System

Abstract

To provide a system for enabling an examinee to efficiently advance learning under an optimum learning environment.SOLUTION: A means for inputting basic information and a learning history of a learner, a means for transmitting the basic information and the learning history to a server, a means for storing the received basic information and learning history in a database, a means for analyzing the basic information and the learning history from the database and generating an optimal virtual competitor for the learner, a means for transmitting data of the virtual competitor to a terminal of the learner, a means for interacting and competing with the virtual competitor on the terminal, a means for transmitting a response of the learner and a competition result to the server, and a means for generating feedback based on the response of the learner and the competition result on the server; A system comprising: means for transmitting to a terminal; means for monitoring stress levels and learning effectiveness of a learner and adjusting settings of a virtual competitor; and means for transmitting adjusted data of the virtual competitor to the terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While competing with rivals in studying for entrance exams can improve motivation and grades, excessive competition can lead to stress and deterioration of interpersonal relationships. Another issue is the lack of rivals at the same level depending on the region or environment. In such situations, learning efficiency and results may not be maximized. The purpose of this invention is to solve these problems and provide a system that allows test-takers to study efficiently in an optimal learning environment. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system including: means for inputting a learner's basic information and learning history; means for transmitting the basic information and learning history to a server; means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner; means for transmitting data of the virtual competitor to the learner's terminal; means for interacting with and competing with the virtual competitor on the terminal; means for transmitting the learner's responses and the results of the competition to a server; means for generating feedback on the basis of the learner's responses and the results of the competition on the server and transmitting the feedback to the terminal; means for monitoring the learner's stress level and learning effect and adjusting the settings of the virtual competitor; and means for transmitting adjustment data of the virtual competitor to the terminal.

[0006] This allows students to avoid conflict with real people while enhancing their learning effectiveness through moderate competition. Furthermore, by adjusting the settings of virtual competitors to suit individual students, it is possible to control stress levels and maintain motivation to study. This allows students to consistently study in an optimal learning environment, thereby maximizing their learning effectiveness.

[0007] "Learner" refers to an individual who takes classes, takes exams, and works on assignments for a specific educational purpose.

[0008] "Basic information" refers to basic personal information about the learner, such as name, age, grade, and school information.

[0009] "Learning history" refers to data on a learner's past classes, exams, mock exam results, and learning progress.

[0010] "Server" refers to a central processing unit that communicates with terminals via a network and stores, analyzes, transmits and receives data.

[0011] A "terminal" is a device that is directly operated by a learner and communicates with a server to input and display data.

[0012] "Database" refers to a data storage system that systematically stores and manages basic information and learning history.

[0013] "Analysis" refers to the process of evaluating and analyzing the received basic information and learning history using specific algorithms to extract the learner's characteristics and patterns.

[0014] "Virtual competitor" refers to a virtual character or agent created to compete and interact with learners.

[0015] "Feedback" refers to response information, including learning improvement points and pointers, generated based on the learner's responses and competition results.

[0016] "Stress level" refers to the degree of psychological stress and tension felt by learners.

[0017] "Adjustment" refers to the process of appropriately changing the difficulty and behavior of the virtual competitor based on the learner's performance and stress level. [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] System Overview and Operation

[0040] This system inputs basic information and learning history of a learner and analyzes that data to generate a virtual opponent that is optimal for the learner. This system provides a moderate competitive environment, maximizing learning effectiveness while managing stress.

[0041] Program processing overview

[0042] Initial Setup and Data Collection

[0043] 1. User Registration

[0044] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[0045] The terminal sends the entered basic information to the server, which stores it in a database.

[0046] 2. Collecting learning history

[0047] Users enter the results of mock exams and progress in classes into the terminal.

[0048] The terminal sends the collected learning history data to the server, which stores it in a database.

[0049] Data analysis and virtual competitor generation

[0050] 3. Data Analysis

[0051] The server analyzes the learner's basic information and learning history stored in the database, and identifies the learner's strong and weak subjects and learning patterns.

[0052] This analysis uses machine learning algorithms to accurately evaluate the learner's characteristics.

[0053] 4. Creating Virtual Competitors

[0054] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[0055] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[0056] Interface, Interaction and Competition

[0057] 5. Transmission of competitor data

[0058] The server transmits data of the generated virtual competitor to the terminal.

[0059] The receiving terminal displays the virtual competitor on the user interface.

[0060] 6. Dialogue and Competition

[0061] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[0062] The terminal compiles the user's answers and those of the virtual competitors in real time and provides feedback to the user.

[0063] Specific examples

[0064] 1. Example of entering basic user information

[0065] Candidate B is using the system for the first time, so he enters his name, age, school name, etc. on the terminal.

[0066] The device sends this basic information to the server, which stores it in a database.

