system

Abstract

Provide a system. A method for automatically generating test questions for a specific educational institution; a means for customizing a learning curriculum based on user profile information; A means for analyzing the user's learning progress data and providing the results; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, competition for university entrance exams has intensified, creating a need for personalized study plans. However, current learning platforms often fail to fully address users' individual needs, preventing students from maximizing their learning outcomes. Furthermore, study methods that rely solely on past exam questions are unable to keep up with the latest exam trends, making the shortest path to success unclear. Therefore, there is a need for a system that can generate questions and customize learning curricula based on each user's desired school, academic ability, and interests, while also accurately analyzing and providing information on their learning progress. [Means for solving the problem]

[0005] The present invention is a system that includes a means for automatically generating test questions tailored to specific educational institutions, a means for customizing a learning curriculum based on the user's profile information, and a means for analyzing the user's learning progress data and providing the results. Specifically, the system uses an external API to automatically generate questions tailored to the desired school and subject, and tailors the individual curriculum based on the user's areas of interest and past academic performance data. The system also periodically analyzes the user's learning progress and visualizes and optimizes learning effectiveness based on statistical data. This allows users to study effectively and quickly pass their desired school.

[0006] "Specific educational institution" refers to a specific university, vocational school, or other educational institution to which the user aspires.

[0007] "Examination questions" refers to questions asked in entrance examinations for universities and other educational institutions.

[0008] "Automatic generation" refers to the process of generating information automatically without human intervention using a program or algorithm.

[0009] "User" refers to the test takers and learners who use this system.

[0010] "Profile Information" refers to information about a user, such as personal information, learning history, and areas of interest.

[0011] A "learning curriculum" refers to a systematic plan of the items and content that a user should learn.

[0012] "Customization" refers to being individually adjusted and optimized according to the needs and characteristics of the user.

[0013] "Study Progress Data" refers to data that shows the progress of a user's learning activities, test scores, etc.

[0014] "Analysis" refers to statistically analyzing collected data and extracting useful information based on the results.

[0015] "External API" refers to an application programming interface provided by a third party that is used by this system for automatic question generation.

[0016] "Statistical data" refers to numerical data used to visualize and analyze a user's learning progress.

[0017] The "shortest route" refers to the most efficient method or means for users to study in order to get into their desired school. [Brief explanation of the drawings]

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

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0039] This invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data and provides the results.

[0040] Automatic generation of exam questions

[0041] First, the server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server then sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the API and stores the returned results as a question set for the user.

[0042] Customized learning curriculum

[0043] The server then references the user's profile information and creates a learning curriculum based on that information. Taking into account the user's inputted areas of interest and past test scores, the server adds to or adjusts the standard curriculum. For example, a user with a strong interest in science might be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0044] Analysis of learning progress data

[0045] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0046] Providing feedback

[0047] Finally, the device provides the user with feedback from the server, including generated problem sets, customized learning curriculum, and progress analysis reports, allowing the user to efficiently plan their learning.

[0048] Specific examples

[0049] For example, if user "John Doe" wants to study physics at the University of Tokyo and wants questions of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics questions suitable for John Doe. Then, based on John Doe's profile information indicating his general interest in science, the server suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. Furthermore, the server analyzes John Doe's performance data from past mock exams and creates a progress report showing which areas he should focus on. This information is then displayed on the device, allowing John Doe to use it to create a study plan.

[0050] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user may enter their name as "John Doe" and apply to the Department of Physics at the University of Tokyo, with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0054] Step 2:

[0055] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0056] json

[0057] {

[0058] "name": "John Doe",

[0059] "university": "Tokyo University",

[0060] "subject": "Physics",

[0061] "difficulty_level": "medium",

[0062] "interest": "science",

[0063] "progress": [

[0064] {"subject": "math", "score": 85},

[0065] {"subject": "science", "score": 90}

[0066] ]

[0067] }

[0068] Step 3:

[0069] Based on the profile information received by the server, an external API is used to automatically generate exam questions corresponding to the desired university and subject. The server generates a prompt such as "Physics exam at the University of Tokyo, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0070] Step 4:

[0071] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum that includes "advanced physics" is generated.

[0072] Step 5:

[0073] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0074] Step 6:

[0075] The server sends the generated problem sets, customized learning curriculum, and progress analysis results to the device, providing this information as feedback to help users study more effectively.

[0076] Step 7:

[0077] The device displays this information to the user, who can then solve the generated problems, follow the curriculum, and check progress analysis results to optimize their own study plan.

[0078] For example, the information John Doe sees on his device includes a medium-difficulty problem set from the Department of Physics at the University of Tokyo, a science-focused curriculum, and statistical data such as "an average score of 85 in math and 90 in science." John Doe can use this information to create an efficient study plan.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional learning support systems do not adequately generate test questions or customize learning curricula to meet the needs of individual users, and they also lack effective analysis and feedback of learning progress. As a result, they are unable to provide an optimized learning experience for users, resulting in problems such as reduced learning efficiency and results.

[0082] 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.

[0083] In this invention, the server includes means for automatically generating test questions based on information entered by the user, means for customizing a learning curriculum based on the user's profile information, means for collecting and analyzing the user's learning progress data and providing the results, and means for the terminal to provide the user with feedback from the server. This makes it possible to generate test questions optimized for each user, provide a customized learning curriculum, and provide appropriate analysis of learning progress and effective feedback.

[0084] The "means for automatically generating exam questions" is a mechanism for generating exam questions using an external API based on the user's desired university, exam subjects, and desired level of difficulty.

[0085] "Means for customizing learning curriculum" refers to a mechanism that adjusts the learning curriculum based on the user's profile information (such as areas of interest and past grades) to provide the user with the most appropriate learning content.

[0086] "Means for collecting learning progress data" refers to a system for regularly collecting learning data, such as a user's daily study time, mock test scores, and level of understanding of specific subjects.

[0087] The "means for analyzing learning progress data" is a mechanism for statistically analyzing collected learning progress data and visualizing each user's learning progress.

[0088] The "feedback provision means" is a mechanism for providing users with the server-generated problem sets, customized learning curriculum, and progress analysis results.

[0089] A "prompt" is a document to be sent to an external API used to generate test questions, specifying a specific educational institution, subject, and difficulty level.

[0090] MODE FOR CARRYING OUT THE INVENTION

[0091] This invention is a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results. The specific configuration and operation of this system are described in detail below.

[0092] Hardware and software used

[0093] The system is primarily composed of a server and user terminals. The specific software uses a generative AI model with an external API. In particular, the OpenAI (registered trademark) API is used to generate test questions.

[0094] Automatic generation of exam questions

[0095] The server automatically generates test questions based on the user's desired university, exam subjects, and desired difficulty level. The server sends a predetermined prompt to an external API and retrieves test questions using a generative AI model. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the external API and stores the returned test questions in a database.

[0096] Specific prompt examples:

[0097] "Generate moderate difficulty questions for the University of Tokyo physics exam."

[0098] Customized learning curriculum

[0099] The server customizes the learning curriculum based on the user's profile information. This profile information includes the user's areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic physics and chemistry courses. The customized learning curriculum is stored in a database on the server.

[0100] Collection and analysis of learning progress data

[0101] The server periodically collects the user's learning progress data and performs statistical analysis. This data includes mock test scores, daily study time, and level of understanding of specific subjects. As a result of the analysis, the system suggests the best time to take the next mock test and areas to focus on for study. This makes it possible to visualize the user's learning status.

[0102] Providing feedback

[0103] The device receives feedback data from the server and displays it in an easy-to-understand manner to the user. The feedback includes the generated test question set, a customized learning curriculum, and progress analysis results. For example, on the device's feedback screen, the user can review the "generated physics question set" and view the "curriculum including advanced physics." The device also displays a progress report stating, "The next mock exam is next month, and the recommended subject is quantum mechanics."

[0104] This system configuration makes it possible to generate test questions optimized for each user, provide individually customized learning curricula, and provide highly accurate analysis of progress data and effective feedback.

[0105] By specifically implementing the invention based on the above aspects, it becomes possible to solve the problems that conventional learning support systems have had and to provide efficient and effective learning support.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Processing Steps

[0108] Step 1: Enter your user information

[0109] The user inputs information such as the university of choice, exam subjects, desired level of difficulty, areas of interest, and past academic results through the terminal.

[0110] Input: desired university (e.g., University of Tokyo), exam subject (e.g., physics), desired difficulty level (e.g., medium), area of ​​interest (e.g., general science), and past academic performance (e.g., 60 points on mock exams).

[0111] Output: This information is sent to the server and stored in a database.

[0112] Specific actions: Enter "University of Tokyo, Physics, Medium level, Interested in science, 60 points on mock exam" into the input form on the device and press the "Submit" button.

[0113] Step 2: Automatic generation of exam questions

[0114] Based on the information received in step 1, the server sends a prompt to the external API and generates test questions using the generative AI model.

[0115] Input: User-entered desired university, exam subjects, and desired difficulty level.

[0116] Data processing: The server uses this information to generate a prompt and sends it to the external API.

[0117] Output: The test questions returned from the external API are saved on the server.

[0118] Specific operation: The server sends a prompt message to the external API saying "Please generate medium-difficulty questions for the University of Tokyo physics exam" and saves the returned question data in the database.

[0119] Step 3: Customize your learning curriculum

[0120] The server customizes the learning curriculum based on the profile information received in step 1.

[0121] Input: User's interests and past learning achievements.

[0122] Data processing: The server makes the necessary adjustments to the standard curriculum.

[0123] Output: The customized learning curriculum is saved in the database.

[0124] Specific operation: The server adds the subject "Advanced Physics" based on the profile data, generates a curriculum including it, and saves it in the database.

[0125] Step 4: Collect and analyze learning progress data

[0126] The server periodically collects user learning progress data and performs statistical analysis.

[0127] Input: User's daily study time, mock test scores, and subject-specific comprehension.

[0128] Data processing: The server statistically analyzes the collected data.

[0129] Output: Progress data and analysis results for each user, such as when the next mock test is due and what areas to focus on.

[0130] Specific operation: The server collects "user's learning progress data (e.g., 2 hours of study per day, 80 points on mock exams)" and generates analysis results based on that data, such as "the next mock exam is next month, and the recommended subject is quantum mechanics."

[0131] Step 5: Provide feedback

[0132] The terminal receives the feedback data from the server and displays it to the user.

[0133] Input: Generated problem sets, customized learning curriculum, and progress analysis results provided by the server.

[0134] Output: These data are presented visually to the user.

[0135] Specific operation: The device's feedback screen displays the "generated physics problem set," allows users to view the "curriculum including advanced physics," and provides a progress report stating that "the next mock exam is next month and the recommended subject is quantum mechanics."

[0136] By following these steps, users can create an effective study plan based on their own learning progress.

[0137] (Application example 1)

[0138] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0139] Conventional learning support systems are limited to providing one-dimensional information when it comes to automatically generating test questions and customizing learning curricula, and are therefore not effective enough in improving users' learning efficiency. Furthermore, there is a lack of a way to provide users' learning progress data in a way that makes it easy to visually grasp it, making it difficult for users to effectively analyze and improve their self-learning progress.

[0140] 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.

[0141] In this invention, the server includes means for automatically generating test questions corresponding to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, and means for displaying the test questions, learning curriculum, and learning progress data in a virtual space, allowing the user to efficiently proceed with their learning plan. This allows the user to more interactively and efficiently manage their learning progress and adjust their learning plan through visual feedback in the virtual space.

[0142] A "specific educational institution" refers to a specific academic institution such as a university or high school, which provides learning content and examinations tailored to that institution.

[0143] "Means for automatically generating test questions" refers to technology that uses an external API to generate test questions based on predetermined prompts and provide them to users.

[0144] "User profile information" refers to personal information entered by the user, such as areas of interest and past academic performance data, and learning content is customized based on this information.

[0145] "Means for customizing learning curriculum" refers to technology that adds to or adjusts standard learning content based on a user's areas of interest and past performance data.

[0146] "Study progress data" refers to data based on a user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0147] "Virtual space" refers to a three-dimensional virtual environment created using computer technology in which users can interact with and learn.

[0148] "Display in virtual space" refers to a technology that uses virtual reality technology to display learning content and progress data in three dimensions, making it easier for users to visually grasp the information.

[0149] "Server" refers to the computer system that receives requests from users, generates test questions, customizes learning curriculum, and analyzes progress data.

[0150] The present invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data to provide the results. The system of the present invention is implemented by the following method.

[0151] First, the server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. To do this, the server uses an external API to generate test questions based on a predetermined prompt. Specifically, the server sends the prompt "medium difficulty physics exam at a specific university" to the external API and stores the returned results as a question set for the user.

[0152] The server then customizes the learning curriculum based on the user's profile information (e.g., areas of interest and past academic performance data). By referencing this profile information, the server can add to or adjust the standard curriculum. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0153] Furthermore, the server periodically collects and analyzes users' learning progress data (for example, mock test scores, daily study time, and level of understanding of specific subjects). The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on when to study.

[0154] Finally, the device provides the user with feedback from the server, including generated test question sets, customized learning curriculum, and progress analysis reports. This information is then visually displayed in a virtual space to help the user efficiently advance their learning plan. The display in the virtual space is achieved using virtual reality technology (e.g., a VR headset).

[0155] As an example, suppose the user enters the following prompt text:

[0156] "Generate medium difficulty questions for a specific university physics exam."

[0157] As a result, the server sends the generated test question set, customized learning curriculum, and progress analysis data to the terminal in response, and the user can proceed with their learning plan while visually checking this information in the virtual space.

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] The server receives user input: the user enters the desired educational institution, subject, and difficulty level, which gives the server input data for generating test questions.

[0161] Step 2:

[0162] The server sends a request to an external API. The server uses the acquired input data (e.g., "medium difficulty physics exam at a specific university") as a prompt and sends it to the external API. The API generates test questions based on the prompt and returns them to the server. The data processing performed here involves parsing the prompt and conveying it to the API in an appropriate format. As output, the server receives the generated test question set.

[0163] Step 3:

[0164] The server retrieves the user's profile information. It then references the user's areas of interest and past performance data to customize the learning curriculum. This generates a customized curriculum based on the profile information. Specifically, it retrieves the profile information from the database and adds or adjusts the standard curriculum based on that information. The output is a customized learning curriculum.

[0165] Step 4:

[0166] The server collects data on the user's learning progress. Data such as the user's daily study time, mock test scores, and level of understanding is collected and statistically analyzed. This generates data that visualizes each user's progress. Specifically, the progress data is retrieved from the database and analyzed using a machine learning algorithm. The output is a progress report.

[0167] Step 5:

[0168] The server sends the generated test question set, customized learning curriculum, and progress report to the user's device, which receives it and, if necessary, visually displays it in the virtual space. Specifically, the server converts the data into an appropriate format and sends it over the network to the user's device. The output is the information displayed on the user's device.

