specifically by solving problems and reading reference materials. As output, new learning progress data is generated.

[1501] Step 6:

[1502] The server collects new learning progress data for the user again and repeats the process from step 1. It receives the new learning progress data as input. It analyzes the data again and evaluates the learning progress. Specifically, it compares the previous progress data with the new data and evaluates the learning effectiveness. It obtains an updated learning progress evaluation result as output.

[1503] Example 3

[1504] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1505] Conventional learning systems have difficulty providing an optimal learning environment that matches each student's individual learning style and emotional state. Furthermore, they are unable to accurately meet the needs of students when generating past exam questions or providing individualized curricula, making it difficult to maximize learning effectiveness. Furthermore, there is a lack of means to analyze learning progress in real time and provide appropriate feedback.

[1506] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1507] In this invention, the server includes a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution the student is aiming for, a means for automatically generating questions tailored to the trends and level of each educational institution, a means for integrating individual curricula and progress analysis, a means for diagnosing the user's learning style, a means for providing optimal learning materials based on the diagnosis results, and a means for recognizing the user's emotions and adjusting the learning environment. This makes it possible to provide the optimal learning method and environment according to the individual needs of each student, maximizing the learning effect.

[1508] "Past exam question generation AI" is an artificial intelligence technology that analyzes past exam questions and automatically generates practice questions tailored to the educational institution you are aiming for.

[1509] "Educational institutions" are institutions that provide higher education, such as universities and vocational schools.

[1510] An "individual curriculum" is a study plan customized to each student's learning style and progress.

[1511] "Progress analysis" is the process of assessing a student's learning progress in real time and providing appropriate feedback.

[1512] A "learning style assessment" is a diagnostic tool used to evaluate a test-taker's learning methods and level of understanding and identify the most suitable learning style.

[1513] "Optimal teaching materials" are study materials and problem sets that are best suited to the test-taker's learning style and level of understanding.

[1514] "Emotion recognition" is a technology that analyzes data such as a test-taker's facial expressions and voice to identify their current emotional state.

[1515] "Adjusting the learning environment" is the process of optimizing the learning environment, such as music and lighting, according to the test-taker's emotional state.

[1516] MODE FOR CARRYING OUT THE INVENTION

[1517] This invention is a system for maximizing the learning effect of test-takers, and includes AI for generating past exam questions, diagnosing learning styles, recognizing emotions, and adjusting the learning environment. Specific embodiments of this system are described below.

[1518] Hardware and software used

[1519] Hardware: Servers, devices (PCs, tablets, smartphones)

[1520] Software: Generative AI models (e.g., GPT-4), emotion recognition engines (e.g., Affectiva), learning management systems (LMS)

[1521] System Overview

[1522] This system provides optimal learning methods and environments according to the student's learning style and emotional state. Specifically, it has the following functions:

[1523] 1. Past exam question generation AI: The server analyzes past exam questions and automatically generates practice questions tailored to the educational institution the student is aiming for.

[1524] 2. Learning style diagnosis: The user takes a learning style diagnosis test using their device, and the server analyzes the diagnosis results using the generated AI model.

[1525] 3. Providing optimal learning materials: The server selects the optimal learning materials based on the diagnostic results and delivers them to the device.

[1526] 4. Emotion recognition: The device uses a camera and microphone to collect the user's facial expressions and voice, and the server analyzes them using an emotion recognition engine.

[1527] 5. Adjusting the learning environment: The server generates instructions to adjust the learning environment based on the user's emotional state, and the device adjusts the environment according to those instructions.

[1528] Specific examples

[1529] For visual learners:

[1530] The user takes a learning style diagnostic test on the device and is diagnosed as a "visual learner."

[1531] The server selects educational materials for visual learners (e.g., infographics, videos) and delivers them to the device.

[1532] If a user feels impatient while studying, the device will capture their facial expression with a camera, and the server will use an emotion recognition engine to analyze the "impatience."

[1533] The server sends an instruction to the terminal to "play quiet music," and the terminal plays quiet classical music.

[1534] If you're lethargic:

[1535] If the user is recognized as being lethargic, the device will capture their facial expression with a camera, and the server will analyze the "lethargy" using an emotion recognition engine.

[1536] The server sends an instruction to the terminal to "provide bright lights and uplifting music," and the terminal brightens the lights and plays uplifting music.