[0067] 2. Learning history input and analysis example

[0068] Candidate B takes the mock test and enters the results into the terminal. The results are recorded in detail, including the score, answer time, and questions answered incorrectly.

[0069] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[0070] 3. Example of Virtual Competitor Generation

[0071] The analysis results indicate that candidate B is good at math but not so good at English.

[0072] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[0073] 4. Examples of dialogue and competition

[0074] When Candidate B takes a mock test on his device, a scenario is displayed in which a virtual competitor is also taking the test at the same time.

[0075] Results are displayed in real time and feedback is provided based on this.

[0076] Feedback and Adjustments

[0077] Stress level feedback from users

[0078] Candidate B enters the stress level he or she felt during the competition.

[0079] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[0080] Strengthening or weakening virtual competitors

[0081] The server will comprehensively evaluate the stress level and learning effect of test-taker B and adjust the settings of the next virtual competitor.

[0082] For example, if you feel too stressed, lower the difficulty of your competitors, and conversely, if you have more time, increase the difficulty.

[0083] In this way, the present invention is designed to allow test takers to study hard in an optimal learning environment, and to maximize the learning effect through moderate competition.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[0087] Step 2:

[0088] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[0089] Step 3:

[0090] The server analyzes the basic information and learning history stored in the database and uses machine learning algorithms to identify the learner's strengths, weaknesses, and learning patterns.

[0091] Step 4:

[0092] Based on the analysis results, the server generates the virtual competitor that is best suited for the learner. The server creates the virtual competitor's data (character settings, behavior patterns, difficulty level, etc.).

[0093] Step 5:

[0094] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[0095] Step 6:

[0096] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0097] Step 7:

[0098] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[0099] Step 8:

[0100] The device then provides the user with feedback based on the calculated score, including points, explanations of incorrect answers, and study advice.

[0101] Step 9:

[0102] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[0103] Step 10:

[0104] The server adjusts the settings of the virtual competitor based on the user's stress level and learning effect. For example, if the user's stress level is high, the difficulty of the competitor is lowered, and if the stress level is low, the difficulty is increased.

[0105] Step 11:

[0106] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[0107] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[0108] Example 1

[0109] 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."

[0110] In today's educational environment, efficient and effective learning requires personalized approaches tailored to individual strengths and weaknesses. It is also important to provide learners with a competitive environment to maintain their motivation and maximize their learning outcomes. Furthermore, stress levels must be monitored and adjusted to avoid excessive stress while learning. However, there is still a lack of learning support systems that meet these requirements.

[0111] 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.

[0112] In this invention, the server includes: means for inputting a learner's basic information and learning history; means for transmitting the basic information and learning history to the server; means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner; means for transmitting data on the virtual competitor to the learner's device; means for interacting with and competing with the virtual competitor on the device; means for transmitting the learner's responses and the competition results to the server; means for generating feedback on the learner's responses and the competition results and transmitting the feedback to the device; means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings; means for transmitting the virtual competitor adjustment data to the device; means for setting and adjusting the virtual competitor's behavior pattern and difficulty level using a generative AI model; and means for providing feedback to the learner via a user interface. This provides a personalized competitive environment for the learner, maximizing learning effectiveness through appropriate competition. Furthermore, real-time feedback and adjustments according to the learner's stress level maintain an optimal learning environment.

[0113] A "learner" is an individual who is studying to receive an education.

[0114] "Basic information" refers to basic data about the learner, such as name, age, and school information.

[0115] "Learning history" is information about a learner's learning activities, such as mock test results and progress in classes.

[0116] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0117] A "server" is a computer system used to store and analyze data, generate virtual competitors, and so on.

[0118] A "database" is a collection of data that stores basic information and learning history of learners, managed by a server.

[0119] "Analysis" is the process of examining data to extract patterns and characteristics.

[0120] A "virtual competitor" is a virtual opponent that is generated using machine learning algorithms or generative AI models and competes against the learner.

[0121] "Feedback" is information about a learner's achievements or performance that is provided based on the learner's responses or competition results.

[0122] "Stress level" is a value that indicates the degree of mental stress that a learner feels while studying or competing.

[0123] A "generative AI model" is a type of algorithm or technique that uses artificial intelligence technology to generate data.

[0124] A "user interface" is a screen or operating means that allows a user to operate a system and receive information.

[0125] This invention is a system that collects and analyzes a learner's basic information and learning history to generate a virtual competitor that is optimal for the learner. This system provides a moderate competitive environment, maximizing the effectiveness of learning while managing the learner's stress.

[0126] Initial Setup and Data Collection

[0127] 1. User Registration

[0128] User: The user enters basic information such as their name, age, and school information into the terminal on the initial screen of the system. For example, they might enter "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[0129] Terminal: The terminal generates an HTTP request to send the entered basic information to the server and sends the data to the server.

[0130] Server: The server stores the received basic information in a database and returns a response indicating successful registration to the device.