[0169] Step 6:

[0170] The device visually displays the data in a virtual space. The device displays the received learning content and progress data in three dimensions to help users efficiently advance their learning plans. Specifically, the device uses virtual reality technology such as a VR headset to display the received data in a visually easy-to-understand format.

[0171] 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.

[0172] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes user learning progress data and provides the results.

[0173] Automatic generation of exam questions

[0174] The server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam of a specific university, medium difficulty" to the API and saves the returned results as a question set for the user.

[0175] Customized learning curriculum

[0176] The server then references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted based on the user's inputted areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0177] Analysis of learning progress data

[0178] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0179] Emotion engine integration

[0180] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. Also, if it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0181] Providing feedback

[0182] Finally, the device provides the user with feedback from the server, including the generated problem set, the customized learning curriculum, the progress analysis report, and the curriculum adjusted by the emotion engine, allowing the user to efficiently advance their learning plan.

[0183] Specific examples

[0184] For example, if user "John Doe" wants to study physics at a particular university and wants problems of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics problems suitable for John Doe. Based on John Doe's profile information, which indicates his general interest in science, the server then suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. The server then analyzes John Doe's past mock exam performance data and creates a progress report showing which areas he should focus on.

[0185] In addition, the emotion engine analyzes John Doe's facial expressions and voice during his study session, and if it determines that he is feeling fatigued, the server adjusts the study curriculum to reduce the learning load. In this way, users can create an optimal study plan based on their emotional state.

[0186] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0187] The processing flow will be explained below.

[0188] Step 1:

[0189] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user might enter their name as "John Doe" and apply to the "Physics Department at a specific university," with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0190] Step 2:

[0191] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0192] json

[0193] {

[0194] "name": "John Doe",

[0195] "university": "Specific University",

[0196] "subject": "Physics",

[0197] "difficulty_level": "medium",

[0198] "interest": "science",

[0199] "progress": [

[0200] {"subject": "math", "score": 85},

[0201] {"subject": "science", "score": 90}

[0202] ]

[0203] }

[0204] Step 3:

[0205] Based on the profile information received, the server uses an external API to automatically generate exam questions for the desired university and subject. The server generates a prompt such as "Physics exam of a specific university, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0206] Step 4:

[0207] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum including "advanced physics" is generated.

[0208] Step 5:

[0209] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0210] Step 6:

[0211] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it will reduce the learning load, and if it determines that the user is highly motivated, it will increase the learning load.

[0212] Step 7:

[0213] The server sends the generated problem set, customized learning curriculum, progress analysis results, and curriculum adjusted by the emotion engine to the device, and provides this information as feedback to help users study more efficiently.

[0214] Step 8:

[0215] The device displays this information to the user. The user can solve the generated problems, study according to the curriculum, and check the progress analysis results and emotion-based adjustments to optimize their study plan. For example, the information John Doe checks on his device includes a "medium-difficulty problem set for a specific university's physics department," a science-focused curriculum, statistical data such as "an average math score of 85 and an average science score of 90," and the study load adjusted by the emotion engine. John Doe can use this information to create an efficient study plan.

[0216] Example 2

[0217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] In conventional educational systems, test question generation, learning curriculum customization, and learning progress data analysis are all performed separately, making it difficult to provide an optimized learning experience for each user. It is also difficult to adjust learning based on the user's emotional state, leading to some users losing motivation due to excessive learning load. To solve these issues, a system is needed that integrates these functions to provide an optimized learning experience for each user.

[0219] 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.

[0220] In this invention, the server includes means for automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for recognizing the user's emotional state and adjusting the learning curriculum based thereon, and means for providing this information to the user via the terminal, thereby providing a learning experience optimized for each user and enabling efficient and effective learning.

[0221] "Specific educational institution" means a specific school, higher education institution, or other educational facility that provides examination questions and learning curricula tailored to the educational objectives and needs of the institution.

[0222] A "means for automatically generating test questions" is a device or program that uses an algorithm or external API to automatically create specific test questions based on conditions entered by a user.

[0223] "Profile information" refers to information about a user, such as the user's areas of interest, past learning history, and academic performance data, and is data used to customize the learning curriculum.

[0224] A "means for customizing a learning curriculum" is a device or program that adjusts a standard learning curriculum based on user profile information and provides the user with an optimized learning plan.

[0225] "Study progress data" is a record of the user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0226] "Means for analyzing progress data" refers to a device or program that statistically analyzes a user's learning progress data, evaluates the user's current learning situation, and provides information that is useful for future learning plans.

[0227] "Means for recognizing emotional state" refers to a device or program that analyzes a user's facial expression, voice, or text data to determine the user's emotional state (e.g., fatigue, stress, motivation).

[0228] A "means for adjusting a curriculum" is a device or program that appropriately changes the content or workload of a learning curriculum based on the recognized emotional state of the user.

[0229] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet, that receives information from the server and provides it to the user.

[0230] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results.

[0231] Automatic generation of exam questions

[0232] The server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. Specifically, the server uses a generative AI model (e.g., ChatGPT (registered trademark)) to send a request to an external API. The request includes a specific prompt. For example, the server sends a request including the prompt, "Please generate medium-difficulty questions for a physics exam at a specific educational institution," and saves the returned questions as a problem set for the user.

[0233] Customized learning curriculum

[0234] The server then analyzes the user's profile information (interests and past academic performance data) and adjusts the standard learning curriculum to provide a customized curriculum. For example, a user interested in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects. This adjustment is made based on an algorithm, and the curriculum content automatically changes when certain conditions are met.

[0235] Collection and analysis of learning progress data

[0236] The server periodically collects and analyzes the user's learning progress data. This data includes the user's scores on mock exams, daily study time, and level of understanding of specific subjects. This data is analyzed using statistical methods, and the results are visualized as the user's individual learning progress. Specific analysis results include the recommended time for the next mock exam and areas to focus on.

[0237] Emotion engine integration

[0238] The server integrates an emotion engine that recognizes the user's emotional state and further adaptively adjusts the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state (fatigue, stress, motivation, etc.). For example, if the server determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. On the other hand, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0239] Providing feedback

[0240] Finally, the device provides the user with feedback from the server, including the generated problem set, a customized learning curriculum, a progress analysis report, and a curriculum adjusted by the emotion engine, allowing the user to efficiently plan their learning.

[0241] Specific examples

[0242] For example, if a user is applying to a specific physics department and wants questions of medium difficulty, the server first uses the generative AI model to generate questions by sending a prompt to the API saying, "Generate medium-difficulty questions for the physics exam at a specific educational institution." Based on the user's profile information, the server then suggests a curriculum that includes "advanced physics." The server then analyzes the user's performance data from past mock exams to create a progress report showing which areas to focus on.

[0243] In addition, the emotion engine analyzes the user's facial expressions and voice during the learning session. If it determines that the user is feeling fatigued, the server adjusts the learning curriculum and reduces the learning load. On the other hand, if the user is highly motivated, the learning load is increased. In this way, the user can create an optimal learning plan based on their emotional state. This system provides a learning experience optimized for each user and supports efficient learning.

[0244] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0245] Step 1: User Input

[0246] The user inputs the desired educational institution, subject, difficulty level, and profile information (areas of interest, past learning history, etc.) through the terminal.

[0247] Input: desired educational institution, subject, difficulty level, profile information

[0248] Output: User input data

[0249] The server receives this input data and passes it on to the next processing step.

[0250] Step 2: Automatic generation of exam questions

[0251] The server uses a generative AI model (e.g., ChatGPT) to send a request to an external API to automatically generate test questions.

[0252] Input: User-entered data (desired educational institution, subject, difficulty level)

[0253] Output: Auto-generated test questions

[0254] Specific operation: The server sends the prompt "Please generate medium difficulty questions for the physics exam of a specific educational institution" to an external API and stores the generated exam questions in the database.

[0255] Step 3: Customize your learning curriculum

[0256] The server customizes the learning curriculum based on the user's profile information.

[0257] Input: User-entered data (profile information)

[0258] Output: Customized learning curriculum

[0259] Specific operation: The server analyzes the user's areas of interest and past grades, adjusts the standard curriculum, and suggests a curriculum that includes "advanced physics."

[0260] Step 4: Collect and analyze learning progress data

[0261] The server periodically collects and analyzes the user's learning progress data.

[0262] Input: User's learning progress data (mock test scores, study time, level of understanding)

[0263] Output: Progress visualization and analysis results

[0264] How it works: The server collects mock test scores, study time, and understanding of specific subjects, and analyzes them using statistical methods. It then suggests the best time to take the next mock test and the areas to focus on.

[0265] Step 5: Emotional Engine Adjustment

[0266] The server uses an emotion engine to identify the user's emotional state and adjust the learning curriculum.

[0267] Input: User emotion data (facial expression, voice, text)

[0268] Output: Aligned learning curriculum

[0269] Specific operation: The server uses an emotion engine to analyze the user's facial expressions and voice to determine fatigue and stress. If the user is fatigued, the learning load is reduced, and if the user is highly motivated, the load is increased.

[0270] Step 6: Provide feedback

[0271] The device provides the user with feedback from the server.

[0272] Input: Feedback data from the server

[0273] Output: Information provided to the user (generated test question sets, customized curriculum, progress analysis report, adjusted curriculum)

[0274] Specific operation: The device displays the information received from the server to the user, allowing the user to plan an efficient study plan based on this information.

[0275] (Application example 2)

[0276] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0277] Conventional learning support systems were unable to grasp the progress and emotional state of individual learners in real time and provide optimal learning curricula accordingly. In particular, when learners felt fatigued or stressed, the curriculum was not adjusted to take this into account, resulting in a decline in learning efficiency. Furthermore, the lack of a means to visually and in real time provide learning content and progress made it difficult for learners to properly grasp their own learning situation.

[0278] 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 automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for analyzing the user's emotional state and adjusting the learning curriculum, and means for presenting the learning content and progress status on a display device in real time. This makes it possible to provide the optimal learning curriculum tailored to the learner's situation in real time, improving learning efficiency and reducing the learner's burden.

[0279] A "means for automatically generating exam questions" is a means for automatically generating exam questions for a particular educational institution based on information entered by a user and using an external API based on predetermined prompts.

[0280] "Means for customizing learning curriculum" refers to a means for dynamically adjusting and suggesting learning content that is optimal for each learner based on the user's profile information, areas of interest, and past performance data.

[0281] "Means for analyzing learning progress data and providing the results" refers to means for periodically collecting and analyzing users' learning progress data and providing visual progress status in real time as statistical analysis results.

[0282] The "means for analyzing the user's emotional state and adjusting the learning curriculum" refers to a means for analyzing the user's facial expressions and voice to recognize the emotional state, and dynamically adjusting the learning curriculum based on the results.

[0283] "Means for presenting learning content and progress status on a display device in real time" refers to means for visually presenting learning content and progress data to learners in real time using a display device such as smart glasses.

[0284] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data to provide the results. A display device such as smart glasses is also used to display learning content and progress in real time.

[0285] Automatic generation of exam questions

[0286] The server automatically generates exam questions based on the user's desired university, subject, and difficulty level. Specifically, the server sends a request to an external API and saves the generated exam questions as a question set for the user. This process uses a generative AI model (e.g., GPT-3 (registered trademark) / 4) and inputs a specified prompt. For example, by sending the prompt "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University," a medium-difficulty physics exam question is generated.

[0287] Customized learning curriculum

[0288] The server references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted taking into account the user's input areas of interest and past test scores. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0289] Analysis of learning progress data

[0290] The server periodically collects and analyzes the user's learning progress data, including the user's mock test scores, daily study time, and level of understanding of specific subjects. This data is statistically analyzed to visualize each user's progress. For example, it suggests the best time to take the next mock test and areas to focus on when to study.

[0291] Emotion engine integration

[0292] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine uses the smart glasses' camera and audio microphone to analyze the user's facial expressions and voice to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it adjusts the curriculum to reduce the learning load. If it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0293] Real-time feedback

[0294] The learning content and progress are displayed in real time on the smart glasses' display. This allows users to receive real-time feedback while studying, optimizing learning efficiency. Specific examples of messages that are displayed to users while studying include, "The best time to take the next practice exam is in three days," and "It would be best to focus on the electromagnetics section of physics right now."

[0295] Specific examples

[0296] For example, when a user wears smart glasses to study, the server functions as follows: First, the user enters information about the university and subjects they wish to study. The server uses this information to send prompts to an external API to generate exam questions. A customized learning curriculum is then created based on the user's profile information. During study, the user's emotional state is identified through the smart glasses' camera and microphone, and the server provides real-time feedback and adjusts the curriculum accordingly.

[0297] This allows users to create optimal study plans based on their emotional state and learning progress, enabling them to study efficiently toward achieving their goals.

[0298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0299] Step 1:

[0300] A user logs into the system and inputs the university of their choice, the subject, and the level of difficulty. This information is sent to the server. The input information is the university of their choice, the subject, and the level of difficulty. The server uses this information to create a prompt for generating exam questions.

[0301] Step 2:

[0302] The server sends a prompt to an external API and generates exam questions using a generative AI model (e.g., GPT-3 / 4). The input is the prompt, e.g., "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University." The server retrieves the exam question data returned by the external API.

[0303] Step 3:

[0304] The server stores the generated test questions as a test question set for the user. The stored data is divided into test question sets for each user.

[0305] Step 4:

[0306] The user enters profile information (interests and past test scores) and sends it to the server, which then obtains the basic data for customizing the user's learning curriculum.

[0307] Step 5:

[0308] The server creates a learning curriculum based on the user's profile information. The input data is areas of interest and past grades, and the output is a customized learning curriculum. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics."

[0309] Step 6:

[0310] The server periodically collects and statistically analyzes users' learning progress data. Input data includes mock test scores and daily study time, and a progress report is generated as output. The server visualizes each user's progress and suggests the best time to take the next mock test and the areas they should study.

[0311] Step 7:

[0312] The user begins learning using the smart glasses. The user's facial expressions and voice data are sent to the server via the smart glasses' camera and audio microphone.

[0313] Step 8:

[0314] The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. The input data is facial image data and voice data, and the output classifies the user's emotional state (e.g., fatigue, stress, high motivation, etc.).

[0315] Step 9:

[0316] The server adjusts the learning curriculum based on the user's emotional state. For example, if the server determines that the user is feeling fatigued, it adjusts the curriculum to reduce the learning load. Conversely, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0317] Step 10:

[0318] The server presents the adjusted learning curriculum in real time on the smart glasses' display. This allows users to check their learning content and progress in real time as they study. For example, messages such as "The best time to take the next mock exam is in three days" or "You should currently focus on the electromagnetics section of physics" are displayed.

[0319] 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.

[0320] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0321] 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.

[0322] [Second embodiment]

[0323] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0324] 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.

[0325] 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).

[0326] 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.

[0327] 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.

[0328] 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).

[0329] 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.

[0330] 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.

[0331] 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.

[0332] 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.

[0333] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0334] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0335] This invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data and provides the results.

[0336] Automatic generation of exam questions

[0337] First, the server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server then sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the API and stores the returned results as a question set for the user.