[1537] Prompt Sentence Examples

[1538] "Provide materials that are best suited to students with visual learning styles."

[1539] "Please suggest a suitable learning environment for users who are feeling impatient."

[1540] "How can we invigorate learning environments for disengaged users?"

[1541] The above is an embodiment of the present invention. This system provides optimal learning methods and environments tailored to the individual needs of test-takers, maximizing learning effectiveness. The flow of the specific processing in the third embodiment will be explained with reference to FIG. 21.

[1542] Program processing flow

[1543] Step 1: Assess your user's learning style

[1544] Input: The user starts the learning style assessment test on their device.

[1545] How it works: A user clicks a button on their device to start a "Learning Styles Test." The device then presents the user with a series of questions, and the user enters their answers.

[1546] Data processing: The device collects the user's answers and sends them to the server, which then analyzes the answers using a generative AI model to diagnose the user's learning style.

[1547] Output: The server sends the diagnostic results to the device and displays something like "You are a visual learner" to the user.

[1548] Step 2: Deliver learning content

[1549] Input: The server receives the user's learning style assessment results.

[1550] How it works: The server selects educational materials for visual learners (e.g., infographics, videos). The server then sends the selected educational materials to the device.

[1551] Data processing: The server selects the most suitable learning materials based on the learning style and delivers them to the device.

[1552] Output: The device displays the learning material to the user, and the user begins learning.

[1553] Step 3: Recognizing user emotions

[1554] Input: The device uses the camera and microphone to collect the user's facial expressions and voice.

[1555] How it works: The device uses a camera to capture the user's facial expressions and a microphone to record their voice. The device then sends the collected data to a server.

[1556] Data processing: The server analyzes the user's emotions using an emotion recognition engine.

[1557] Output: The server sends the analysis results to the terminal and displays a message such as "You are feeling impatient" to the user.

[1558] Step 4: Adjust your learning environment

[1559] Input: The server receives the user's emotional state.

[1560] Operation: The server generates an instruction to "play quiet music for users who are feeling impatient." The server sends the instruction to the terminal.

[1561] Data processing: The server generates instructions to adjust the learning environment based on the user's emotional state.

[1562] Output: The device plays quiet classical music to create a calming learning environment for the user.

[1563] The above is a concrete explanation of the program processing of this system.

[1564] (Application example 3)

[1565] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1566] Conventional learning systems do not fully consider the individual needs and emotional states of test takers, which means that learning effectiveness is not maximized. Furthermore, in factories, there is a lack of means to recognize the emotions and states of workers in real time and optimize the work environment based on that, which leads to issues such as reduced work efficiency and safety. To solve these issues, a system is needed that recognizes the emotions and states of test takers and workers in real time and provides an optimal environment based on that information.

[1567] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1568] In this invention, the server includes: a means for utilizing a past exam question generation AI to provide preparation tailored to the university the candidate is aiming for; a means for automatically generating questions tailored to the trends and level of each university; a means for integrating individual curricula and progress analysis; a means for recognizing the emotions and state of workers in real time and optimizing the work environment based on the emotions; a means for analyzing emotions from the worker's facial expressions and tone of voice using an emotion recognition engine; a means for adjusting the work environment based on the emotion data using a data processing algorithm; and a means for adjusting lighting and music using a control system. This makes it possible to maximize the learning effect of test takers and improve the work efficiency and safety of workers.

[1569] "Past exam question generation AI" is an artificial intelligence that automatically generates practice questions tailored to the university you are aiming for based on past exam questions.

[1570] "Means for providing measures" are methods or devices for providing students with study plans and study materials tailored to the university they are aiming for.

[1571] "Means for automatically generating questions" refers to a method or device for automatically creating questions that are in line with the trends and level of each university.

[1572] "Means for integrating individualized curriculum and progress analysis" refers to methods and devices for analyzing a candidate's learning progress and creating and integrating an individualized learning plan based on that analysis.

[1573] "Means for recognizing a worker's emotions and state in real time and optimizing the work environment based on that" refers to a method or device for detecting a worker's emotions and physical state in real time and adjusting the work environment accordingly.

[1574] An "emotion recognition engine" is software or hardware that analyzes emotions from a worker's facial expressions and tone of voice.

[1575] The "data processing algorithm" is a computational method for generating instructions to optimize the work environment based on data obtained from the emotion recognition engine.