[0131] 2. Collecting learning history

[0132] User: The user enters the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[0133] Terminal: The terminal sends the input learning history data to the server.

[0134] Server: The server stores the received learning history data in a database.

[0135] Data analysis and virtual competitor generation

[0136] 3. Data Analysis

[0137] Server: The server retrieves basic information and learning history data of the learner from the database and analyzes it using machine learning algorithms (for example, Python's Scikit-learn library). It identifies the learner's strong and weak subjects and learning patterns.

[0138] 4. Creating Virtual Competitors

[0139] Server: Based on the analysis results, the server uses a generative AI model to generate the optimal virtual competitor for the learner. Specifically, it sets the competitor's strong and weak subjects and behavioral patterns.

[0140] Interface, Interaction and Competition

[0141] 5. Transmission of competitor data

[0142] Server: The server sends the data of the generated virtual competitor to the terminal.

[0143] Terminal: The terminal displays the received data on the user interface, allowing the user to check the information of the virtual competitors.

[0144] 6. Dialogue and Competition

[0145] User: A user competes against a virtual opponent through a terminal, such as a mock test. For example, the user starts a mock test and enters their answers to each question.

[0146] Terminal: The terminal compiles the user's answers in real time and simultaneously displays the answers of their virtual competitors.

[0147] Server: The server compiles all answer data in real time and sends the results to the device.

[0148] Feedback and Adjustments

[0149] 7. Stress level feedback

[0150] User: The user enters the stress level they felt during the race into the terminal. For example, they enter "Stress level: 4 (scale of 1 to 5)."

[0151] Device: The device sends the input stress level to the server.

[0152] Server: The server stores the received stress data in a database.

[0153] 8. Adjusting the next competitor

[0154] Server: The server will comprehensively evaluate the received stress level data and learning effect and adjust the settings of the next virtual competitor. For example, if the stress level is high, the number of favorite subjects for the next competitor will be reduced.

[0155] Prompt Sentence Examples

[0156] 1. Enter basic user information

[0157] "Please enter your name, age, and school name as a new user."

[0158] 2. Enter your learning history

[0159] "Please enter your mock test results (score, answer time, and questions you got wrong)."

[0160] 3. Setting up a virtual competitor

[0161] "Virtual competitor data received. Start the conversation."

[0162] 4. Enter your stress level

[0163] "Please rate the stress level you felt during the competition on a scale of 1 to 5 and enter it."

[0164] The system allows learners to effectively learn with virtual competitors that are optimized for their individual needs, and also provides appropriate stress-level measures to maximize learning outcomes.

[0165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0166] Step 1: User Registration

[0167] Input: The user enters basic information such as name, age, and school information into the terminal. For example, "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[0168] Operation:

[0169] User: Enter your name, age, and school information.

[0170] Terminal: Generates an HTTP request and sends the entered basic information to the server.

[0171] Server: Saves the received basic information in the database. If saving is successful, generates a response indicating successful registration and sends it to the device.

[0172] Output: A successful registration response from the server is displayed on the terminal.

[0173] Step 2: Collecting learning history

[0174] Input: The user inputs the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[0175] Operation:

[0176] User: Enter mock test results and class progress.

[0177] Terminal: Generates an HTTP request and sends the entered learning history data to the server.

[0178] Server: Stores the received learning history data in a database.

[0179] Output: Learning history data stored on the server.

[0180] Step 3: Data analysis

[0181] Input: The server retrieves the learner's basic information and learning history data from the database.

[0182] Operation:

[0183] Server: Performs analysis using machine learning algorithms (e.g., Python's Scikit-learn library) to identify learners' strengths and weaknesses and learning patterns.

[0184] Output: The analysis results provide data on the learner's strong and weak subjects, as well as their learning patterns.

[0185] Step 4: Generate a virtual competitor

[0186] Input: The server bases the parsed results.

[0187] Operation:

[0188] Server: Using a generative AI model, it generates a virtual competitor that is optimal for the learner, based on, for example, their strong and weak subjects, behavioral patterns, etc.

[0189] Output: Virtual competitor data is generated.

[0190] Step 5: Submit competitor data

[0191] Input: Server-generated virtual competitor data.

[0192] Operation:

[0193] Server: Sends the virtual competitor data to the device.

[0194] Terminal: Displays the received data in a user interface.

[0195] Output: Information about your virtual competitors will be displayed on your terminal.

[0196] Step 6: Dialogue and competition

[0197] Input: Practice test answers that users enter into the terminal.

[0198] Operation:

[0199] User: Answer practice test questions.

[0200] Terminal: User answers are collected in real time and the answers of virtual competitors are displayed simultaneously.

[0201] Server: Aggregates all answer data in real time.

[0202] Output: Mock test results are displayed in real time and feedback is provided.