[0338] Customized learning curriculum

[0339] The server then references the user's profile information and creates a learning curriculum based on that information. Taking into account the user's inputted areas of interest and past test scores, the server adds to or adjusts the standard curriculum. For example, a user with a strong interest in science might be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0340] Analysis of learning progress data

[0341] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0342] Providing feedback

[0343] Finally, the device provides the user with feedback from the server, including generated problem sets, customized learning curriculum, and progress analysis reports, allowing the user to efficiently plan their learning.

[0344] Specific examples

[0345] For example, if user "John Doe" wants to study physics at the University of Tokyo and wants questions of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics questions suitable for John Doe. Then, based on John Doe's profile information indicating his general interest in science, the server suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. Furthermore, the server analyzes John Doe's performance data from past mock exams and creates a progress report showing which areas he should focus on. This information is then displayed on the device, allowing John Doe to use it to create a study plan.

[0346] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0347] The processing flow will be explained below.

[0348] Step 1:

[0349] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user may enter their name as "John Doe" and apply to the Department of Physics at the University of Tokyo, with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0350] Step 2:

[0351] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0352] json

[0353] {

[0354] "name": "John Doe",

[0355] "university": "Tokyo University",

[0356] "subject": "Physics",

[0357] "difficulty_level": "medium",

[0358] "interest": "science",

[0359] "progress": [

[0360] {"subject": "math", "score": 85},

[0361] {"subject": "science", "score": 90}

[0362] ]

[0363] }

[0364] Step 3:

[0365] Based on the profile information received by the server, an external API is used to automatically generate exam questions corresponding to the desired university and subject. The server generates a prompt such as "Physics exam at the University of Tokyo, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0366] Step 4:

[0367] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum that includes "advanced physics" is generated.

[0368] Step 5:

[0369] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0370] Step 6:

[0371] The server sends the generated problem sets, customized learning curriculum, and progress analysis results to the device, providing this information as feedback to help users study more effectively.

[0372] Step 7:

[0373] The device displays this information to the user, who can then solve the generated problems, follow the curriculum, and check progress analysis results to optimize their own study plan.

[0374] For example, the information John Doe sees on his device includes a medium-difficulty problem set from the Department of Physics at the University of Tokyo, a science-focused curriculum, and statistical data such as "an average score of 85 in math and 90 in science." John Doe can use this information to create an efficient study plan.

[0375] Example 1

[0376] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0377] Conventional learning support systems do not adequately generate test questions or customize learning curricula to meet the needs of individual users, and they also lack effective analysis and feedback of learning progress. As a result, they are unable to provide an optimized learning experience for users, resulting in problems such as reduced learning efficiency and results.

[0378] 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.

[0379] In this invention, the server includes means for automatically generating test questions based on information entered by the user, means for customizing a learning curriculum based on the user's profile information, means for collecting and analyzing the user's learning progress data and providing the results, and means for the terminal to provide the user with feedback from the server. This makes it possible to generate test questions optimized for each user, provide a customized learning curriculum, and provide appropriate analysis of learning progress and effective feedback.

[0380] The "means for automatically generating exam questions" is a mechanism for generating exam questions using an external API based on the user's desired university, exam subjects, and desired level of difficulty.

[0381] "Means for customizing learning curriculum" refers to a mechanism that adjusts the learning curriculum based on the user's profile information (such as areas of interest and past grades) to provide the user with the most appropriate learning content.

[0382] "Means for collecting learning progress data" refers to a system for regularly collecting learning data, such as a user's daily study time, mock test scores, and level of understanding of specific subjects.

[0383] The "means for analyzing learning progress data" is a mechanism for statistically analyzing collected learning progress data and visualizing each user's learning progress.

[0384] The "feedback provision means" is a mechanism for providing users with the server-generated problem sets, customized learning curriculum, and progress analysis results.

[0385] A "prompt" is a document to be sent to an external API used to generate test questions, specifying a specific educational institution, subject, and difficulty level.

[0386] MODE FOR CARRYING OUT THE INVENTION

[0387] This invention is a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results. The specific configuration and operation of this system are described in detail below.

[0388] Hardware and software used

[0389] The system is primarily composed of a server and user devices. The specific software uses a generative AI model with external APIs. In particular, OpenAI's API is used to generate test questions.

[0390] Automatic generation of exam questions

[0391] The server automatically generates test questions based on the user's desired university, exam subjects, and desired difficulty level. The server sends a predetermined prompt to an external API and retrieves test questions using a generative AI model. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the external API and stores the returned test questions in a database.

[0392] Specific prompt examples:

[0393] "Generate moderate difficulty questions for the University of Tokyo physics exam."

[0394] Customized learning curriculum

[0395] The server customizes the learning curriculum based on the user's profile information. This profile information includes the user's areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic physics and chemistry courses. The customized learning curriculum is stored in a database on the server.

[0396] Collection and analysis of learning progress data

[0397] The server periodically collects the user's learning progress data and performs statistical analysis. This data includes mock test scores, daily study time, and level of understanding of specific subjects. As a result of the analysis, the system suggests the best time to take the next mock test and areas to focus on for study. This makes it possible to visualize the user's learning status.

[0398] Providing feedback

[0399] The device receives feedback data from the server and displays it in an easy-to-understand manner to the user. The feedback includes the generated test question set, a customized learning curriculum, and progress analysis results. For example, on the device's feedback screen, the user can review the "generated physics question set" and view the "curriculum including advanced physics." The device also displays a progress report stating, "The next mock exam is next month, and the recommended subject is quantum mechanics."

[0400] This system configuration makes it possible to generate test questions optimized for each user, provide individually customized learning curricula, and provide highly accurate analysis of progress data and effective feedback.

[0401] By specifically implementing the invention based on the above aspects, it becomes possible to solve the problems that conventional learning support systems have had and to provide efficient and effective learning support.

[0402] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0403] Processing Steps

[0404] Step 1: Enter your user information

[0405] The user inputs information such as the university of choice, exam subjects, desired level of difficulty, areas of interest, and past academic results through the terminal.

[0406] Input: desired university (e.g., University of Tokyo), exam subject (e.g., physics), desired difficulty level (e.g., medium), area of ​​interest (e.g., general science), and past academic performance (e.g., 60 points on mock exams).

[0407] Output: This information is sent to the server and stored in a database.

[0408] Specific actions: Enter "University of Tokyo, Physics, Medium level, Interested in science, 60 points on mock exam" into the input form on the device and press the "Submit" button.

[0409] Step 2: Automatic generation of exam questions

[0410] Based on the information received in step 1, the server sends a prompt to the external API and generates test questions using the generative AI model.

[0411] Input: User-entered desired university, exam subjects, and desired difficulty level.

[0412] Data processing: The server uses this information to generate a prompt and sends it to the external API.

[0413] Output: The test questions returned from the external API are saved on the server.

[0414] Specific operation: The server sends a prompt message to the external API saying "Please generate medium-difficulty questions for the University of Tokyo physics exam" and saves the returned question data in the database.

[0415] Step 3: Customize your learning curriculum

[0416] The server customizes the learning curriculum based on the profile information received in step 1.

[0417] Input: User's interests and past learning achievements.

[0418] Data processing: The server makes the necessary adjustments to the standard curriculum.

[0419] Output: The customized learning curriculum is saved in the database.

[0420] Specific operation: The server adds the subject "Advanced Physics" based on the profile data, generates a curriculum including it, and saves it in the database.

[0421] Step 4: Collect and analyze learning progress data

[0422] The server periodically collects user learning progress data and performs statistical analysis.

[0423] Input: User's daily study time, mock test scores, and subject-specific comprehension.

[0424] Data processing: The server statistically analyzes the collected data.

[0425] Output: Progress data and analysis results for each user, such as when the next mock test is due and what areas to focus on.

[0426] Specific operation: The server collects "user's learning progress data (e.g., 2 hours of study per day, 80 points on mock exams)" and generates analysis results based on that data, such as "the next mock exam is next month, and the recommended subject is quantum mechanics."

[0427] Step 5: Provide feedback

[0428] The terminal receives the feedback data from the server and displays it to the user.

[0429] Input: Generated problem sets, customized learning curriculum, and progress analysis results provided by the server.

[0430] Output: These data are presented visually to the user.

[0431] Specific operation: The device's feedback screen displays the "generated physics problem set," allows users to view the "curriculum including advanced physics," and provides a progress report stating that "the next mock exam is next month and the recommended subject is quantum mechanics."

[0432] By following these steps, users can create an effective study plan based on their own learning progress.

[0433] (Application example 1)

[0434] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0435] Conventional learning support systems are limited to providing one-dimensional information when it comes to automatically generating test questions and customizing learning curricula, and are therefore not effective enough in improving users' learning efficiency. Furthermore, there is a lack of a way to provide users' learning progress data in a way that makes it easy to visually grasp it, making it difficult for users to effectively analyze and improve their self-learning progress.

[0436] 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.

[0437] In this invention, the server includes means for automatically generating test questions corresponding to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, and means for displaying the test questions, learning curriculum, and learning progress data in a virtual space, allowing the user to efficiently proceed with their learning plan. This allows the user to more interactively and efficiently manage their learning progress and adjust their learning plan through visual feedback in the virtual space.

[0438] A "specific educational institution" refers to a specific academic institution such as a university or high school, which provides learning content and examinations tailored to that institution.

[0439] "Means for automatically generating test questions" refers to technology that uses an external API to generate test questions based on predetermined prompts and provide them to users.

[0440] "User profile information" refers to personal information entered by the user, such as areas of interest and past academic performance data, and learning content is customized based on this information.

[0441] "Means for customizing learning curriculum" refers to technology that adds to or adjusts standard learning content based on a user's areas of interest and past performance data.

[0442] "Study progress data" refers to data based on a user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0443] "Virtual space" refers to a three-dimensional virtual environment created using computer technology in which users can interact with and learn.

[0444] "Display in virtual space" refers to a technology that uses virtual reality technology to display learning content and progress data in three dimensions, making it easier for users to visually grasp the information.

[0445] "Server" refers to the computer system that receives requests from users, generates test questions, customizes learning curriculum, and analyzes progress data.

[0446] The present invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data to provide the results. The system of the present invention is implemented by the following method.

[0447] First, the server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. To do this, the server uses an external API to generate test questions based on a predetermined prompt. Specifically, the server sends the prompt "medium difficulty physics exam at a specific university" to the external API and stores the returned results as a question set for the user.

[0448] The server then customizes the learning curriculum based on the user's profile information (e.g., areas of interest and past academic performance data). By referencing this profile information, the server can add to or adjust the standard curriculum. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0449] Furthermore, the server periodically collects and analyzes users' learning progress data (for example, mock test scores, daily study time, and level of understanding of specific subjects). The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on when to study.

[0450] Finally, the device provides the user with feedback from the server, including generated test question sets, customized learning curriculum, and progress analysis reports. This information is then visually displayed in a virtual space to help the user efficiently advance their learning plan. The display in the virtual space is achieved using virtual reality technology (e.g., a VR headset).

[0451] As an example, suppose the user enters the following prompt text:

[0452] "Generate medium difficulty questions for a specific university physics exam."

[0453] As a result, the server sends the generated test question set, customized learning curriculum, and progress analysis data to the terminal in response, and the user can proceed with their learning plan while visually checking this information in the virtual space.

[0454] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0455] Step 1:

[0456] The server receives user input: the user enters the desired educational institution, subject, and difficulty level, which gives the server input data for generating test questions.

[0457] Step 2:

[0458] The server sends a request to an external API. The server uses the acquired input data (e.g., "medium difficulty physics exam at a specific university") as a prompt and sends it to the external API. The API generates test questions based on the prompt and returns them to the server. The data processing performed here involves parsing the prompt and conveying it to the API in an appropriate format. As output, the server receives the generated test question set.

[0459] Step 3:

[0460] The server retrieves the user's profile information. It then references the user's areas of interest and past performance data to customize the learning curriculum. This generates a customized curriculum based on the profile information. Specifically, it retrieves the profile information from the database and adds or adjusts the standard curriculum based on that information. The output is a customized learning curriculum.

[0461] Step 4:

[0462] The server collects data on the user's learning progress. Data such as the user's daily study time, mock test scores, and level of understanding is collected and statistically analyzed. This generates data that visualizes each user's progress. Specifically, the progress data is retrieved from the database and analyzed using a machine learning algorithm. The output is a progress report.

[0463] Step 5:

[0464] The server sends the generated test question set, customized learning curriculum, and progress report to the user's device, which receives it and, if necessary, visually displays it in the virtual space. Specifically, the server converts the data into an appropriate format and sends it over the network to the user's device. The output is the information displayed on the user's device.

[0465] Step 6:

[0466] The device visually displays the data in a virtual space. The device displays the received learning content and progress data in three dimensions to help users efficiently advance their learning plans. Specifically, the device uses virtual reality technology such as a VR headset to display the received data in a visually easy-to-understand format.

[0467] 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.

[0468] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes user learning progress data and provides the results.

[0469] Automatic generation of exam questions

[0470] The server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam of a specific university, medium difficulty" to the API and saves the returned results as a question set for the user.

[0471] Customized learning curriculum

[0472] The server then references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted based on the user's inputted areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0473] Analysis of learning progress data

[0474] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0475] Emotion engine integration

[0476] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. Also, if it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0477] Providing feedback

[0478] Finally, the device provides the user with feedback from the server, including the generated problem set, the customized learning curriculum, the progress analysis report, and the curriculum adjusted by the emotion engine, allowing the user to efficiently advance their learning plan.

[0479] Specific examples

[0480] For example, if user "John Doe" wants to study physics at a particular university and wants problems of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics problems suitable for John Doe. Based on John Doe's profile information, which indicates his general interest in science, the server then suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. The server then analyzes John Doe's past mock exam performance data and creates a progress report showing which areas he should focus on.

[0481] In addition, the emotion engine analyzes John Doe's facial expressions and voice during his study session, and if it determines that he is feeling fatigued, the server adjusts the study curriculum to reduce the learning load. In this way, users can create an optimal study plan based on their emotional state.

[0482] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0483] The processing flow will be explained below.

[0484] Step 1:

[0485] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user might enter their name as "John Doe" and apply to the "Physics Department at a specific university," with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0486] Step 2:

[0487] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0488] json

[0489] {

[0490] "name": "John Doe",

[0491] "university": "Specific University",

[0492] "subject": "Physics",

[0493] "difficulty_level": "medium",

[0494] "interest": "science",

[0495] "progress": [

[0496] {"subject": "math", "score": 85},

[0497] {"subject": "science", "score": 90}

[0498] ]

[0499] }

[0500] Step 3:

[0501] Based on the profile information received, the server uses an external API to automatically generate exam questions for the desired university and subject. The server generates a prompt such as "Physics exam of a specific university, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0502] Step 4:

[0503] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum including "advanced physics" is generated.