[1576] A "control system" is the hardware and software that controls the lighting and music.

[1577] The embodiments of the present invention will be described in detail below.

[1578] System Overview

[1579] The system is designed to maximize the learning effect of test takers and improve the work efficiency and safety of factory workers. It consists of multiple components, including past exam question generation AI, an emotion recognition engine, a data processing algorithm, and a control system.

[1580] Hardware and software used

[1581] Camera: Captures the worker's facial expressions in real time.

[1582] Microphone: Analyzes the tone and volume of a worker's voice.

[1583] Speaker: Outputs music and voice instructions.

[1584] Lighting system: Adjust the brightness and color of the lights.

[1585] Emotion recognition engine: Analyzes emotions from the worker's facial expressions and tone of voice. Specifically, it uses a general emotion recognition API.

[1586] Data processing algorithm: Generates instructions to optimize the work environment based on data obtained from the emotion recognition engine.

[1587] Control system: A control program for adjusting lighting and music. Uses a microcontroller such as Arduino or Raspberry Pi.

[1588] Program processing explanation

[1589] 1. Cameras and microphones capture workers' facial expressions and voices:

[1590] A camera captures the worker's face in real time, and a microphone collects their voice.

[1591] 2. Emotion recognition engine analyzes the data:

[1592] An emotion recognition engine is used to recognize emotions from the worker's facial expressions.

[1593] Analyze emotions from tone of voice.

[1594] 3. Data processing algorithms generate the optimal environment:

[1595] Based on data obtained from the emotion recognition engine, it is determined whether the worker is feeling fatigued or stressed.

[1596] Choose some relaxing music and play it through the speakers.

[1597] Adjust your lighting system to a warmer tone.

[1598] 4. The control system regulates the environment:

[1599] Use Arduino or Raspberry Pi to control lighting color and music playback.

[1600] Specific examples

[1601] Example prompts to input to the generative AI model

[1602] Analyze workers' facial expressions and tone of voice, and if they appear tired or stressed, play relaxing music and adjust the lighting to warmer colors.

[1603] In this way, the system can maximize the learning effect of test takers and improve the work efficiency and safety of factory workers.

[1604] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1605] Step 1:

[1606] The server uses a camera and microphone to capture the worker's facial expressions and voice in real time. The input is the worker's facial video and voice audio data, and the output is to send this data to an emotion recognition engine. Specifically, the camera captures the worker's face and the microphone collects their voice.

[1607] Step 2:

[1608] The server uses an emotion recognition engine to analyze the captured facial and voice data. The input is the video and audio data obtained in step 1, and the output is the worker's emotional state (e.g., fatigue, stress, relaxation). Specifically, the emotion recognition engine analyzes facial expressions from the video data and tone of voice from the audio data.

[1609] Step 3:

[1610] The server uses a data processing algorithm to generate instructions for optimizing the work environment based on the emotional state data obtained from the emotion recognition engine. The input is the emotional state data obtained in step 2, and the output is the optimal work environment settings (e.g., music selection, lighting adjustment). Specifically, the data processing algorithm calculates the optimal environment settings according to the emotional state.

[1611] Step 4:

[1612] The server uses a control system to adjust the work environment based on the generated instructions. The input is the environmental setting data obtained in step 3, and the output is the actual change to the work environment (e.g., playing music, adjusting the color and brightness of the lighting). Specific actions include the control system playing relaxing music from the speakers and adjusting the lighting system to a warmer color.

[1613] Step 5:

[1614] The server again captures the state of the work environment after the change using a camera and microphone and sends it to the emotion recognition engine. The input is the video of the worker's face after the change and audio data of his / her voice, and the output is data for analyzing the emotional state again. Specifically, the camera and microphone capture the worker's state again and send it to the emotion recognition engine.

[1615] Step 6:

[1616] The server again uses the emotion recognition engine to analyze the impact of the changed work environment on the worker's emotional state. The input is the video and audio data obtained in step 5, and the output is the changed emotional state data. Specifically, the emotion recognition engine again analyzes facial expressions from the video data and tone of voice from the audio data.

[1617] Step 7:

[1618] The server adjusts the work environment again as necessary based on the changed emotional state data. The input is the emotional state data obtained in step 6, and the output is the optimal work environment settings again. Specifically, the data processing algorithm calculates the optimal environment settings again according to the emotional state, and the control system makes the necessary adjustments.