[0203] Step 7: Stress Level Feedback

[0204] Input: The user enters their stress level into the device.

[0205] Operation:

[0206] User: Rate their stress level on a scale of 1 to 5 and enter it into the device.

[0207] Device: Sends stress level data to the server.

[0208] Server: Stores the received stress data in a database.

[0209] Output: Stress level data stored on the server.

[0210] Step 8: Adjust your next competitor

[0211] Input: Stress level data and learning effect data stored by the server.

[0212] Operation:

[0213] Server: Comprehensively evaluates the received stress level data and learning effect, and adjusts the settings of the next virtual competitor. For example, if the stress level is high, reduce the number of favorite subjects.

[0214] Output: The configuration data for the next virtual competitor is generated.

[0215] (Application example 1)

[0216] 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."

[0217] In today's educational environment, learners are required to study in an optimal competitive environment. However, real interactions and competitors are not always available, making it difficult for learners to maintain their motivation and learning efficiency. Furthermore, existing systems may not adequately manage stress levels or optimize learning outcomes. A new system using virtual competitors to solve these issues and enable learners to study efficiently and effectively is needed.

[0218] 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.

[0219] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting data of the virtual competitor to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting settings of the virtual competitor, means for transmitting adjustment data of the virtual competitor to the terminal, means for displaying the virtual competitor in three dimensions using a head-mounted display, and means for the learner to experience a realistic competition via the head-mounted display. This allows the learner to efficiently and effectively progress in their learning in an appropriate competitive environment, maximizing learning effectiveness and minimizing stress.

[0220] "Basic information of learners" refers to information that identifies individuals, such as the learner's name, age, and affiliated institution.

[0221] "Learning history" refers to data that records the content, grades, and progress of a learner's past learning.

[0222] A "server" is a computer system for storing, managing, and analyzing data.

[0223] A "database" is a collection of information that systematically stores and manages learners' basic information and learning history.

[0224] A "virtual competitor" is a virtual character or avatar created to compete with the learner.

[0225] A "terminal" is a computing device operated by a learner to exchange data with a server.

[0226] A "head-mounted display" is an output device worn on the head to display visual information.

[0227] "3D display" is a technique for displaying objects in three dimensions, providing the user with a sense of depth.

[0228] "Stress level" is an indicator of the degree of psychological and physiological stress felt by learners.

[0229] "Learning effect" refers to the degree of improvement in knowledge and skills that a learner gains through learning.

[0230] "Response" refers to a reply or answer given by a learner to a task or question.

[0231] "Feedback" refers to evaluation and advice provided based on learner responses and competition results.

[0232] "Adjustment data" refers to specific parameters and information for changing the settings of a virtual competitor.

[0233] "Analysis" is the process of clarifying patterns and characteristics of data using basic information and learning history of learners.

[0234] An "immersive competitive experience" is an experience that allows players to compete in a virtual environment with a feeling close to reality.

[0235] A "generative AI model" is a computational model that uses machine learning algorithms to create new virtual competitors based on data.

[0236] A "prompt" is an instruction or question input to an AI model.

[0237] The present invention is a system that inputs basic information and learning history of a learner, analyzes the data, generates an optimal virtual competitor, and provides the learner with an appropriate competitive environment. A specific method for implementing this system will be described.

[0238] System configuration

[0239] 1. User terminal and head-mounted display

[0240] Learners use smartphones and head-mounted displays (HMDs).

[0241] Provides an interface for entering basic information and learning history of learners.

[0242] 2. Server

[0243] A cloud server (e.g., AWS (registered trademark)) for storing, managing, and analyzing data.

[0244] A database (e.g., Amazon RDS) to store learner data.

[0245] Machine learning algorithms for data analysis and virtual competitor generation (e.g., TENSORFLOW®).

[0246] 3. Database

[0247] Systematically store learner's basic information and learning history.

[0248] It is designed to allow quick access to and analysis of the data you need.

[0249] Program processing

[0250] Initial Setup and Data Collection

[0251] 1. User Registration

[0252] The user uses the terminal to enter basic information (such as name, age, and learning institution information).

[0253] The terminal sends the entered basic information to the server, which stores it in a database.

[0254] 2. Collecting learning history

[0255] Users enter the results of mock exams and progress in classes into the terminal.

[0256] The terminal sends the collected learning history data to the server, which stores it in a database.

[0257] Data analysis and virtual competitor generation

[0258] 3. Data Analysis

[0259] The server analyzes the learner's basic information and learning history stored in the database.

[0260] Using a machine learning algorithm (TensorFlow), we identify learners' strengths, weaknesses, and learning patterns.

[0261] 4. Creating Virtual Competitors

[0262] Based on the analysis results, the most suitable virtual competitor for the learner is generated.

[0263] The virtual competitors are set with difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[0264] Interface, Interaction and Competition

[0265] 5. Transmission of competitor data

[0266] The server transmits data of the generated virtual competitor to the terminal.