[0504] Step 5:

[0505] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0506] Step 6:

[0507] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it will reduce the learning load, and if it determines that the user is highly motivated, it will increase the learning load.

[0508] Step 7:

[0509] The server sends the generated problem set, customized learning curriculum, progress analysis results, and curriculum adjusted by the emotion engine to the device, and provides this information as feedback to help users study more efficiently.

[0510] Step 8:

[0511] The device displays this information to the user. The user can solve the generated problems, study according to the curriculum, and check the progress analysis results and emotion-based adjustments to optimize their study plan. For example, the information John Doe checks on his device includes a "medium-difficulty problem set for a specific university's physics department," a science-focused curriculum, statistical data such as "an average math score of 85 and an average science score of 90," and the study load adjusted by the emotion engine. John Doe can use this information to create an efficient study plan.

[0512] Example 2

[0513] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0514] In conventional educational systems, test question generation, learning curriculum customization, and learning progress data analysis are all performed separately, making it difficult to provide an optimized learning experience for each user. It is also difficult to adjust learning based on the user's emotional state, leading to some users losing motivation due to excessive learning load. To solve these issues, a system is needed that integrates these functions to provide an optimized learning experience for each user.

[0515] 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.

[0516] In this invention, the server includes means for automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for recognizing the user's emotional state and adjusting the learning curriculum based thereon, and means for providing this information to the user via the terminal, thereby providing a learning experience optimized for each user and enabling efficient and effective learning.

[0517] "Specific educational institution" means a specific school, higher education institution, or other educational facility that provides examination questions and learning curricula tailored to the educational objectives and needs of the institution.

[0518] A "means for automatically generating test questions" is a device or program that uses an algorithm or external API to automatically create specific test questions based on conditions entered by a user.

[0519] "Profile information" refers to information about a user, such as the user's areas of interest, past learning history, and academic performance data, and is data used to customize the learning curriculum.

[0520] A "means for customizing a learning curriculum" is a device or program that adjusts a standard learning curriculum based on user profile information and provides the user with an optimized learning plan.

[0521] "Study progress data" is a record of the user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0522] "Means for analyzing progress data" refers to a device or program that statistically analyzes a user's learning progress data, evaluates the user's current learning situation, and provides information that is useful for future learning plans.

[0523] "Means for recognizing emotional state" refers to a device or program that analyzes a user's facial expression, voice, or text data to determine the user's emotional state (e.g., fatigue, stress, motivation).

[0524] A "means for adjusting a curriculum" is a device or program that appropriately changes the content or workload of a learning curriculum based on the recognized emotional state of the user.

[0525] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet, that receives information from the server and provides it to the user.

[0526] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results.

[0527] Automatic generation of exam questions

[0528] The server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. Specifically, the server uses a generative AI model (e.g., ChatGPT) to send a request to an external API. The request includes a specific prompt. For example, the server sends a request including the prompt "Please generate medium-difficulty questions for a physics exam at a specific educational institution," and saves the returned questions as a problem set for the user.

[0529] Customized learning curriculum

[0530] The server then analyzes the user's profile information (interests and past academic performance data) and adjusts the standard learning curriculum to provide a customized curriculum. For example, a user interested in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects. This adjustment is made based on an algorithm, and the curriculum content automatically changes when certain conditions are met.

[0531] Collection and analysis of learning progress data

[0532] The server periodically collects and analyzes the user's learning progress data. This data includes the user's scores on mock exams, daily study time, and level of understanding of specific subjects. This data is analyzed using statistical methods, and the results are visualized as the user's individual learning progress. Specific analysis results include the recommended time for the next mock exam and areas to focus on.

[0533] Emotion engine integration

[0534] The server integrates an emotion engine that recognizes the user's emotional state and further adaptively adjusts the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state (fatigue, stress, motivation, etc.). For example, if the server determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. On the other hand, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0535] Providing feedback

[0536] Finally, the device provides the user with feedback from the server, including the generated problem set, a customized learning curriculum, a progress analysis report, and a curriculum adjusted by the emotion engine, allowing the user to efficiently plan their learning.

[0537] Specific examples

[0538] For example, if a user is applying to a specific physics department and wants questions of medium difficulty, the server first uses the generative AI model to generate questions by sending a prompt to the API saying, "Generate medium-difficulty questions for the physics exam at a specific educational institution." Based on the user's profile information, the server then suggests a curriculum that includes "advanced physics." The server then analyzes the user's performance data from past mock exams to create a progress report showing which areas to focus on.

[0539] In addition, the emotion engine analyzes the user's facial expressions and voice during the learning session. If it determines that the user is feeling fatigued, the server adjusts the learning curriculum and reduces the learning load. On the other hand, if the user is highly motivated, the learning load is increased. In this way, the user can create an optimal learning plan based on their emotional state. This system provides a learning experience optimized for each user and supports efficient learning.

[0540] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0541] Step 1: User Input

[0542] The user inputs the desired educational institution, subject, difficulty level, and profile information (areas of interest, past learning history, etc.) through the terminal.

[0543] Input: desired educational institution, subject, difficulty level, profile information

[0544] Output: User input data

[0545] The server receives this input data and passes it on to the next processing step.

[0546] Step 2: Automatic generation of exam questions

[0547] The server uses a generative AI model (e.g., ChatGPT) to send a request to an external API to automatically generate test questions.

[0548] Input: User-entered data (desired educational institution, subject, difficulty level)

[0549] Output: Auto-generated test questions

[0550] Specific operation: The server sends the prompt "Please generate medium difficulty questions for the physics exam of a specific educational institution" to an external API and stores the generated exam questions in the database.

[0551] Step 3: Customize your learning curriculum

[0552] The server customizes the learning curriculum based on the user's profile information.

[0553] Input: User-entered data (profile information)

[0554] Output: Customized learning curriculum

[0555] Specific operation: The server analyzes the user's areas of interest and past grades, adjusts the standard curriculum, and suggests a curriculum that includes "advanced physics."

[0556] Step 4: Collect and analyze learning progress data

[0557] The server periodically collects and analyzes the user's learning progress data.

[0558] Input: User's learning progress data (mock test scores, study time, level of understanding)

[0559] Output: Progress visualization and analysis results

[0560] How it works: The server collects mock test scores, study time, and understanding of specific subjects, and analyzes them using statistical methods. It then suggests the best time to take the next mock test and the areas to focus on.

[0561] Step 5: Emotional Engine Adjustment

[0562] The server uses an emotion engine to identify the user's emotional state and adjust the learning curriculum.

[0563] Input: User emotion data (facial expression, voice, text)

[0564] Output: Aligned learning curriculum

[0565] Specific operation: The server uses an emotion engine to analyze the user's facial expressions and voice to determine fatigue and stress. If the user is fatigued, the learning load is reduced, and if the user is highly motivated, the load is increased.

[0566] Step 6: Provide feedback

[0567] The device provides the user with feedback from the server.

[0568] Input: Feedback data from the server

[0569] Output: Information provided to the user (generated test question sets, customized curriculum, progress analysis report, adjusted curriculum)

[0570] Specific operation: The device displays the information received from the server to the user, allowing the user to plan an efficient study plan based on this information.

[0571] (Application example 2)

[0572] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0573] Conventional learning support systems were unable to grasp the progress and emotional state of individual learners in real time and provide optimal learning curricula accordingly. In particular, when learners felt fatigued or stressed, the curriculum was not adjusted to take this into account, resulting in a decline in learning efficiency. Furthermore, the lack of a means to visually and in real time provide learning content and progress made it difficult for learners to properly grasp their own learning situation.

[0574] 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 automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for analyzing the user's emotional state and adjusting the learning curriculum, and means for presenting the learning content and progress status on a display device in real time. This makes it possible to provide the optimal learning curriculum tailored to the learner's situation in real time, improving learning efficiency and reducing the learner's burden.

[0575] A "means for automatically generating exam questions" is a means for automatically generating exam questions for a particular educational institution based on information entered by a user and using an external API based on predetermined prompts.

[0576] "Means for customizing learning curriculum" refers to a means for dynamically adjusting and suggesting learning content that is optimal for each learner based on the user's profile information, areas of interest, and past performance data.

[0577] "Means for analyzing learning progress data and providing the results" refers to means for periodically collecting and analyzing users' learning progress data and providing visual progress status in real time as statistical analysis results.

[0578] The "means for analyzing the user's emotional state and adjusting the learning curriculum" refers to a means for analyzing the user's facial expressions and voice to recognize the emotional state, and dynamically adjusting the learning curriculum based on the results.

[0579] "Means for presenting learning content and progress status on a display device in real time" refers to means for visually presenting learning content and progress data to learners in real time using a display device such as smart glasses.

[0580] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data to provide the results. A display device such as smart glasses is also used to display learning content and progress in real time.

[0581] Automatic generation of exam questions

[0582] The server automatically generates exam questions based on the user's desired university, subject, and difficulty level. Specifically, the server sends a request to an external API and saves the generated exam questions as a question set for the user. This process uses a generative AI model (e.g., GPT-3 / 4) and inputs a specified prompt. For example, by sending the prompt "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University," a medium-difficulty physics exam question will be generated.

[0583] Customized learning curriculum

[0584] The server references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted taking into account the user's input areas of interest and past test scores. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0585] Analysis of learning progress data

[0586] The server periodically collects and analyzes the user's learning progress data, including the user's mock test scores, daily study time, and level of understanding of specific subjects. This data is statistically analyzed to visualize each user's progress. For example, it suggests the best time to take the next mock test and areas to focus on when to study.

[0587] Emotion engine integration

[0588] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine uses the smart glasses' camera and audio microphone to analyze the user's facial expressions and voice to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it adjusts the curriculum to reduce the learning load. If it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0589] Real-time feedback

[0590] The learning content and progress are displayed in real time on the smart glasses' display. This allows users to receive real-time feedback while studying, optimizing learning efficiency. Specific examples of messages that are displayed to users while studying include, "The best time to take the next practice exam is in three days," and "It would be best to focus on the electromagnetics section of physics right now."

[0591] Specific examples

[0592] For example, when a user wears smart glasses to study, the server functions as follows: First, the user enters information about the university and subjects they wish to study. The server uses this information to send prompts to an external API to generate exam questions. A customized learning curriculum is then created based on the user's profile information. During study, the user's emotional state is identified through the smart glasses' camera and microphone, and the server provides real-time feedback and adjusts the curriculum accordingly.

[0593] This allows users to create optimal study plans based on their emotional state and learning progress, enabling them to study efficiently toward achieving their goals.

[0594] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0595] Step 1:

[0596] A user logs into the system and inputs the university of their choice, the subject, and the level of difficulty. This information is sent to the server. The input information is the university of their choice, the subject, and the level of difficulty. The server uses this information to create a prompt for generating exam questions.

[0597] Step 2:

[0598] The server sends a prompt to an external API and generates exam questions using a generative AI model (e.g., GPT-3 / 4). The input is the prompt, e.g., "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University." The server retrieves the exam question data returned by the external API.

[0599] Step 3:

[0600] The server stores the generated test questions as a test question set for the user. The stored data is divided into test question sets for each user.

[0601] Step 4:

[0602] The user enters profile information (interests and past test scores) and sends it to the server, which then obtains the basic data for customizing the user's learning curriculum.

[0603] Step 5:

[0604] The server creates a learning curriculum based on the user's profile information. The input data is areas of interest and past grades, and the output is a customized learning curriculum. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics."

[0605] Step 6:

[0606] The server periodically collects and statistically analyzes users' learning progress data. Input data includes mock test scores and daily study time, and a progress report is generated as output. The server visualizes each user's progress and suggests the best time to take the next mock test and the areas they should study.

[0607] Step 7:

[0608] The user begins learning using the smart glasses. The user's facial expressions and voice data are sent to the server via the smart glasses' camera and audio microphone.

[0609] Step 8:

[0610] The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. The input data is facial image data and voice data, and the output classifies the user's emotional state (e.g., fatigue, stress, high motivation, etc.).

[0611] Step 9:

[0612] The server adjusts the learning curriculum based on the user's emotional state. For example, if the server determines that the user is feeling fatigued, it adjusts the curriculum to reduce the learning load. Conversely, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0613] Step 10:

[0614] The server presents the adjusted learning curriculum in real time on the smart glasses' display. This allows users to check their learning content and progress in real time as they study. For example, messages such as "The best time to take the next mock exam is in three days" or "You should currently focus on the electromagnetics section of physics" are displayed.

[0615] 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.

[0616] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0617] 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.

[0618] [Third embodiment]

[0619] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0620] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0631] This invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data and provides the results.

[0632] Automatic generation of exam questions

[0633] First, the server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server then sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the API and stores the returned results as a question set for the user.

[0634] Customized learning curriculum

[0635] The server then references the user's profile information and creates a learning curriculum based on that information. Taking into account the user's inputted areas of interest and past test scores, the server adds to or adjusts the standard curriculum. For example, a user with a strong interest in science might be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0636] Analysis of learning progress data

[0637] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0638] Providing feedback

[0639] Finally, the device provides the user with feedback from the server, including generated problem sets, customized learning curriculum, and progress analysis reports, allowing the user to efficiently plan their learning.

[0640] Specific examples

[0641] For example, if user "John Doe" wants to study physics at the University of Tokyo and wants questions of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics questions suitable for John Doe. Then, based on John Doe's profile information indicating his general interest in science, the server suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. Furthermore, the server analyzes John Doe's performance data from past mock exams and creates a progress report showing which areas he should focus on. This information is then displayed on the device, allowing John Doe to use it to create a study plan.

[0642] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0643] The processing flow will be explained below.

[0644] Step 1:

[0645] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user may enter their name as "John Doe" and apply to the Department of Physics at the University of Tokyo, with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0646] Step 2:

[0647] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0648] json

[0649] {

[0650] "name": "John Doe",

[0651] "university": "Tokyo University",

[0652] "subject": "Physics",

[0653] "difficulty_level": "medium",

[0654] "interest": "science",

[0655] "progress": [

[0656] {"subject": "math", "score": 85},

[0657] {"subject": "science", "score": 90}

[0658] ]

[0659] }

[0660] Step 3:

[0661] Based on the profile information received by the server, an external API is used to automatically generate exam questions corresponding to the desired university and subject. The server generates a prompt such as "Physics exam at the University of Tokyo, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0662] Step 4:

[0663] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum that includes "advanced physics" is generated.

[0664] Step 5:

[0665] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0666] Step 6:

[0667] The server sends the generated problem sets, customized learning curriculum, and progress analysis results to the device, providing this information as feedback to help users study more effectively.

[0668] Step 7:

[0669] The device displays this information to the user, who can then solve the generated problems, follow the curriculum, and check progress analysis results to optimize their own study plan.

[0670] For example, the information John Doe sees on his device includes a medium-difficulty problem set from the Department of Physics at the University of Tokyo, a science-focused curriculum, and statistical data such as "an average score of 85 in math and 90 in science." John Doe can use this information to create an efficient study plan.