[1619] 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.

[1620] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1621] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1622] 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.

[1623] [Third embodiment]

[1624] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1625] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1626] 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).

[1627] 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.

[1628] 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.

[1629] 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).

[1630] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1631] 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.

[1632] 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.

[1633] 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.

[1634] 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.

[1635] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1636] "Example 1"

[1637] The present invention is an exam preparation system that utilizes AI to generate past exam questions. This system provides preparation tailored to the university of your choice. Specifically, it is equipped with AI that automatically generates questions tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, this system will automatically generate long-form English questions tailored to University A.

[1638] "Example 2"

[1639] Furthermore, this embodiment of the present invention has the function of integrating individualized curriculum and progress analysis. This allows students to manage their learning progress in a centralized manner, providing them with a chance to pass the entrance exam for their desired university with minimal study. For example, if a student has weaknesses in a particular area of ​​mathematics, this system can provide an individualized curriculum that focuses on that area.

[1640] "Example 3"

[1641] Furthermore, this embodiment of the present invention has the function of accurately grasping the needs of test takers and maximizing the effectiveness of learning by utilizing innovative technology. This allows test takers to be provided with the optimal learning method that suits their learning style and level of understanding, helping them realize their dream of passing the school of their choice. For example, if a test taker is good at visual learning, this system will provide visual learning materials and questions.

[1642] The processing flow of each embodiment will be described below.

[1643] "Example 1"

[1644] Step 1: The student enters the university they are aiming for into the system.

[1645] Step 2: The system uses AI to generate past exam questions and automatically generate questions that are tailored to the trends and level of each university. For example, if University A places emphasis on long-form English questions, the system will automatically generate long-form English questions for University A.

[1646] Step 3: The generated questions are provided to test takers and used for study.

[1647] "Example 2"

[1648] Step 1: Candidates enter their learning progress into the system.

[1649] Step 2: The system generates a personalized curriculum based on the learning progress entered. For example, if a student has weaknesses in a particular area of ​​mathematics, the system will provide a personalized curriculum focused on that area.

[1650] Step 3: The generated individual curriculum is provided to the student and used for study.

[1651] "Example 3"

[1652] Step 1: The candidate enters their learning style and level of understanding into the system.

[1653] Step 2: The system will provide the most suitable learning method based on the input information. For example, if the test-taker is good at visual learning, the system will provide visual learning materials and questions.

[1654] Step 3: The provided learning methods are provided to the candidate and used for studying.

[1655] Example 1

[1656] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1657] With conventional test preparation systems, it was difficult to efficiently generate questions that matched the trends of specific educational institutions, making it difficult to tailor preparation to suit the educational institution that test takers were aiming for. Furthermore, they lacked functionality to integrate individualized curricula and progress analysis, making it impossible to maximize test takers' learning effectiveness. Furthermore, there was a need for a method that would not be limited by data from the past few years and would provide test takers with a chance of passing their desired educational institution with minimal study.

[1658] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for the user to select an educational institution to which the user aspires, a means for the server to acquire trend data for the selected educational institution, a means for the server to input a prompt sentence to the generative AI model based on the trend data acquired by the server, a means for the generative AI model to generate questions based on the prompt sentence, a means for the server to provide the generated questions to the user, and a means for integrating an individual curriculum and progress analysis. This enables the user to efficiently study preparation questions tailored to the educational institution to which the user aspires.

[1659] "User" refers to an individual who uses the system to study practice questions tailored to the educational institution they are aiming for.

[1660] "Server" refers to a computer system that processes data in response to user requests, generates questions using a generative AI model, and provides them to users.

[1661] "Educational Institution" refers to a particular school, university, or other learning institution that a user is pursuing.

[1662] "Trend data" refers to information about past entrance examination questions and question trends of a particular educational institution.

[1663] A "generative AI model" refers to an artificial intelligence model that automatically generates questions tailored to a specific educational institution based on a prompt.

[1664] A "prompt" refers to text that provides specific instructions for generating questions to a generative AI model.

[1665] "Individualized curriculum" refers to a customized learning plan based on a user's learning progress and goals.

[1666] "Progress analysis" refers to the process of evaluating a user's learning status and analyzing the effectiveness and progress of their learning.