[0267] The user uses a head-mounted display to visually see their virtual opponent in 3D.

[0268] 6. Dialogue and Competition

[0269] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[0270] The terminal compiles the user's responses and the answers of the virtual competitors in real time and provides feedback.

[0271] Feedback and Adjustments

[0272] 7. Stress Level Monitoring

[0273] An interface is provided for users to input the stress level they felt during the competition.

[0274] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[0275] 8. Strengthening or weakening virtual competitors

[0276] The server adjusts the settings of the next virtual competitor based on the received data.

[0277] Dynamically adjust the difficulty of the virtual competitor according to the learner's perceived stress level and learning effectiveness.

[0278] Specific examples

[0279] 1. Example of entering basic user information

[0280] When a new candidate uses the system, they enter their name, age, name of their learning institution, etc. into the terminal.

[0281] The device sends this basic information to the server, which stores it in a database.

[0282] 2. Learning history input and analysis example

[0283] Candidates take the mock test and enter the results into a terminal, which records the score, answer time, and questions answered incorrectly in detail.

[0284] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[0285] 3. Example of Virtual Competitor Generation

[0286] The analysis results indicate that the test-taker is good at mathematics but weak at English.

[0287] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[0288] 4. Examples of dialogue and competition

[0289] When a candidate takes a mock test on their device, they are presented with a scenario in which a virtual competitor is also taking the test at the same time.

[0290] When the user uses a head-mounted display, the virtual opponent is displayed in three dimensions and provides real-time feedback.

[0291] Prompt Sentence Examples

[0292] Describe the steps for users to enter their learning history and save it on a cloud server. Next, develop a system that uses a machine learning algorithm to generate a virtual opponent based on that data and competes with the learner in real time. Specifically, describe the flow, including analysis using TensorFlow, data storage on AWS, and real-time updates to the user interface.

[0293] In this way, the present invention is designed to help learners study efficiently and effectively, and by providing an immersive competitive experience using a head-mounted display, it is possible to maximize learning effectiveness while minimizing stress.

[0294] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0295] Step 1:

[0296] User Registration

[0297] The user uses a smartphone or head-mounted display to input basic information (such as name, age, and information about the institution of study). The input basic information is sent from the device to the server. The server stores the received basic information in a database. The input is basic information, and the output is the basic information stored in the database.

[0298] Step 2:

[0299] Collection of learning history

[0300] Users enter mock test results and lesson progress into their terminal. The entered learning history data is sent from the terminal to the server. The server stores the received learning history data in a database. The input is learning history data, and the output is the learning history stored in the database.

[0301] Step 3:

[0302] Data analysis

[0303] The server retrieves the learner's basic information and learning history stored in the database. Using a machine learning algorithm (TensorFlow), it performs analysis to identify the learner's strong and weak subjects and learning patterns. The input is basic information and learning history data, and the output is the analysis results of the learner's strong and weak subjects and learning patterns.

[0304] Step 4:

[0305] Virtual Competitor Creation

[0306] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The generated virtual competitor is registered with settings, personality, and behavior patterns that correspond to the learner's strong and weak subjects. The input is the analysis results, and the output is data on the generated virtual competitor.

[0307] Step 5:

[0308] Submitting competitor data

[0309] The server sends the generated virtual competitor data to the terminal. The user can visually confirm the virtual competitor in 3D using a head-mounted display. The input is the virtual competitor data, and the output is the 3D virtual competitor displayed on the head-mounted display.

[0310] Step 6:

[0311] Dialogue and Competition

[0312] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions. The terminals compile the user's responses and the answers of the virtual competitors in real time and send them to a server. The input is the responses of the user and the virtual competitors, and the output is the compiled results.

[0313] Step 7:

[0314] Generate feedback

[0315] The server generates feedback based on the learner's responses and the competition results. The generated feedback is sent to the terminal and provided to the user. The inputs are the learner's responses and the competition results, and the output is the generated feedback.

[0316] Step 8:

[0317] Stress level monitoring

[0318] Users input the stress level they felt during the competition. The input stress level data is sent from the device to the server. The server uses this data to adjust future dialogue settings and the difficulty of the competition. The input is stress level data, and the output is the adjusted difficulty setting for the competition.

[0319] Step 9:

[0320] Strengthening or weakening virtual competitors

[0321] The server adjusts the settings of the next virtual competitor based on the received data. It dynamically adjusts the difficulty of the virtual competitor according to the learner's stress level and learning effect. The input is the received data and feedback, and the output is the adjusted settings of the virtual competitor.

[0322] 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.

[0323] System Overview and Operation

[0324] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[0325] Program processing overview

[0326] Initial Setup and Data Collection

[0327] 1. User Registration

[0328] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[0329] The terminal sends the entered basic information to the server, which stores it in a database.