[0671] Example 1

[0672] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0673] Conventional learning support systems do not adequately generate test questions or customize learning curricula to meet the needs of individual users, and they also lack effective analysis and feedback of learning progress. As a result, they are unable to provide an optimized learning experience for users, resulting in problems such as reduced learning efficiency and results.

[0674] 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.

[0675] In this invention, the server includes means for automatically generating test questions based on information entered by the user, means for customizing a learning curriculum based on the user's profile information, means for collecting and analyzing the user's learning progress data and providing the results, and means for the terminal to provide the user with feedback from the server. This makes it possible to generate test questions optimized for each user, provide a customized learning curriculum, and provide appropriate analysis of learning progress and effective feedback.

[0676] The "means for automatically generating exam questions" is a mechanism for generating exam questions using an external API based on the user's desired university, exam subjects, and desired level of difficulty.

[0677] "Means for customizing learning curriculum" refers to a mechanism that adjusts the learning curriculum based on the user's profile information (such as areas of interest and past grades) to provide the user with the most appropriate learning content.

[0678] "Means for collecting learning progress data" refers to a system for regularly collecting learning data, such as a user's daily study time, mock test scores, and level of understanding of specific subjects.

[0679] The "means for analyzing learning progress data" is a mechanism for statistically analyzing collected learning progress data and visualizing each user's learning progress.

[0680] The "feedback provision means" is a mechanism for providing users with the server-generated problem sets, customized learning curriculum, and progress analysis results.

[0681] A "prompt" is a document to be sent to an external API used to generate test questions, specifying a specific educational institution, subject, and difficulty level.

[0682] MODE FOR CARRYING OUT THE INVENTION

[0683] This invention is a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results. The specific configuration and operation of this system are described in detail below.

[0684] Hardware and software used

[0685] The system is primarily composed of a server and user devices. The specific software uses a generative AI model with external APIs. In particular, OpenAI's API is used to generate test questions.

[0686] Automatic generation of exam questions

[0687] The server automatically generates test questions based on the user's desired university, exam subjects, and desired difficulty level. The server sends a predetermined prompt to an external API and retrieves test questions using a generative AI model. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the external API and stores the returned test questions in a database.

[0688] Specific prompt examples:

[0689] "Generate moderate difficulty questions for the University of Tokyo physics exam."

[0690] Customized learning curriculum

[0691] The server customizes the learning curriculum based on the user's profile information. This profile information includes the user's areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic physics and chemistry courses. The customized learning curriculum is stored in a database on the server.

[0692] Collection and analysis of learning progress data

[0693] The server periodically collects the user's learning progress data and performs statistical analysis. This data includes mock test scores, daily study time, and level of understanding of specific subjects. As a result of the analysis, the system suggests the best time to take the next mock test and areas to focus on for study. This makes it possible to visualize the user's learning status.

[0694] Providing feedback

[0695] The device receives feedback data from the server and displays it in an easy-to-understand manner to the user. The feedback includes the generated test question set, a customized learning curriculum, and progress analysis results. For example, on the device's feedback screen, the user can review the "generated physics question set" and view the "curriculum including advanced physics." The device also displays a progress report stating, "The next mock exam is next month, and the recommended subject is quantum mechanics."

[0696] This system configuration makes it possible to generate test questions optimized for each user, provide individually customized learning curricula, and provide highly accurate analysis of progress data and effective feedback.

[0697] By specifically implementing the invention based on the above aspects, it becomes possible to solve the problems that conventional learning support systems have had and to provide efficient and effective learning support.

[0698] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0699] Processing Steps

[0700] Step 1: Enter your user information

[0701] The user inputs information such as the university of choice, exam subjects, desired level of difficulty, areas of interest, and past academic results through the terminal.

[0702] Input: desired university (e.g., University of Tokyo), exam subject (e.g., physics), desired difficulty level (e.g., medium), area of ​​interest (e.g., general science), and past academic performance (e.g., 60 points on mock exams).

[0703] Output: This information is sent to the server and stored in a database.

[0704] Specific actions: Enter "University of Tokyo, Physics, Medium level, Interested in science, 60 points on mock exam" into the input form on the device and press the "Submit" button.

[0705] Step 2: Automatic generation of exam questions

[0706] Based on the information received in step 1, the server sends a prompt to the external API and generates test questions using the generative AI model.

[0707] Input: User-entered desired university, exam subjects, and desired difficulty level.

[0708] Data processing: The server uses this information to generate a prompt and sends it to the external API.

[0709] Output: The test questions returned from the external API are saved on the server.

[0710] Specific operation: The server sends a prompt message to the external API saying "Please generate medium-difficulty questions for the University of Tokyo physics exam" and saves the returned question data in the database.

[0711] Step 3: Customize your learning curriculum

[0712] The server customizes the learning curriculum based on the profile information received in step 1.

[0713] Input: User's interests and past learning achievements.

[0714] Data processing: The server makes the necessary adjustments to the standard curriculum.

[0715] Output: The customized learning curriculum is saved in the database.

[0716] Specific operation: The server adds the subject "Advanced Physics" based on the profile data, generates a curriculum including it, and saves it in the database.

[0717] Step 4: Collect and analyze learning progress data

[0718] The server periodically collects user learning progress data and performs statistical analysis.

[0719] Input: User's daily study time, mock test scores, and subject-specific comprehension.

[0720] Data processing: The server statistically analyzes the collected data.

[0721] Output: Progress data and analysis results for each user, such as when the next mock test is due and what areas to focus on.

[0722] Specific operation: The server collects "user's learning progress data (e.g., 2 hours of study per day, 80 points on mock exams)" and generates analysis results based on that data, such as "the next mock exam is next month, and the recommended subject is quantum mechanics."

[0723] Step 5: Provide feedback

[0724] The terminal receives the feedback data from the server and displays it to the user.

[0725] Input: Generated problem sets, customized learning curriculum, and progress analysis results provided by the server.

[0726] Output: These data are presented visually to the user.

[0727] Specific operation: The device's feedback screen displays the "generated physics problem set," allows users to view the "curriculum including advanced physics," and provides a progress report stating that "the next mock exam is next month and the recommended subject is quantum mechanics."

[0728] By following these steps, users can create an effective study plan based on their own learning progress.

[0729] (Application example 1)

[0730] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0731] Conventional learning support systems are limited to providing one-dimensional information when it comes to automatically generating test questions and customizing learning curricula, and are therefore not effective enough in improving users' learning efficiency. Furthermore, there is a lack of a way to provide users' learning progress data in a way that makes it easy to visually grasp it, making it difficult for users to effectively analyze and improve their self-learning progress.

[0732] 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.

[0733] In this invention, the server includes means for automatically generating test questions corresponding to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, and means for displaying the test questions, learning curriculum, and learning progress data in a virtual space, allowing the user to efficiently proceed with their learning plan. This allows the user to more interactively and efficiently manage their learning progress and adjust their learning plan through visual feedback in the virtual space.

[0734] A "specific educational institution" refers to a specific academic institution such as a university or high school, which provides learning content and examinations tailored to that institution.

[0735] "Means for automatically generating test questions" refers to technology that uses an external API to generate test questions based on predetermined prompts and provide them to users.

[0736] "User profile information" refers to personal information entered by the user, such as areas of interest and past academic performance data, and learning content is customized based on this information.

[0737] "Means for customizing learning curriculum" refers to technology that adds to or adjusts standard learning content based on a user's areas of interest and past performance data.

[0738] "Study progress data" refers to data based on a user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0739] "Virtual space" refers to a three-dimensional virtual environment created using computer technology in which users can interact with and learn.

[0740] "Display in virtual space" refers to a technology that uses virtual reality technology to display learning content and progress data in three dimensions, making it easier for users to visually grasp the information.

[0741] "Server" refers to the computer system that receives requests from users, generates test questions, customizes learning curriculum, and analyzes progress data.

[0742] The present invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data to provide the results. The system of the present invention is implemented by the following method.

[0743] First, the server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. To do this, the server uses an external API to generate test questions based on a predetermined prompt. Specifically, the server sends the prompt "medium difficulty physics exam at a specific university" to the external API and stores the returned results as a question set for the user.

[0744] The server then customizes the learning curriculum based on the user's profile information (e.g., areas of interest and past academic performance data). By referencing this profile information, the server can add to or adjust the standard curriculum. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0745] Furthermore, the server periodically collects and analyzes users' learning progress data (for example, mock test scores, daily study time, and level of understanding of specific subjects). The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on when to study.

[0746] Finally, the device provides the user with feedback from the server, including generated test question sets, customized learning curriculum, and progress analysis reports. This information is then visually displayed in a virtual space to help the user efficiently advance their learning plan. The display in the virtual space is achieved using virtual reality technology (e.g., a VR headset).

[0747] As an example, suppose the user enters the following prompt text:

[0748] "Generate medium difficulty questions for a specific university physics exam."

[0749] As a result, the server sends the generated test question set, customized learning curriculum, and progress analysis data to the terminal in response, and the user can proceed with their learning plan while visually checking this information in the virtual space.

[0750] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0751] Step 1:

[0752] The server receives user input: the user enters the desired educational institution, subject, and difficulty level, which gives the server input data for generating test questions.

[0753] Step 2:

[0754] The server sends a request to an external API. The server uses the acquired input data (e.g., "medium difficulty physics exam at a specific university") as a prompt and sends it to the external API. The API generates test questions based on the prompt and returns them to the server. The data processing performed here involves parsing the prompt and conveying it to the API in an appropriate format. As output, the server receives the generated test question set.

[0755] Step 3:

[0756] The server retrieves the user's profile information. It then references the user's areas of interest and past performance data to customize the learning curriculum. This generates a customized curriculum based on the profile information. Specifically, it retrieves the profile information from the database and adds or adjusts the standard curriculum based on that information. The output is a customized learning curriculum.

[0757] Step 4:

[0758] The server collects data on the user's learning progress. Data such as the user's daily study time, mock test scores, and level of understanding is collected and statistically analyzed. This generates data that visualizes each user's progress. Specifically, the progress data is retrieved from the database and analyzed using a machine learning algorithm. The output is a progress report.

[0759] Step 5:

[0760] The server sends the generated test question set, customized learning curriculum, and progress report to the user's device, which receives it and, if necessary, visually displays it in the virtual space. Specifically, the server converts the data into an appropriate format and sends it over the network to the user's device. The output is the information displayed on the user's device.

[0761] Step 6:

[0762] The device visually displays the data in a virtual space. The device displays the received learning content and progress data in three dimensions to help users efficiently advance their learning plans. Specifically, the device uses virtual reality technology such as a VR headset to display the received data in a visually easy-to-understand format.

[0763] 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.

[0764] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes user learning progress data and provides the results.

[0765] Automatic generation of exam questions

[0766] The server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam of a specific university, medium difficulty" to the API and saves the returned results as a question set for the user.

[0767] Customized learning curriculum

[0768] The server then references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted based on the user's inputted areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[0769] Analysis of learning progress data

[0770] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0771] Emotion engine integration

[0772] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. Also, if it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0773] Providing feedback

[0774] Finally, the device provides the user with feedback from the server, including the generated problem set, the customized learning curriculum, the progress analysis report, and the curriculum adjusted by the emotion engine, allowing the user to efficiently advance their learning plan.

[0775] Specific examples

[0776] For example, if user "John Doe" wants to study physics at a particular university and wants problems of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics problems suitable for John Doe. Based on John Doe's profile information, which indicates his general interest in science, the server then suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. The server then analyzes John Doe's past mock exam performance data and creates a progress report showing which areas he should focus on.

[0777] In addition, the emotion engine analyzes John Doe's facial expressions and voice during his study session, and if it determines that he is feeling fatigued, the server adjusts the study curriculum to reduce the learning load. In this way, users can create an optimal study plan based on their emotional state.

[0778] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0779] The processing flow will be explained below.

[0780] Step 1:

[0781] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user might enter their name as "John Doe" and apply to the "Physics Department at a specific university," with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0782] Step 2:

[0783] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0784] json

[0785] {

[0786] "name": "John Doe",

[0787] "university": "Specific University",

[0788] "subject": "Physics",

[0789] "difficulty_level": "medium",

[0790] "interest": "science",

[0791] "progress": [

[0792] {"subject": "math", "score": 85},

[0793] {"subject": "science", "score": 90}

[0794] ]

[0795] }

[0796] Step 3:

[0797] Based on the profile information received, the server uses an external API to automatically generate exam questions for the desired university and subject. The server generates a prompt such as "Physics exam of a specific university, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0798] Step 4:

[0799] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum including "advanced physics" is generated.

[0800] Step 5:

[0801] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0802] Step 6:

[0803] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it will reduce the learning load, and if it determines that the user is highly motivated, it will increase the learning load.

[0804] Step 7:

[0805] The server sends the generated problem set, customized learning curriculum, progress analysis results, and curriculum adjusted by the emotion engine to the device, and provides this information as feedback to help users study more efficiently.

[0806] Step 8:

[0807] The device displays this information to the user. The user can solve the generated problems, study according to the curriculum, and check the progress analysis results and emotion-based adjustments to optimize their study plan. For example, the information John Doe checks on his device includes a "medium-difficulty problem set for a specific university's physics department," a science-focused curriculum, statistical data such as "an average math score of 85 and an average science score of 90," and the study load adjusted by the emotion engine. John Doe can use this information to create an efficient study plan.

[0808] Example 2

[0809] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0810] In conventional educational systems, test question generation, learning curriculum customization, and learning progress data analysis are all performed separately, making it difficult to provide an optimized learning experience for each user. It is also difficult to adjust learning based on the user's emotional state, leading to some users losing motivation due to excessive learning load. To solve these issues, a system is needed that integrates these functions to provide an optimized learning experience for each user.

[0811] 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.

[0812] In this invention, the server includes means for automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for recognizing the user's emotional state and adjusting the learning curriculum based thereon, and means for providing this information to the user via the terminal, thereby providing a learning experience optimized for each user and enabling efficient and effective learning.

[0813] "Specific educational institution" means a specific school, higher education institution, or other educational facility that provides examination questions and learning curricula tailored to the educational objectives and needs of the institution.

[0814] A "means for automatically generating test questions" is a device or program that uses an algorithm or external API to automatically create specific test questions based on conditions entered by a user.

[0815] "Profile information" refers to information about a user, such as the user's areas of interest, past learning history, and academic performance data, and is data used to customize the learning curriculum.

[0816] A "means for customizing a learning curriculum" is a device or program that adjusts a standard learning curriculum based on user profile information and provides the user with an optimized learning plan.

[0817] "Study progress data" is a record of the user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[0818] "Means for analyzing progress data" refers to a device or program that statistically analyzes a user's learning progress data, evaluates the user's current learning situation, and provides information that is useful for future learning plans.

[0819] "Means for recognizing emotional state" refers to a device or program that analyzes a user's facial expression, voice, or text data to determine the user's emotional state (e.g., fatigue, stress, motivation).

[0820] A "means for adjusting a curriculum" is a device or program that appropriately changes the content or workload of a learning curriculum based on the recognized emotional state of the user.