[1667] "Problem" refers to a learning task that the user must solve, generated by a generative AI model.

[1668] This invention is an exam preparation system that utilizes past exam question generation AI, and aims to enable users to efficiently study exam questions tailored to the educational institution they are aiming for. This system involves a series of processes in which the user selects the educational institution they are aiming for, a server obtains trend data for the selected educational institution, inputs prompts into a generative AI model to generate questions, and provides the generated questions to the user.

[1669] Hardware and software used

[1670] Server: Database Management System (DBMS), generative AI model, HTTP server

[1671] Device: Web browser or dedicated application

[1672] User: The device used to access the system (PC, tablet, smartphone, etc.)

[1673] Data processing and calculation

[1674] 1. The user selects the educational institution they wish to attend

[1675] A user logs in to the system and selects the educational institution they are interested in. For example, to select "University A," the user selects "University A" from the drop-down menu and clicks the "Select" button.

[1676] 2. The server retrieves the institution's trend data.

[1677] The server retrieves data about past entrance exam questions and question trends for the educational institution selected by the user from the database. For example, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'University A'" to extract the required data.

[1678] 3. The server inputs a prompt to the generative AI model.

[1679] The server inputs a prompt to the generative AI model based on the acquired trend data. The prompt is text that gives the generative AI model specific instructions for generating questions. For example, it generates a prompt such as "Please generate a long-answer English question for University A."

[1680] 4. Generative AI models generate problems

[1681] Based on the prompt, the generative AI model generates questions that are in line with the trends of each educational institution. The generative AI model uses natural language processing technology to analyze the prompt and generate appropriate questions. For example, it generates long-form English questions for University A.

[1682] 5. The server provides the generated questions to the user.

[1683] The server sends the generated questions to the user's device so that the user can solve them. The server also sends the generated questions to the user's device as an HTTP response, which is then displayed in the user's browser or application. For example, a long-form English question for University A is displayed on the user's device.

[1684] Examples of specific examples and prompts

[1685] Specific examples

[1686] If the user selects "University B," the server retrieves past math problem data from University B and inputs the prompt "Please generate math problems for University B" into the generative AI model. The generative AI model generates math problems for University B, and the server provides them to the user.

[1687] Prompt Sentence Examples

[1688] "Generate long-form English questions for University A."

[1689] "Generate math problems for University B"

[1690] "Generate physics problems from University C"

[1691] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[1692] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1693] Step 1:

[1694] Users select the educational institution they wish to pursue

[1695] A user logs into the system and selects the educational institution of interest. Specifically, the user selects the educational institution using a drop-down menu or search function and clicks the "Select" button. The input is the name of the educational institution selected by the user, and the output is the name of the selected educational institution being sent to the server.

[1696] Step 2:

[1697] The server retrieves the institution's trend data.

[1698] The server retrieves data on past entrance exam questions and question trends for the educational institution selected by the user from the database. Specifically, the server executes the SQL query "SELECT FROM university_data WHERE university_name = 'selected educational institution'" to extract the required data. The input is the name of the selected educational institution, and the output is the trend data for that educational institution.

[1699] Step 3:

[1700] The server inputs a prompt to the generative AI model.

[1701] The server inputs a prompt to the generative AI model based on the acquired trend data. Specifically, the server generates a prompt such as "Please generate questions for a specific subject at the selected educational institution" and sends an HTTP POST request to the API endpoint of the generative AI model. The input is the trend data and the prompt, and the output is the prompt sent to the generative AI model.

[1702] Step 4:

[1703] Generative AI models generate problems

[1704] The generative AI model generates questions based on the prompt sentence, tailored to the trends of each educational institution. Specifically, the generative AI model analyzes the prompt sentence using natural language processing technology and generates appropriate questions. The input is the prompt sentence, and the output is the generated question.

[1705] Step 5:

[1706] The server provides the generated questions to the user.

[1707] The server sends the generated problem to the user's device so that the user can solve it. Specifically, the server sends the generated problem to the user's device as an HTTP response and displays it in the user's browser or application. The input is the generated problem, and the output is the problem displayed on the user's device.

[1708] In this way, users can efficiently study practice questions tailored to the educational institution they are aiming for.