[0330] 2. Collecting learning history

[0331] Users enter the results of mock exams and progress in classes into the terminal.

[0332] The terminal sends the collected learning history data to the server, which stores it in a database.

[0333] 3. Collecting Emotional Data

[0334] While the user is using the device to study or take a practice test, the device collects facial and voice data through its camera and microphone.

[0335] The emotion engine analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[0336] The terminal transmits the emotion data analyzed by the emotion engine to the server.

[0337] Data analysis and virtual competitor generation

[0338] 4. Data Analysis

[0339] The server analyzes the basic information, learning history, and emotional data stored in the database.

[0340] The server uses machine learning algorithms to identify a learner's strengths and weaknesses, learning patterns, and emotional state.

[0341] 5. Creating Virtual Competitors

[0342] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[0343] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[0344] Interface, Interaction and Competition

[0345] 6. Transmission of competitor data

[0346] The server transmits data of the generated virtual competitor to the terminal.

[0347] The terminal prepares to display the virtual competitor on the user interface based on the received data.

[0348] 7. Dialogue and Competition

[0349] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0350] The user and the virtual competitor proceed through mock tests and study sessions.

[0351] Feedback and Adjustments

[0352] 1. Providing Feedback

[0353] The device compiles the results of practice tests and study sessions and provides feedback to the user, including scores, explanations of incorrect answers, and study advice.

[0354] 2. Utilizing Emotional Data

[0355] The emotion engine monitors the user's emotional state during the learning session and transmits it to the server.

[0356] The server dynamically adjusts the behavior and dialogue scripts of the virtual competitors based on the emotional data.

[0357] 3. Stress management and difficulty adjustment

[0358] Based on the user's stress level and learning effect, the server adjusts the virtual competitor's settings. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the stress level is low, the server raises the difficulty.

[0359] Specific examples

[0360] 1. Example of entering basic information and learning history

[0361] To use the system for the first time, examinee C enters basic information and the results of the mock test on a terminal. The terminal sends this data to the server, which then stores it in a database.

[0362] 2. Emotion data collection and analysis example

[0363] While Candidate C is taking the mock exam, the device's camera and microphone collect facial and voice data, which the emotion engine analyzes to assess stress and concentration levels.

[0364] The analysis results (e.g., "I'm anxious during the exam," "I'm concentrating," etc.) are sent to the server.

[0365] 3. Virtual Competitor Creation and Interaction Examples

[0366] Based on the analysis results, the server generates the optimal virtual competitor for test-taker C. For example, it sets a well-balanced competitor who is good at English and also fairly good at mathematics.

[0367] When Test Taker C takes a mock test with the virtual competitor in his next study session, the competitor answers in real time, and the dialogue continues.

[0368] 4. Feedback and Adjustment Examples

[0369] After the mock test is completed, the device displays the results (score, explanations of incorrect answers, etc.) and also provides feedback based on emotional data.

[0370] When Test Taker C enters his / her satisfaction and stress level from the study session into his / her device, the server uses this information to adjust the settings of the virtual competitor and reflect them in the next session.

[0371] In this way, the present invention, which is combined with an emotion engine, can provide an optimal learning environment while taking into account the user's emotional state, thereby maximizing learning effectiveness.

[0372] The processing flow will be explained below.

[0373] Step 1:

[0374] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[0375] Step 2:

[0376] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[0377] Step 3:

[0378] While a user is using the device to study or take a practice test, the device transmits facial and voice data via a camera and microphone to the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[0379] Step 4:

[0380] The device sends the emotional data analyzed by the emotion engine to the server, which stores it in a database and integrates it with previous learning history for further analysis.

[0381] Step 5:

[0382] The server analyzes the basic information, learning history, and emotional data stored in the database, and uses machine learning algorithms to identify the learner's strengths and weaknesses, learning patterns, and emotional state.

[0383] Step 6:

[0384] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The virtual competitor is set to a level of difficulty, personality, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[0385] Step 7:

[0386] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[0387] Step 8:

[0388] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0389] Step 9:

[0390] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[0391] Step 10:

[0392] The device compiles the test results and emotional data and provides feedback to the user, including the score, explanations of incorrect answers, and study advice.

[0393] Step 11:

[0394] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[0395] Step 12:

[0396] The server adjusts the virtual competitor's settings based on the user's stress level, learning effect, and emotional data. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the user's stress level is low, the server raises the difficulty.

[0397] Step 13:

[0398] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[0399] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[0400] Example 2

[0401] 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."

[0402] Today's learners face diverse learning environments, requiring optimal learning support tailored to their individual learning styles and emotional states. However, traditional learning systems do not take the user's emotional state into account, making it difficult to provide a personalized, competitive environment that maximizes learning efficiency. Furthermore, there are a lack of methods to enhance learning effectiveness while appropriately managing learners' stress levels. This makes it difficult for learners to maintain their motivation to study.