[0821] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet, that receives information from the server and provides it to the user.

[0822] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results.

[0823] Automatic generation of exam questions

[0824] The server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. Specifically, the server uses a generative AI model (e.g., ChatGPT) to send a request to an external API. The request includes a specific prompt. For example, the server sends a request including the prompt "Please generate medium-difficulty questions for a physics exam at a specific educational institution," and saves the returned questions as a problem set for the user.

[0825] Customized learning curriculum

[0826] The server then analyzes the user's profile information (interests and past academic performance data) and adjusts the standard learning curriculum to provide a customized curriculum. For example, a user interested in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects. This adjustment is made based on an algorithm, and the curriculum content automatically changes when certain conditions are met.

[0827] Collection and analysis of learning progress data

[0828] The server periodically collects and analyzes the user's learning progress data. This data includes the user's scores on mock exams, daily study time, and level of understanding of specific subjects. This data is analyzed using statistical methods, and the results are visualized as the user's individual learning progress. Specific analysis results include the recommended time for the next mock exam and areas to focus on.

[0829] Emotion engine integration

[0830] The server integrates an emotion engine that recognizes the user's emotional state and further adaptively adjusts the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state (fatigue, stress, motivation, etc.). For example, if the server determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. On the other hand, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0831] Providing feedback

[0832] Finally, the device provides the user with feedback from the server, including the generated problem set, a customized learning curriculum, a progress analysis report, and a curriculum adjusted by the emotion engine, allowing the user to efficiently plan their learning.

[0833] Specific examples

[0834] For example, if a user is applying to a specific physics department and wants questions of medium difficulty, the server first uses the generative AI model to generate questions by sending a prompt to the API saying, "Generate medium-difficulty questions for the physics exam at a specific educational institution." Based on the user's profile information, the server then suggests a curriculum that includes "advanced physics." The server then analyzes the user's performance data from past mock exams to create a progress report showing which areas to focus on.

[0835] In addition, the emotion engine analyzes the user's facial expressions and voice during a learning session. If it determines that the user is feeling fatigued, the server adjusts the learning curriculum and reduces the learning load. On the other hand, if the user is highly motivated, it increases the learning load. In this way, users can create the optimal learning plan according to their emotional state. This system provides a learning experience optimized for each user and supports efficient learning.

[0836] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0837] Step 1: User Input

[0838] The user inputs the desired educational institution, subject, difficulty level, and profile information (areas of interest, past learning history, etc.) through the terminal.

[0839] Input: desired educational institution, subject, difficulty level, profile information

[0840] Output: User input data

[0841] The server receives this input data and passes it on to the next processing step.

[0842] Step 2: Automatic generation of exam questions

[0843] The server uses a generative AI model (e.g., ChatGPT) to send a request to an external API to automatically generate test questions.

[0844] Input: User-entered data (desired educational institution, subject, difficulty level)

[0845] Output: Auto-generated test questions

[0846] Specific operation: The server sends the prompt "Please generate medium difficulty questions for the physics exam of a specific educational institution" to an external API and stores the generated exam questions in the database.

[0847] Step 3: Customize your learning curriculum

[0848] The server customizes the learning curriculum based on the user's profile information.

[0849] Input: User-entered data (profile information)

[0850] Output: Customized learning curriculum

[0851] Specific operation: The server analyzes the user's areas of interest and past grades, adjusts the standard curriculum, and suggests a curriculum that includes "advanced physics."

[0852] Step 4: Collect and analyze learning progress data

[0853] The server periodically collects and analyzes the user's learning progress data.

[0854] Input: User's learning progress data (mock test scores, study time, level of understanding)

[0855] Output: Progress visualization and analysis results

[0856] How it works: The server collects mock test scores, study time, and understanding of specific subjects, and analyzes them using statistical methods. It then suggests the best time to take the next mock test and the areas to focus on.

[0857] Step 5: Emotional Engine Adjustment

[0858] The server uses an emotion engine to identify the user's emotional state and adjust the learning curriculum.

[0859] Input: User emotion data (facial expression, voice, text)

[0860] Output: Aligned learning curriculum

[0861] Specific operation: The server uses an emotion engine to analyze the user's facial expressions and voice to determine fatigue and stress. If the user is fatigued, the learning load is reduced, and if the user is highly motivated, the load is increased.

[0862] Step 6: Provide feedback

[0863] The device provides the user with feedback from the server.

[0864] Input: Feedback data from the server

[0865] Output: Information provided to the user (generated test question sets, customized curriculum, progress analysis report, adjusted curriculum)

[0866] Specific operation: The device displays the information received from the server to the user, allowing the user to plan an efficient study plan based on this information.

[0867] (Application example 2)

[0868] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0869] Conventional learning support systems were unable to grasp the progress and emotional state of individual learners in real time and provide optimal learning curricula accordingly. In particular, when learners felt fatigued or stressed, the curriculum was not adjusted to take this into account, resulting in a decline in learning efficiency. Furthermore, the lack of a means to visually and in real time provide learning content and progress made it difficult for learners to properly grasp their own learning situation.

[0870] 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 automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for analyzing the user's emotional state and adjusting the learning curriculum, and means for presenting the learning content and progress status on a display device in real time. This makes it possible to provide the optimal learning curriculum tailored to the learner's situation in real time, improving learning efficiency and reducing the learner's burden.

[0871] A "means for automatically generating exam questions" is a means for automatically generating exam questions for a particular educational institution based on information entered by a user and using an external API based on predetermined prompts.

[0872] "Means for customizing learning curriculum" refers to a means for dynamically adjusting and suggesting learning content that is optimal for each learner based on the user's profile information, areas of interest, and past performance data.

[0873] "Means for analyzing learning progress data and providing the results" refers to means for periodically collecting and analyzing users' learning progress data and providing visual progress status in real time as statistical analysis results.

[0874] The "means for analyzing the user's emotional state and adjusting the learning curriculum" refers to a means for analyzing the user's facial expressions and voice to recognize the emotional state, and dynamically adjusting the learning curriculum based on the results.

[0875] "Means for presenting learning content and progress status on a display device in real time" refers to means for visually presenting learning content and progress data to learners in real time using a display device such as smart glasses.

[0876] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data to provide the results. A display device such as smart glasses is also used to display learning content and progress in real time.

[0877] Automatic generation of exam questions

[0878] The server automatically generates exam questions based on the user's desired university, subject, and difficulty level. Specifically, the server sends a request to an external API and saves the generated exam questions as a question set for the user. This process uses a generative AI model (e.g., GPT-3 / 4) and inputs a specified prompt. For example, by sending the prompt "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University," a medium-difficulty physics exam question will be generated.

[0879] Customized learning curriculum

[0880] The server references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted taking into account the user's input areas of interest and past test scores. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0881] Analysis of learning progress data

[0882] The server periodically collects and analyzes the user's learning progress data, including the user's mock test scores, daily study time, and level of understanding of specific subjects. This data is statistically analyzed to visualize each user's progress. For example, it suggests the best time to take the next mock test and areas to focus on when to study.

[0883] Emotion engine integration

[0884] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine uses the smart glasses' camera and audio microphone to analyze the user's facial expressions and voice to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it adjusts the curriculum to reduce the learning load. If it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0885] Real-time feedback

[0886] The learning content and progress are displayed in real time on the smart glasses' display. This allows users to receive real-time feedback while studying, optimizing learning efficiency. Specific examples of messages that are displayed to users while studying include, "The best time to take the next practice exam is in three days," and "It would be best to focus on the electromagnetics section of physics right now."

[0887] Specific examples

[0888] For example, when a user wears smart glasses to study, the server functions as follows: First, the user enters information about the university and subjects they wish to study. The server uses this information to send prompts to an external API to generate exam questions. A customized learning curriculum is then created based on the user's profile information. During study, the user's emotional state is identified through the smart glasses' camera and microphone, and the server provides real-time feedback and adjusts the curriculum accordingly.

[0889] This allows users to create optimal study plans based on their emotional state and learning progress, enabling them to study efficiently toward achieving their goals.

[0890] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0891] Step 1:

[0892] A user logs into the system and inputs the university of their choice, the subject, and the level of difficulty. This information is sent to the server. The input information is the university of their choice, the subject, and the level of difficulty. The server uses this information to create a prompt for generating exam questions.

[0893] Step 2:

[0894] The server sends a prompt to an external API and generates exam questions using a generative AI model (e.g., GPT-3 / 4). The input is the prompt, e.g., "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University." The server retrieves the exam question data returned by the external API.

[0895] Step 3:

[0896] The server stores the generated test questions as a test question set for the user. The stored data is divided into test question sets for each user.

[0897] Step 4:

[0898] The user enters profile information (interests and past test scores) and sends it to the server, which then obtains the basic data for customizing the user's learning curriculum.

[0899] Step 5:

[0900] The server creates a learning curriculum based on the user's profile information. The input data is areas of interest and past grades, and the output is a customized learning curriculum. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics."

[0901] Step 6:

[0902] The server periodically collects and statistically analyzes users' learning progress data. Input data includes mock test scores and daily study time, and a progress report is generated as output. The server visualizes each user's progress and suggests the best time to take the next mock test and the areas they should study.

[0903] Step 7:

[0904] The user begins learning using the smart glasses. The user's facial expressions and voice data are sent to the server via the smart glasses' camera and audio microphone.

[0905] Step 8:

[0906] The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. The input data is facial image data and voice data, and the output classifies the user's emotional state (e.g., fatigue, stress, high motivation, etc.).

[0907] Step 9:

[0908] The server adjusts the learning curriculum based on the user's emotional state. For example, if the server determines that the user is feeling fatigued, it adjusts the curriculum to reduce the learning load. Conversely, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[0909] Step 10:

[0910] The server presents the adjusted learning curriculum in real time on the smart glasses' display. This allows users to check their learning content and progress in real time as they study. For example, messages such as "The best time to take the next mock exam is in three days" or "You should currently focus on the electromagnetics section of physics" are displayed.

[0911] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0912] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0913] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0914] [Fourth embodiment]

[0915] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0916] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0917] 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).

[0918] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0919] 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.

[0920] 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).

[0921] 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.

[0922] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0923] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0924] 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.

[0925] 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.

[0926] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0927] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0928] This invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data and provides the results.

[0929] Automatic generation of exam questions

[0930] First, the server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server then sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the API and stores the returned results as a question set for the user.

[0931] Customized learning curriculum

[0932] The server then references the user's profile information and creates a learning curriculum based on that information. Taking into account the user's inputted areas of interest and past test scores, the server adds to or adjusts the standard curriculum. For example, a user with a strong interest in science might be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[0933] Analysis of learning progress data

[0934] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[0935] Providing feedback

[0936] Finally, the device provides the user with feedback from the server, including generated problem sets, customized learning curriculum, and progress analysis reports, allowing the user to efficiently plan their learning.

[0937] Specific examples

[0938] For example, if user "John Doe" wants to study physics at the University of Tokyo and wants questions of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics questions suitable for John Doe. Then, based on John Doe's profile information indicating his general interest in science, the server suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. Furthermore, the server analyzes John Doe's performance data from past mock exams and creates a progress report showing which areas he should focus on. This information is then displayed on the device, allowing John Doe to use it to create a study plan.

[0939] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[0940] The processing flow will be explained below.

[0941] Step 1:

[0942] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user may enter their name as "John Doe" and apply to the Department of Physics at the University of Tokyo, with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[0943] Step 2:

[0944] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[0945] json

[0946] {

[0947] "name": "John Doe",

[0948] "university": "Tokyo University",

[0949] "subject": "Physics",

[0950] "difficulty_level": "medium",

[0951] "interest": "science",

[0952] "progress": [

[0953] {"subject": "math", "score": 85},

[0954] {"subject": "science", "score": 90}

[0955] ]

[0956] }

[0957] Step 3:

[0958] Based on the profile information received by the server, an external API is used to automatically generate exam questions corresponding to the desired university and subject. The server generates a prompt such as "Physics exam at the University of Tokyo, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[0959] Step 4:

[0960] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum that includes "advanced physics" is generated.

[0961] Step 5:

[0962] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[0963] Step 6:

[0964] The server sends the generated problem sets, customized learning curriculum, and progress analysis results to the device, providing this information as feedback to help users study more effectively.

[0965] Step 7:

[0966] The device displays this information to the user, who can then solve the generated problems, follow the curriculum, and check progress analysis results to optimize their own study plan.

[0967] For example, the information John Doe sees on his device includes a medium-difficulty problem set from the Department of Physics at the University of Tokyo, a science-focused curriculum, and statistical data such as "an average score of 85 in math and 90 in science." John Doe can use this information to create an efficient study plan.

[0968] Example 1

[0969] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0970] Conventional learning support systems do not adequately generate test questions or customize learning curricula to meet the needs of individual users, and they also lack effective analysis and feedback of learning progress. As a result, they are unable to provide an optimized learning experience for users, resulting in problems such as reduced learning efficiency and results.

[0971] 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.

[0972] In this invention, the server includes means for automatically generating test questions based on information entered by the user, means for customizing a learning curriculum based on the user's profile information, means for collecting and analyzing the user's learning progress data and providing the results, and means for the terminal to provide the user with feedback from the server. This makes it possible to generate test questions optimized for each user, provide a customized learning curriculum, and provide appropriate analysis of learning progress and effective feedback.

[0973] The "means for automatically generating exam questions" is a mechanism for generating exam questions using an external API based on the user's desired university, exam subjects, and desired level of difficulty.

[0974] "Means for customizing learning curriculum" refers to a mechanism that adjusts the learning curriculum based on the user's profile information (such as areas of interest and past grades) to provide the user with the most appropriate learning content.

[0975] "Means for collecting learning progress data" refers to a system for regularly collecting learning data, such as a user's daily study time, mock test scores, and level of understanding of specific subjects.

[0976] The "means for analyzing learning progress data" is a mechanism for statistically analyzing collected learning progress data and visualizing each user's learning progress.

[0977] The "feedback provision means" is a mechanism for providing users with the server-generated problem sets, customized learning curriculum, and progress analysis results.

[0978] A "prompt" is a document to be sent to an external API used to generate test questions, specifying a specific educational institution, subject, and difficulty level.

[0979] MODE FOR CARRYING OUT THE INVENTION

[0980] This invention is a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results. The specific configuration and operation of this system are described in detail below.

[0981] Hardware and software used

[0982] The system is primarily composed of a server and user devices. The specific software uses a generative AI model with external APIs. In particular, OpenAI's API is used to generate test questions.

[0983] Automatic generation of exam questions

[0984] The server automatically generates test questions based on the user's desired university, exam subjects, and desired difficulty level. The server sends a predetermined prompt to an external API and retrieves test questions using a generative AI model. For example, the server sends the prompt "Physics exam at the University of Tokyo, medium difficulty" to the external API and stores the returned test questions in a database.

[0985] Specific prompt examples:

[0986] "Generate moderate difficulty questions for the University of Tokyo physics exam."