[1709] (Application example 1)

[1710] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1711] Conventional exam preparation systems have difficulty efficiently generating questions that are in line with the question trends of specific educational institutions, and are unable to integrate curriculum and progress analysis tailored to the individual needs of test takers. Furthermore, there is a lack of systems that can be easily used on mobile devices such as smartphones, making it difficult for test takers to study efficiently. This has made it difficult to maximize the effectiveness of test takers' learning in order to pass the entrance exams for their desired schools.

[1712] 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.

[1713] In this invention, the server includes: a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest; a means for automatically generating questions tailored to the trends and level of each educational institution; a means for integrating individual curricula and progress analysis; a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user; and a means for displaying the generated questions on a smartphone. This enables test-takers to efficiently study questions tailored to the question trends of specific educational institutions, maximize their learning effectiveness through curricula and progress analysis tailored to their individual needs, and easily advance their studies to pass their desired schools.

[1714] "Past exam question generation AI" is an artificial intelligence technology that automatically generates new questions based on past exam questions.

[1715] "Target educational institution" refers to the specific school or university that the candidate is aiming to get into.

[1716] "Means of providing countermeasures" refers to methods of providing study methods and materials that will help students pass the entrance exams for the educational institutions they are aiming for.

[1717] "Trends and levels at each educational institution" refers to the characteristics and difficulty of the questions asked by each educational institution.

[1718] "Means for automatically generating questions" refers to a method for automatically creating test questions based on specific conditions using artificial intelligence.

[1719] "Individual curriculum" refers to a study plan tailored to each student's learning progress and goals.

[1720] "Progress analysis" is a method of assessing and analyzing a student's learning progress.

[1721] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[1722] "User-selected educational institutions and subjects" refers to the specific school or university that the candidate has chosen to study at, and the specific subjects that will be tested at that school or university.

[1723] "Means for displaying on a smartphone" refers to a method for displaying the generated test questions and learning content on a smartphone screen.

[1724] A system for implementing this invention includes a means for utilizing past exam question generation AI to provide strategies tailored to the educational institution of interest, a means for automatically generating questions that are in line with the trends and level of each educational institution, a means for integrating individual curriculums and progress analysis, a means for using a generative AI model to generate questions based on the educational institution and subjects selected by the user, and a means for displaying the generated questions on a smartphone.

[1725] Program processing explanation

[1726] Hardware used:

[1727] Smartphone

[1728] Software used:

[1729] OpenAI API

[1730] Python

[1731] Data processing and calculation:

[1732] 1. User input: Users input the educational institution and subject they wish to study through a smartphone application.

[1733] 2. Prompt generation: The server generates a prompt based on the information entered by the user. For example, it generates a prompt such as "Please generate a long-answer English question for University A."

[1734] 3. Request to AI model: Send the generated prompt sentence to the OpenAI API and have the generative AI model (GPT-3) generate a problem.

[1735] 4. Problem retrieval: The server receives the problem returned by the generative AI model and formats it appropriately.

[1736] 5. Display on smartphone: The formatted questions are displayed on a smartphone application.

[1737] Specific examples

[1738] For example, if a user selects "Long-form English questions from University A," the following prompt sentence will be sent to the generative AI model.

[1739] Example prompt sentence:

[1740] Please generate long-form English questions for University A.

[1741] Based on this prompt, the generative AI model generates a long-form English question that matches the question trends of University A and returns it to the server. The server receives the question and displays it on the smartphone application.

[1742] In this way, users can efficiently study questions that match the exam trends of the educational institution they are aiming for through their smartphones. This allows students to maximize their learning effectiveness through a curriculum tailored to their individual needs and progress analysis, making it easy to study for admission to their desired school.

[1743] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1744] Step 1:

[1745] Users launch the smartphone application and enter the educational institution and subject they wish to attend.

[1746] Input: Name of educational institution, subject name

[1747] Output: User input data (educational institution name, subject name)

[1748] Specific operation: The user enters the name of the educational institution and the name of the subject in the application's input form and presses the submit button.

[1749] Step 2:

[1750] The terminal transmits the user input data to the server.

[1751] Input: User-entered data (educational institution name, subject name)

[1752] Output: User-entered data sent to the server

[1753] Specific operation: The smartphone sends user input data to a server via the Internet.

[1754] Step 3:

[1755] The server generates a prompt sentence based on the received user input data.

[1756] Input: User-entered data (educational institution name, subject name)

[1757] Output: Generated prompt statement

[1758] Specific operation: The server generates a prompt such as "Please generate a long-answer English question for University A."