[0403] 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.

[0404] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for collecting emotional data from the user's terminal during learning and practice tests, means for transmitting the emotional data to the server, means for analyzing the basic information, learning history, and emotional data from the database and generating a virtual competitor optimal for the learner, means for transmitting data on the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the results of the competition to the server, means for generating feedback on the learner's responses, the results of the competition, and the emotional data and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the settings of the virtual competitor, and means for transmitting adjustment data on the virtual competitor to the terminal. This makes it possible to provide an optimal learning environment and manage stress to maximize learning efficiency while taking the learner's emotional state into consideration.

[0405] "Learner" refers to the person receiving education and the entity using the system.

[0406] "Basic information" refers to personal information such as the learner's name, age, and school information.

[0407] "Learning history" refers to information about a learner's past learning activities, such as mock test results and class progress.

[0408] A "terminal" is a device used by learners to input and output information. Examples include personal computers and smartphones.

[0409] A "server" refers to a computer system that performs processes such as storing, analyzing, sending and receiving data.

[0410] A "database" refers to a system that systematically stores and manages data such as basic information, learning history, and emotional data.

[0411] "Emotional data" refers to data on the emotional state of a learner obtained from facial expressions, voice, etc.

[0412] "Emotion engine" refers to software or algorithms used to analyze emotion data and identify a learner's emotional state.

[0413] "Virtual competitor" refers to a virtual competitor corresponding to a learner, which is generated according to the characteristics of the learner.

[0414] "Dialogue script" refers to the language and behavioural scenarios that a virtual competitor uses in dialogue with learners.

[0415] "Feedback" refers to evaluations and advice provided based on learners' learning results and emotional data.

[0416] "Stress level" refers to the degree of stress a learner feels while studying.

[0417] "Learning outcomes" refer to the results and improvement in knowledge that learners achieve through learning activities.

[0418] "Adjustment Data" refers to data for modifying the settings of a virtual competitor.

[0419] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[0420] Hardware and software used

[0421] The present invention uses the following hardware and software:

[0422] Device: The device used by the learner, such as a computer, tablet, or smartphone.

[0423] Server: A computer system that stores, analyzes, sends and receives data. For example, a cloud-based server can be used.

[0424] Database: A system that systematically stores and manages basic information, learning history, emotional data, etc. Specifically, database systems such as MySQL (registered trademark) and MongoDB are used.

[0425] Emotion engine: Software or algorithms for analyzing emotion data and identifying the learner's emotional state, specifically using Python's OpenCV or Google® Cloud Speech-to-Text API.

[0426] Machine learning algorithm: The algorithm used for analysis processing, specifically Scikit-learn and TensorFlow.

[0427] Specific explanation of the system

[0428] User registration and basic information entry

[0429] The user uses the terminal to enter basic information (such as name, age, school information, etc.). The user enters this information into the input form displayed on the terminal screen and presses the "Submit" button. The entered basic information is sent from the terminal to the server, which then stores it in a database.

[0430] Collection of learning history

[0431] Users enter their mock test results and progress in classes into the device. The device then sends the entered learning history data to the server, which then stores it in a database. For example, this data might include "Math: 85 points, English: 90 points, Science: 78 points, Social Studies: 82 points."

[0432] Emotion data collection and analysis

[0433] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data. The emotion engine analyzes this data in real time to identify the user's emotional state. For example, emotions such as "nervous" or "concentrated" may be identified, and the analysis results are sent from the device to the server.

[0434] Data analysis and virtual competitor generation

[0435] The server analyzes the basic information, learning history, and emotional data stored in the database. It uses machine learning algorithms to identify the learner's strong and weak subjects, learning patterns, and emotional state. Based on this, it generates the optimal virtual competitor. For example, if a learner is weak in English but good at math, it will generate a virtual competitor accordingly.

[0436] User Interface and Competitor View

[0437] The server transmits data about the generated virtual competitor to the terminal. The terminal prepares to display the virtual competitor on the user interface based on the received data. The user can then start interacting with the virtual competitor via the terminal and proceed with the mock test or learning session.

[0438] Providing feedback and making adjustments

[0439] The results of mock tests and study sessions are sent from the device to a server. The server then generates feedback based on this information and provides it to the learner. The feedback includes the student's score, explanations for incorrect answers, and study advice. Furthermore, the system dynamically adjusts the virtual competitor's settings based on the emotional data and reflects them in the next session. For example, if the user's stress level is high, the system may adjust the difficulty of the virtual competitor.