[0987] Customized learning curriculum

[0988] The server customizes the learning curriculum based on the user's profile information. This profile information includes the user's areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic physics and chemistry courses. The customized learning curriculum is stored in a database on the server.

[0989] Collection and analysis of learning progress data

[0990] The server periodically collects the user's learning progress data and performs statistical analysis. This data includes mock test scores, daily study time, and level of understanding of specific subjects. As a result of the analysis, the system suggests the best time to take the next mock test and areas to focus on for study. This makes it possible to visualize the user's learning status.

[0991] Providing feedback

[0992] The device receives feedback data from the server and displays it in an easy-to-understand manner to the user. The feedback includes the generated test question set, a customized learning curriculum, and progress analysis results. For example, on the device's feedback screen, the user can review the "generated physics question set" and view the "curriculum including advanced physics." The device also displays a progress report stating, "The next mock exam is next month, and the recommended subject is quantum mechanics."

[0993] This system configuration makes it possible to generate test questions optimized for each user, provide individually customized learning curricula, and provide highly accurate analysis of progress data and effective feedback.

[0994] By specifically implementing the invention based on the above aspects, it becomes possible to solve the problems that conventional learning support systems have had and to provide efficient and effective learning support.

[0995] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0996] Processing Steps

[0997] Step 1: Enter your user information

[0998] The user inputs information such as the university of choice, exam subjects, desired level of difficulty, areas of interest, and past academic results through the terminal.

[0999] Input: desired university (e.g., University of Tokyo), exam subject (e.g., physics), desired difficulty level (e.g., medium), area of ​​interest (e.g., general science), and past academic performance (e.g., 60 points on mock exams).

[1000] Output: This information is sent to the server and stored in a database.

[1001] Specific actions: Enter "University of Tokyo, Physics, Medium level, Interested in science, 60 points on mock exam" into the input form on the device and press the "Submit" button.

[1002] Step 2: Automatic generation of exam questions

[1003] Based on the information received in step 1, the server sends a prompt to the external API and generates test questions using the generative AI model.

[1004] Input: User-entered desired university, exam subjects, and desired difficulty level.

[1005] Data processing: The server uses this information to generate a prompt and sends it to the external API.

[1006] Output: The test questions returned from the external API are saved on the server.

[1007] Specific operation: The server sends a prompt message to the external API saying "Please generate medium-difficulty questions for the University of Tokyo physics exam" and saves the returned question data in the database.

[1008] Step 3: Customize your learning curriculum

[1009] The server customizes the learning curriculum based on the profile information received in step 1.

[1010] Input: User's interests and past learning achievements.

[1011] Data processing: The server makes the necessary adjustments to the standard curriculum.

[1012] Output: The customized learning curriculum is saved in the database.

[1013] Specific operation: The server adds the subject "Advanced Physics" based on the profile data, generates a curriculum including it, and saves it in the database.

[1014] Step 4: Collect and analyze learning progress data

[1015] The server periodically collects user learning progress data and performs statistical analysis.

[1016] Input: User's daily study time, mock test scores, and subject-specific comprehension.

[1017] Data processing: The server statistically analyzes the collected data.

[1018] Output: Progress data and analysis results for each user, such as when the next mock test is due and what areas to focus on.

[1019] Specific operation: The server collects "user's learning progress data (e.g., 2 hours of study per day, 80 points on mock exams)" and generates analysis results based on that data, such as "the next mock exam is next month, and the recommended subject is quantum mechanics."

[1020] Step 5: Provide feedback

[1021] The terminal receives the feedback data from the server and displays it to the user.

[1022] Input: Generated problem sets, customized learning curriculum, and progress analysis results provided by the server.

[1023] Output: These data are presented visually to the user.

[1024] Specific operation: The device's feedback screen displays the "generated physics problem set," allows users to view the "curriculum including advanced physics," and provides a progress report stating that "the next mock exam is next month and the recommended subject is quantum mechanics."

[1025] By following these steps, users can create an effective study plan based on their own learning progress.

[1026] (Application example 1)

[1027] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1028] Conventional learning support systems are limited to providing one-dimensional information when it comes to automatically generating test questions and customizing learning curricula, and are therefore not effective enough in improving users' learning efficiency. Furthermore, there is a lack of a way to provide users' learning progress data in a way that makes it easy to visually grasp it, making it difficult for users to effectively analyze and improve their self-learning progress.

[1029] 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.

[1030] In this invention, the server includes means for automatically generating test questions corresponding to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, and means for displaying the test questions, learning curriculum, and learning progress data in a virtual space, allowing the user to efficiently proceed with their learning plan. This allows the user to more interactively and efficiently manage their learning progress and adjust their learning plan through visual feedback in the virtual space.

[1031] A "specific educational institution" refers to a specific academic institution such as a university or high school, which provides learning content and examinations tailored to that institution.

[1032] "Means for automatically generating test questions" refers to technology that uses an external API to generate test questions based on predetermined prompts and provide them to users.

[1033] "User profile information" refers to personal information entered by the user, such as areas of interest and past academic performance data, and learning content is customized based on this information.

[1034] "Means for customizing learning curriculum" refers to technology that adds to or adjusts standard learning content based on a user's areas of interest and past performance data.

[1035] "Study progress data" refers to data based on a user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[1036] "Virtual space" refers to a three-dimensional virtual environment created using computer technology in which users can interact with and learn.

[1037] "Display in virtual space" refers to a technology that uses virtual reality technology to display learning content and progress data in three dimensions, making it easier for users to visually grasp the information.

[1038] "Server" refers to the computer system that receives requests from users, generates test questions, customizes learning curriculum, and analyzes progress data.

[1039] The present invention relates to a system that automatically generates test questions tailored to a specific educational institution, customizes a learning curriculum based on a user's profile information, and analyzes the user's learning progress data to provide the results. The system of the present invention is implemented by the following method.

[1040] First, the server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. To do this, the server uses an external API to generate test questions based on a predetermined prompt. Specifically, the server sends the prompt "medium difficulty physics exam at a specific university" to the external API and stores the returned results as a question set for the user.

[1041] The server then customizes the learning curriculum based on the user's profile information (e.g., areas of interest and past academic performance data). By referencing this profile information, the server can add to or adjust the standard curriculum. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[1042] Furthermore, the server periodically collects and analyzes users' learning progress data (for example, mock test scores, daily study time, and level of understanding of specific subjects). The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on when to study.

[1043] Finally, the device provides the user with feedback from the server, including generated test question sets, customized learning curriculum, and progress analysis reports. This information is then visually displayed in a virtual space to help the user efficiently advance their learning plan. The display in the virtual space is achieved using virtual reality technology (e.g., a VR headset).

[1044] As an example, suppose the user enters the following prompt text:

[1045] "Generate medium difficulty questions for a specific university physics exam."

[1046] As a result, the server sends the generated test question set, customized learning curriculum, and progress analysis data to the terminal in response, and the user can proceed with their learning plan while visually checking this information in the virtual space.

[1047] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1048] Step 1:

[1049] The server receives user input: the user enters the desired educational institution, subject, and difficulty level, which gives the server input data for generating test questions.

[1050] Step 2:

[1051] The server sends a request to an external API. The server uses the acquired input data (e.g., "medium difficulty physics exam at a specific university") as a prompt and sends it to the external API. The API generates test questions based on the prompt and returns them to the server. The data processing performed here involves parsing the prompt and conveying it to the API in an appropriate format. As output, the server receives the generated test question set.

[1052] Step 3:

[1053] The server retrieves the user's profile information. It then references the user's areas of interest and past performance data to customize the learning curriculum. This generates a customized curriculum based on the profile information. Specifically, it retrieves the profile information from the database and adds or adjusts the standard curriculum based on that information. The output is a customized learning curriculum.

[1054] Step 4:

[1055] The server collects data on the user's learning progress. Data such as the user's daily study time, mock test scores, and level of understanding is collected and statistically analyzed. This generates data that visualizes each user's progress. Specifically, the progress data is retrieved from the database and analyzed using a machine learning algorithm. The output is a progress report.

[1056] Step 5:

[1057] The server sends the generated test question set, customized learning curriculum, and progress report to the user's device, which receives it and, if necessary, visually displays it in the virtual space. Specifically, the server converts the data into an appropriate format and sends it over the network to the user's device. The output is the information displayed on the user's device.

[1058] Step 6:

[1059] The device visually displays the data in a virtual space. The device displays the received learning content and progress data in three dimensions to help users efficiently advance their learning plans. Specifically, the device uses virtual reality technology such as a VR headset to display the received data in a visually easy-to-understand format.

[1060] 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.

[1061] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes user learning progress data and provides the results.

[1062] Automatic generation of exam questions

[1063] The server automatically generates test questions based on the user's desired university, subject, and difficulty level. The server sends a request to an external API to generate test questions based on a given prompt. For example, the server sends the prompt "Physics exam of a specific university, medium difficulty" to the API and saves the returned results as a question set for the user.

[1064] Customized learning curriculum

[1065] The server then references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted based on the user's inputted areas of interest and past test scores. For example, a user with a strong interest in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects.

[1066] Analysis of learning progress data

[1067] The server periodically collects and analyzes the user's learning progress data. This includes the user's mock test scores, daily study time, and level of understanding of specific subjects. The server statistically analyzes this data and visualizes each user's progress. Specific analysis results include the recommended timing for the next mock test and areas to focus on.

[1068] Emotion engine integration

[1069] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. Also, if it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[1070] Providing feedback

[1071] Finally, the device provides the user with feedback from the server, including the generated problem set, the customized learning curriculum, the progress analysis report, and the curriculum adjusted by the emotion engine, allowing the user to efficiently advance their learning plan.

[1072] Specific examples

[1073] For example, if user "John Doe" wants to study physics at a particular university and wants problems of medium difficulty, the server first sends a request to an external API to automatically generate a set of physics problems suitable for John Doe. Based on John Doe's profile information, which indicates his general interest in science, the server then suggests a curriculum that includes "advanced physics" in addition to standard physics and chemistry courses. The server then analyzes John Doe's past mock exam performance data and creates a progress report showing which areas he should focus on.

[1074] In addition, the emotion engine analyzes John Doe's facial expressions and voice during his study session, and if it determines that he is feeling fatigued, the server adjusts the study curriculum to reduce the learning load. In this way, users can create an optimal study plan based on their emotional state.

[1075] In this way, we can provide a learning experience that is optimized for each user and help them study efficiently to get into their desired school.

[1076] The processing flow will be explained below.

[1077] Step 1:

[1078] The user enters their profile information into the device. This information includes their name, desired university, desired subjects, current academic level, areas of interest, past test scores, etc. For example, a user might enter their name as "John Doe" and apply to the "Physics Department at a specific university," with their current academic level as "average," their area of ​​interest as "science," and their past test scores as "85 points in math, 90 points in science."

[1079] Step 2:

[1080] The device sends the entered profile information to the server. The specific data format is JSON, and this data is transferred to the server. For example, the following JSON data is sent:

[1081] json

[1082] {

[1083] "name": "John Doe",

[1084] "university": "Specific University",

[1085] "subject": "Physics",

[1086] "difficulty_level": "medium",

[1087] "interest": "science",

[1088] "progress": [

[1089] {"subject": "math", "score": 85},

[1090] {"subject": "science", "score": 90}

[1091] ]

[1092] }

[1093] Step 3:

[1094] Based on the profile information received, the server uses an external API to automatically generate exam questions for the desired university and subject. The server generates a prompt such as "Physics exam of a specific university, medium difficulty level" and sends it to the external API. The server receives the results returned by the API and saves them as a question set for the user.

[1095] Step 4:

[1096] The server analyzes the user's profile information and creates an individualized learning curriculum. It adjusts the standard curriculum taking into account the user's areas of interest and past academic performance data. For example, for a user with a strong interest in science, a curriculum including "advanced physics" is generated.

[1097] Step 5:

[1098] The server analyzes the user's progress data, performs statistical analysis based on the received past test score data and new learning data, and calculates the average score, standard deviation, or progress trend, thereby visualizing the effectiveness of the user's learning.

[1099] Step 6:

[1100] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it will reduce the learning load, and if it determines that the user is highly motivated, it will increase the learning load.

[1101] Step 7:

[1102] The server sends the generated problem set, customized learning curriculum, progress analysis results, and curriculum adjusted by the emotion engine to the device, and provides this information as feedback to help users study more efficiently.

[1103] Step 8:

[1104] The device displays this information to the user. The user can solve the generated problems, study according to the curriculum, and check the progress analysis results and emotion-based adjustments to optimize their study plan. For example, the information John Doe checks on his device includes a "medium-difficulty problem set for a specific university's physics department," a science-focused curriculum, statistical data such as "an average math score of 85 and an average science score of 90," and the study load adjusted by the emotion engine. John Doe can use this information to create an efficient study plan.

[1105] Example 2

[1106] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1107] In conventional educational systems, test question generation, learning curriculum customization, and learning progress data analysis are all performed separately, making it difficult to provide an optimized learning experience for each user. It is also difficult to adjust learning based on the user's emotional state, leading to some users losing motivation due to excessive learning load. To solve these issues, a system is needed that integrates these functions to provide an optimized learning experience for each user.

[1108] 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.

[1109] In this invention, the server includes means for automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for recognizing the user's emotional state and adjusting the learning curriculum based thereon, and means for providing this information to the user via the terminal, thereby providing a learning experience optimized for each user and enabling efficient and effective learning.

[1110] "Specific educational institution" means a specific school, higher education institution, or other educational facility that provides examination questions and learning curricula tailored to the educational objectives and needs of the institution.

[1111] A "means for automatically generating test questions" is a device or program that uses an algorithm or external API to automatically create specific test questions based on conditions entered by a user.

[1112] "Profile information" refers to information about a user, such as the user's areas of interest, past learning history, and academic performance data, and is data used to customize the learning curriculum.

[1113] A "means for customizing a learning curriculum" is a device or program that adjusts a standard learning curriculum based on user profile information and provides the user with an optimized learning plan.

[1114] "Study progress data" is a record of the user's learning activities, including mock test scores, study time, and level of understanding of each subject.

[1115] "Means for analyzing progress data" refers to a device or program that statistically analyzes a user's learning progress data, evaluates the user's current learning situation, and provides information that is useful for future learning plans.

[1116] "Means for recognizing emotional state" refers to a device or program that analyzes a user's facial expression, voice, or text data to determine the user's emotional state (e.g., fatigue, stress, motivation).

[1117] A "means for adjusting a curriculum" is a device or program that appropriately changes the content or workload of a learning curriculum based on the recognized emotional state of the user.

[1118] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet, that receives information from the server and provides it to the user.

[1119] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data and provides the results.

[1120] Automatic generation of exam questions

[1121] The server automatically generates test questions based on the user's desired educational institution, subject, and difficulty level. Specifically, the server uses a generative AI model (e.g., ChatGPT) to send a request to an external API. The request includes a specific prompt. For example, the server sends a request including the prompt "Please generate medium-difficulty questions for a physics exam at a specific educational institution," and saves the returned questions as a problem set for the user.