[1759] Step 4:

[1760] The server sends the generated prompt text to the OpenAI API and requests the generative AI model to generate a question.

[1761] Input: Generated prompt text

[1762] Output: The problem data returned by the generative AI model

[1763] Specific operation: The server sends a prompt to the OpenAI API, and the generative AI model (GPT-3) generates and returns a problem.

[1764] Step 5:

[1765] The server receives the problem data returned by the generative AI model and formats it appropriately.

[1766] Input: Problem data returned by the generative AI model

[1767] Output: Formatted problem data

[1768] Specific operation: The server analyzes the problem data received and converts it into a format that can be displayed on a smartphone.

[1769] Step 6:

[1770] The server sends the formatted question data to the terminal.

[1771] Input: Formatted question data

[1772] Output: Problem data sent to the terminal

[1773] Specific operation: The server sends the formatted problem data to the smartphone via the Internet.

[1774] Step 7:

[1775] The terminal displays the received question data to the user.

[1776] Input: Problem data sent to the terminal

[1777] Output: Problem data displayed on a smartphone screen

[1778] Specific operation: The smartphone displays the received problem data on the screen, allowing the user to solve the problem.

[1779] Example 2

[1780] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1781] With conventional learning support systems, it was difficult to accurately grasp each student's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, feedback on learning progress and curriculum updates were often done manually, making it difficult to provide efficient learning support. Furthermore, the system was limited in its ability to generate past exam questions and provide questions tailored to the trends of each university, failing to fully meet the needs of students.

[1782] 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: a means for a user to input learning progress and weaknesses; a means for a terminal to transmit the input data to the server; a means for the server to analyze the data using a generation AI model; a means for the server to generate an individual curriculum based on the analysis results; a means for the server to transmit the generated curriculum to the terminal and provide it to the user; a means for the user to periodically input learning progress and for the server to analyze progress data and update the curriculum; a means for integrating the individual curriculum and progress analysis; a means for utilizing past exam question generation AI to provide strategies tailored to the target university; a means for automatically generating questions tailored to the trends and level of each university; a means for providing a chance to pass the desired university with minimal study; and a means for accurately grasping the needs of test takers, maximizing the effectiveness of learning using innovative technology, and helping them realize their dream of passing the desired school. This makes it possible to accurately grasp each test taker's individual learning progress and weaknesses and provide an optimal curriculum based on that. Furthermore, automatic feedback on learning progress and curriculum updates enable efficient learning support. In addition, the system has a wide range of features, including the generation of past exam questions and questions tailored to the trends of each university, allowing it to fully meet the needs of test takers.

[1783] "User" refers to a test-taker who uses the system to input their learning progress and weaknesses and receive an individualized curriculum.

[1784] "Terminal" refers to a device that allows a user to input their learning progress and weaknesses and communicate with the server.

[1785] "Server" refers to a computer system that receives data sent by users, analyzes the data using a generative AI model, and generates and provides an individual curriculum.

[1786] A "generative AI model" refers to an artificial intelligence model that analyzes a user's learning progress and weaknesses and generates an optimal individual curriculum.

[1787] "Study progress" refers to the progress and achievement of a user as they progress through their studies.

[1788] "Weakness" refers to a part in which the user has difficulty with a particular learning area or problem.

[1789] "Individualized curriculum" refers to a learning plan optimized for each individual user, generated based on the user's learning progress and weaknesses.

[1790] "Progress data" refers to data regarding the progress and achievement of learning that is periodically entered by the user.

[1791] "Past exam question generation AI" refers to an artificial intelligence model that automatically generates practice questions tailored to the university you are aiming for based on past exam questions.

[1792] "Trends and levels at each university" refers to the characteristics and difficulty of each university's exam questions.

[1793] "Feedback" refers to evaluation and advice on the user's learning progress.

[1794] "Curriculum update" refers to reevaluating an existing individual curriculum based on the user's progress data and changing the content as necessary.

[1795] The present invention is a system for managing the learning progress of test takers in an integrated manner and integrating individual curricula and progress analysis. Specific embodiments of this system will be described below.

[1796] System Overview

[1797] This system allows users (test takers) to input their learning progress and weaknesses, and provides an optimal individual curriculum based on that. The system is primarily composed of a server, a terminal, and a generative AI model.