[1122] Customized learning curriculum

[1123] The server then analyzes the user's profile information (interests and past academic performance data) and adjusts the standard learning curriculum to provide a customized curriculum. For example, a user interested in science might be offered a curriculum that includes "advanced physics" in addition to basic subjects. This adjustment is made based on an algorithm, and the curriculum content automatically changes when certain conditions are met.

[1124] Collection and analysis of learning progress data

[1125] The server periodically collects and analyzes the user's learning progress data. This data includes the user's scores on mock exams, daily study time, and level of understanding of specific subjects. This data is analyzed using statistical methods, and the results are visualized as the user's individual learning progress. Specific analysis results include the recommended time for the next mock exam and areas to focus on.

[1126] Emotion engine integration

[1127] The server integrates an emotion engine that recognizes the user's emotional state and further adaptively adjusts the learning curriculum. The emotion engine analyzes the user's facial expressions, voice, or text data to identify their emotional state (fatigue, stress, motivation, etc.). For example, if the server determines that the user is feeling fatigued or stressed while studying, it adjusts the curriculum to reduce the learning load. On the other hand, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[1128] Providing feedback

[1129] Finally, the device provides the user with feedback from the server, including the generated problem set, a customized learning curriculum, a progress analysis report, and a curriculum adjusted by the emotion engine, allowing the user to efficiently plan their learning.

[1130] Specific examples

[1131] For example, if a user is applying to a specific physics department and wants questions of medium difficulty, the server first uses the generative AI model to generate questions by sending a prompt to the API saying, "Generate medium-difficulty questions for the physics exam at a specific educational institution." Based on the user's profile information, the server then suggests a curriculum that includes "advanced physics." The server then analyzes the user's performance data from past mock exams to create a progress report showing which areas to focus on.

[1132] In addition, the emotion engine analyzes the user's facial expressions and voice during the learning session. If it determines that the user is feeling fatigued, the server adjusts the learning curriculum and reduces the learning load. On the other hand, if the user is highly motivated, the learning load is increased. In this way, the user can create an optimal learning plan based on their emotional state. This system provides a learning experience optimized for each user and supports efficient learning.

[1133] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1134] Step 1: User Input

[1135] The user inputs the desired educational institution, subject, difficulty level, and profile information (areas of interest, past learning history, etc.) through the terminal.

[1136] Input: desired educational institution, subject, difficulty level, profile information

[1137] Output: User input data

[1138] The server receives this input data and passes it on to the next processing step.

[1139] Step 2: Automatic generation of exam questions

[1140] The server uses a generative AI model (e.g., ChatGPT) to send a request to an external API to automatically generate test questions.

[1141] Input: User-entered data (desired educational institution, subject, difficulty level)

[1142] Output: Auto-generated test questions

[1143] Specific operation: The server sends the prompt "Please generate medium difficulty questions for the physics exam of a specific educational institution" to an external API and stores the generated exam questions in the database.

[1144] Step 3: Customize your learning curriculum

[1145] The server customizes the learning curriculum based on the user's profile information.

[1146] Input: User-entered data (profile information)

[1147] Output: Customized learning curriculum

[1148] Specific operation: The server analyzes the user's areas of interest and past grades, adjusts the standard curriculum, and suggests a curriculum that includes "advanced physics."

[1149] Step 4: Collect and analyze learning progress data

[1150] The server periodically collects and analyzes the user's learning progress data.

[1151] Input: User's learning progress data (mock test scores, study time, level of understanding)

[1152] Output: Progress visualization and analysis results

[1153] How it works: The server collects mock test scores, study time, and understanding of specific subjects, and analyzes them using statistical methods. It then suggests the best time to take the next mock test and the areas to focus on.

[1154] Step 5: Emotional Engine Adjustment

[1155] The server uses an emotion engine to identify the user's emotional state and adjust the learning curriculum.

[1156] Input: User emotion data (facial expression, voice, text)

[1157] Output: Aligned learning curriculum

[1158] Specific operation: The server uses an emotion engine to analyze the user's facial expressions and voice to determine fatigue and stress. If the user is fatigued, the learning load is reduced, and if the user is highly motivated, the load is increased.

[1159] Step 6: Provide feedback

[1160] The device provides the user with feedback from the server.

[1161] Input: Feedback data from the server

[1162] Output: Information provided to the user (generated test question sets, customized curriculum, progress analysis report, adjusted curriculum)

[1163] Specific operation: The device displays the information received from the server to the user, allowing the user to plan an efficient study plan based on this information.

[1164] (Application example 2)

[1165] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1166] Conventional learning support systems were unable to grasp the progress and emotional state of individual learners in real time and provide optimal learning curricula accordingly. In particular, when learners felt fatigued or stressed, the curriculum was not adjusted to take this into account, resulting in a decline in learning efficiency. Furthermore, the lack of a means to visually and in real time provide learning content and progress made it difficult for learners to properly grasp their own learning situation.

[1167] 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 automatically generating test questions tailored to a specific educational institution, means for customizing a learning curriculum based on user profile information, means for analyzing the user's learning progress data and providing the results, means for analyzing the user's emotional state and adjusting the learning curriculum, and means for presenting the learning content and progress status on a display device in real time. This makes it possible to provide the optimal learning curriculum tailored to the learner's situation in real time, improving learning efficiency and reducing the learner's burden.

[1168] A "means for automatically generating exam questions" is a means for automatically generating exam questions for a particular educational institution based on information entered by a user and using an external API based on predetermined prompts.

[1169] "Means for customizing learning curriculum" refers to a means for dynamically adjusting and suggesting learning content that is optimal for each learner based on the user's profile information, areas of interest, and past performance data.

[1170] "Means for analyzing learning progress data and providing the results" refers to means for periodically collecting and analyzing users' learning progress data and providing visual progress status in real time as statistical analysis results.

[1171] The "means for analyzing the user's emotional state and adjusting the learning curriculum" refers to a means for analyzing the user's facial expressions and voice to recognize the emotional state, and dynamically adjusting the learning curriculum based on the results.

[1172] "Means for presenting learning content and progress status on a display device in real time" refers to means for visually presenting learning content and progress data to learners in real time using a display device such as smart glasses.

[1173] This invention combines an emotion engine with a system that automatically generates test questions tailored to specific educational institutions, customizes learning curricula based on user profile information, and analyzes the user's learning progress data to provide the results. A display device such as smart glasses is also used to display learning content and progress in real time.

[1174] Automatic generation of exam questions

[1175] The server automatically generates exam questions based on the user's desired university, subject, and difficulty level. Specifically, the server sends a request to an external API and saves the generated exam questions as a question set for the user. This process uses a generative AI model (e.g., GPT-3 / 4) and inputs a specified prompt. For example, by sending the prompt "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University," a medium-difficulty physics exam question will be generated.

[1176] Customized learning curriculum

[1177] The server references the user's profile information and creates a learning curriculum based on that information. The standard curriculum is adjusted taking into account the user's input areas of interest and past test scores. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics" in addition to basic subjects.

[1178] Analysis of learning progress data

[1179] The server periodically collects and analyzes the user's learning progress data, including the user's mock test scores, daily study time, and level of understanding of specific subjects. This data is statistically analyzed to visualize each user's progress. For example, it suggests the best time to take the next mock test and areas to focus on when to study.

[1180] Emotion engine integration

[1181] The server works with an emotion engine that recognizes the user's emotions to further adaptively adjust the learning curriculum. The emotion engine uses the smart glasses' camera and audio microphone to analyze the user's facial expressions and voice to identify their emotional state. For example, if it determines that the user is feeling tired or stressed, it adjusts the curriculum to reduce the learning load. If it determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[1182] Real-time feedback

[1183] The learning content and progress are displayed in real time on the smart glasses' display. This allows users to receive real-time feedback while studying, optimizing learning efficiency. Specific examples of messages that are displayed to users while studying include, "The best time to take the next practice exam is in three days," and "It would be best to focus on the electromagnetics section of physics right now."

[1184] Specific examples

[1185] For example, when a user wears smart glasses to study, the server functions as follows: First, the user enters information about the university and subjects they wish to study. The server uses this information to send prompts to an external API to generate exam questions. A customized learning curriculum is then created based on the user's profile information. During study, the user's emotional state is identified through the smart glasses' camera and microphone, and the server provides real-time feedback and adjusts the curriculum accordingly.

[1186] This allows users to create optimal study plans based on their emotional state and learning progress, enabling them to study efficiently toward achieving their goals.

[1187] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1188] Step 1:

[1189] A user logs into the system and inputs the university of their choice, the subject, and the level of difficulty. This information is sent to the server. The input information is the university of their choice, the subject, and the level of difficulty. The server uses this information to create a prompt for generating exam questions.

[1190] Step 2:

[1191] The server sends a prompt to an external API and generates exam questions using a generative AI model (e.g., GPT-3 / 4). The input is the prompt, e.g., "Create an exam question with a medium difficulty level for Physics suitable for entry exams at Tokyo University." The server retrieves the exam question data returned by the external API.

[1192] Step 3:

[1193] The server stores the generated test questions as a test question set for the user. The stored data is divided into test question sets for each user.

[1194] Step 4:

[1195] The user enters profile information (interests and past test scores) and sends it to the server, which then obtains the basic data for customizing the user's learning curriculum.

[1196] Step 5:

[1197] The server creates a learning curriculum based on the user's profile information. The input data is areas of interest and past grades, and the output is a customized learning curriculum. For example, a user with a strong interest in science will be suggested a curriculum that includes "advanced physics."

[1198] Step 6:

[1199] The server periodically collects and statistically analyzes users' learning progress data. Input data includes mock test scores and daily study time, and a progress report is generated as output. The server visualizes each user's progress and suggests the best time to take the next mock test and the areas they should study.

[1200] Step 7:

[1201] The user begins learning using the smart glasses. The user's facial expressions and voice data are sent to the server via the smart glasses' camera and audio microphone.

[1202] Step 8:

[1203] The server uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state. The input data is facial image data and voice data, and the output classifies the user's emotional state (e.g., fatigue, stress, high motivation, etc.).

[1204] Step 9:

[1205] The server adjusts the learning curriculum based on the user's emotional state. For example, if the server determines that the user is feeling fatigued, it adjusts the curriculum to reduce the learning load. Conversely, if the server determines that the user is highly motivated, it increases the learning load and provides more challenging tasks.

[1206] Step 10:

[1207] The server presents the adjusted learning curriculum in real time on the smart glasses' display. This allows users to check their learning content and progress in real time as they study. For example, messages such as "The best time to take the next mock exam is in three days" or "You should currently focus on the electromagnetics section of physics" are displayed.

[1208] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1209] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1210] 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 robot 414.

[1211] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1212] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1213] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1214] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1215] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1216] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1217] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1218] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1219] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1220] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1221] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1222] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1223] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1224] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1225] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1226] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1227] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1228] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1229] The following is further disclosed regarding the above embodiment.

[1230] (Claim 1)

[1231] A means for automatically generating exam questions for a particular educational institution;

[1232] a means for customizing a learning curriculum based on user profile information;

[1233] A means for analyzing the user's learning progress data and providing the results;

[1234] A system including:

[1235] (Claim 2)

[1236] 2. The system according to claim 1, wherein the means for automatically generating test questions generates test questions based on predetermined prompts using an external API.

[1237] (Claim 3)

[1238] 2. The system according to claim 1, wherein the means for customizing the learning curriculum adjusts learning content based on the user's areas of interest and past performance data.

[1239] "Example 1"

[1240] (Claim 1)

[1241] means for automatically generating test questions based on information entered by a user;

[1242] a means for customizing a learning curriculum based on user profile information;

[1243] A means of collecting user learning progress data, analyzing it and providing results;

[1244] a means by which the device provides feedback to the user from the server;

[1245] A system including:

[1246] (Claim 2)

[1247] 2. The system according to claim 1, wherein the means for automatically generating test questions generates test questions based on a predetermined prompt sentence using an external API.

[1248] (Claim 3)

[1249] 2. The system according to claim 1, wherein the means for customizing the learning curriculum adjusts learning content based on the user's areas of interest and past test performance data.

[1250] "Application Example 1"

[1251] (Claim 1)

[1252] A means for automatically generating exam questions for a particular educational institution;

[1253] a means for customizing a learning curriculum based on user profile information;

[1254] A means for analyzing the user's learning progress data and providing the results;

[1255] A means for displaying the above test questions, learning curriculum, and learning progress data in a virtual space, allowing users to efficiently proceed with their learning plans;

[1256] A system including:

[1257] (Claim 2)

[1258] 2. The system according to claim 1, wherein the means for automatically generating test questions generates test questions based on predetermined prompts using an external API.

[1259] (Claim 3)

[1260] 2. The system according to claim 1, wherein the means for customizing the learning curriculum adjusts learning content based on the user's areas of interest and past performance data.

[1261] (Claim 4)

[1262] 2. The system according to claim 1, wherein the display in the virtual space is a three-dimensional display of the user's learning progress data, utilizing virtual reality technology.

[1263] "Example 2: Combining Emotion Engines"

[1264] (Claim 1)

[1265] A means for automatically generating exam questions for a particular educational institution;

[1266] a means for customizing a learning curriculum based on user profile information;

[1267] A means for analyzing the user's learning progress data and providing the results;

[1268] a means for recognizing a user's emotional state and adjusting the learning curriculum accordingly;

[1269] A means for providing such information to the user via a terminal;

[1270] A system including:

[1271] (Claim 2)

[1272] 2. The system according to claim 1, wherein the means for automatically generating test questions generates test questions based on predetermined prompts using an external API.

[1273] (Claim 3)

[1274] 2. The system according to claim 1, wherein the means for customizing the learning curriculum adjusts learning content based on the user's areas of interest and past performance data.

[1275] "Application example 2 when combining emotion engines"

[1276] (Claim 1)

[1277] A means for automatically generating exam questions for a particular educational institution;

[1278] a means for customizing a learning curriculum based on user profile information;

[1279] A means for analyzing the user's learning progress data and providing the results;

[1280] A means for analyzing the user's emotional state and adjusting the learning curriculum;

[1281] A means to present learning content and progress in real time on a display device,

[1282] A system including:

[1283] (Claim 2)

[1284] 10. The system of claim 1, further comprising means for generating test questions based on predetermined prompts using an external API.

[1285] (Claim 3)

[1286] 10. The system of claim 1, further comprising means for adjusting learning content based on a user's areas of interest and past performance data. [Explanation of symbols]

[1287] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically generating exam questions for a particular educational institution; a means for customizing a learning curriculum based on user profile information; A means for analyzing the user's learning progress data and providing the results; A system including:

2. 2. The system of claim 1, wherein the means for automatically generating test questions uses an external API to generate test questions based on predetermined prompts.

3. 2. The system according to claim 1, wherein the means for customizing the learning curriculum adjusts learning content based on the user's areas of interest and past performance data.

Images