[1798] Hardware and software used

[1799] Server: A high-performance computer system that receives and analyzes data, and generates and provides curriculum.

[1800] Device: A device used by a user (e.g., PC, tablet, smartphone) to input learning progress and weaknesses and display the curriculum.

[1801] Generative AI models: For example, advanced artificial intelligence models such as OpenAI's GPT-4 are used to analyze user data and generate optimal curriculum.

[1802] Program processing

[1803] 1. User learning data input:

[1804] The user uses the terminal to input their learning progress and weaknesses, for example, "I can't solve calculus problems."

[1805] 2. Sending data to the server:

[1806] The device sends the input learning data to the server. Specifically, the device sends the data to the server using an HTTP request.

[1807] 3. Data Analysis:

[1808] The server inputs the received data into the generative AI model, which analyzes the user's learning progress and weaknesses. For example, the generative AI model might output an analysis result such as "The user has a weakness in differential and integral calculus."

[1809] 4. Creating a personalized curriculum:

[1810] Based on the analysis results of the generative AI model, the server generates an individual curriculum that focuses on the user's weaknesses. For example, the server generates a curriculum that covers calculus from the basics to applications.

[1811] 5. Curriculum Delivery:

[1812] The server sends the generated individual curriculum to the terminal. The terminal displays the received curriculum to the user. For example, the terminal displays a "Basic Calculus Problem Set" to the user.

[1813] 6. Learning progress feedback and updates:

[1814] The user periodically inputs their learning progress using the terminal. The terminal then sends the input progress data to the server. The server analyzes the progress data and updates the curriculum as necessary. For example, the server generates a curriculum that advances to advanced problems, since the user has cleared basic problems.

[1815] Specific examples

[1816] The user uses a device to input "I can't solve the basic calculus problems." The device sends this data to the server. The server analyzes the data using a generative AI model and determines that "the user has weaknesses in the basics of calculus." The server generates a "curriculum covering calculus from basic to advanced" and sends it to the device. The device displays this curriculum to the user. The user studies according to the curriculum and periodically inputs their progress. The server analyzes the progress data, and if it determines that the user has cleared the basic problems, generates a curriculum to move on to advanced problems.

[1817] Prompt Sentence Examples

[1818] "Analyze the user's learning progress data and generate a personalized curriculum covering everything from the basics to advanced calculus."

[1819] In this way, a system is constructed in which the server, terminals, and users work together to support the learning of test takers.

[1820] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1821] Step 1:

[1822] The user uses the device to input their learning progress and weak points. Specifically, the user inputs "I can't solve calculus problems." The input data is information about the user's learning progress and weak points. The device temporarily stores this input data.

[1823] Step 2:

[1824] The terminal sends the input data to the server. Specifically, the terminal uses an HTTP request to send data about the user's learning progress and weaknesses to the server. The input is the user's learning progress data, and the output is data sent to the server.

[1825] Step 3:

[1826] The server inputs the received data into the generative AI model. Specifically, the server passes the user's learning progress data to the generative AI model for analysis. The input is the user's learning progress data, and the output is the analysis results by the generative AI model. The generative AI model identifies the user's weaknesses and outputs an analysis result such as "The user has a weakness in differential calculus."

[1827] Step 4:

[1828] The server generates an individual curriculum based on the analysis results of the generative AI model. Specifically, the server receives the analysis results and creates a curriculum that focuses on the user's weaknesses. The input is the analysis results of the generative AI model, and the output is an individual curriculum. For example...

Claims

1. A means for users to select the educational institution they wish to pursue; and means for the server to obtain trend data for a selected educational institution; A means for inputting a prompt sentence into a generative AI model based on trend data of the educational institution acquired by the server; A means for the generative AI model to generate a question based on the prompt sentence; means for the server to provide the generated questions to a user; A means to integrate individualized curriculum and progress analysis; Including, The means for integrating the individual curriculum and the progress analysis is a system that reviews the individual curriculum based on the results of scoring the questions provided to the user.

2. 2. The system of claim 1, further comprising a means for providing a chance of being accepted into a desired educational institution with minimal study, without being restricted by past years.

3. 2. The system of claim 1, further comprising a means for accurately grasping the needs of examinees, maximizing the effectiveness of their learning by utilizing innovative technology, and helping them realize their dream of being accepted into their desired educational institution.

Images