[0440] Specific examples

[0441] 1. After entering user information

[0442] Name: Yamada Taro

[0443] Age: 17

[0444] School information: 〇〇High School

[0445] 2. Example of mock test result input

[0446] Mock exam results:

[0447] Mathematics: 85 points

[0448] English: 90 points

[0449] Science: 78 points

[0450] Social: 82 points

[0451] 3. Example of emotion data analysis

[0452] Emotions during exams: Impatience

[0453] Concentration: High

[0454] Expression: Tense

[0455] 4. Examples of Providing Feedback

[0456] Mock exam results:

[0457] Score: 85 points

[0458] Wrong answer: Question 5, Question 8

[0459] Study advice: Focus on grammar next time

[0460] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0461] Step 1:

[0462] User Registration

[0463] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[0464] Input: The user enters their name, age, and school information into the input form on the device and presses the "Submit" button.

[0465] Data processing and calculation: The device formats this information and sends it to the server using the HTTPS protocol.

[0466] Output: The server stores the received basic information in a database.

[0467] Specific behavior: The device detects user input in real time and displays a confirmation message after submission.

[0468] Step 2:

[0469] Collection of learning history

[0470] Users enter the results of mock exams and progress in classes into the terminal.

[0471] Input: The user enters the scores for each subject in the mock test and presses the submit button.

[0472] Data processing and calculation: The terminal converts the input data into JSON format and sends it to the server.

[0473] Output: The server stores the received learning history in a database.

[0474] What happens: The terminal validates the input data, displays warning messages if necessary, and displays a confirmation message after the data has been sent.

[0475] Step 3:

[0476] Collecting Emotional Data

[0477] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data.

[0478] Input: The device collects the user's facial expressions and voice in real time using a camera and microphone while learning.

[0479] Data processing and calculation: The emotion engine processes the collected facial expression data and analyzes the voice data to identify the user's emotional state (e.g., joy, tension, impatience).

[0480] Output: The analysis results (emotion data) are sent to the server and stored in a database.

[0481] Specific operation: The device periodically collects data and sends it to the server at each collection interval. The device is designed not to notify the user when data is collected.

[0482] Step 4:

[0483] Data analysis

[0484] The server analyzes the basic information, learning history, and emotional data stored in the database.

[0485] Input: The server retrieves basic information, learning history, and emotion data from the database.

[0486] Data processing and computation: Use machine learning algorithms (e.g., Scikit-learn, TensorFlow) to identify strengths and weaknesses, learning patterns, and emotional states.

[0487] Output: The analysis results are output as data that can be used to generate virtual competitors.

[0488] Specific operation: The server periodically executes the analysis task and stores the results in a database. The server is also configured to provide immediate feedback to the learner on the analysis results.

[0489] Step 5:

[0490] Virtual Competitor Creation

[0491] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[0492] Input: Basic information, learning history, and analysis results of emotion data.

[0493] Data processing and calculation: Based on the analysis results, the server sets the virtual competitor's strong and weak subjects, personality, and behavioral patterns.

[0494] Output: Virtual competitor data is generated and sent to the terminal.

[0495] What it does: The server automatically adjusts the virtual competitor settings to generate a competitor customized to the user's learning needs.

[0496] Step 6:

[0497] Submitting and Displaying Competitor Data

[0498] The server transmits data of the generated virtual competitor to the terminal.

[0499] Input: Virtual competitor data.

[0500] Data processing and calculation: The server converts the data into an appropriate format and sends it to the terminal.

[0501] Output: The terminal receives data to display the virtual competitors in the user interface.

[0502] Specific operation: When the terminal receives the competitor's data, it displays it on the screen and provides an interface that allows the user to interact with the competitor.

[0503] Step 7:

[0504] Dialogue and Competition

[0505] The user initiates a dialogue with a virtual competitor via the terminal.

[0506] Input: User interactions and responses to competitions.

[0507] Data processing and calculation: The terminal generates responses based on the dialogue script received from the server and processes the competition results in real time.

[0508] Output: The device sends the progress of the interaction and competition to the server.

[0509] Specific operation: The terminal processes user input in real time and displays the responses of virtual competitors according to the dialogue script. The competition results are periodically sent to the server.

[0510] Step 8:

[0511] Providing feedback

[0512] The server generates feedback based on the results of the learning session.

[0513] Input: Competition results, sentiment data, user responses.

[0514] Data processing and calculation: The server aggregates this data and generates feedback, including incorrect answers and study advice.

[0515] Output: The generated feedback is sent to the device.

[0516] What happens: The device notifies the user of the feedback and displays details on the screen, including the score and areas for improvement.

[0517] Step 9:

[0518] Monitor and regulate stress levels

[0519] The emotion engine monitors the user's stress level and transmits it to the server.

[0520] Input: Facial and voice data of the user during training.

[0521] Data processing and computation: Analyzes emotional state to identify stress levels and adjusts virtual competitor settings accordingly.

[0522] Output: The adjustment data is sent to the device and reflected in the next training session.

[0523] How it works: The server analyzes emotional data in real time and dynamically adjusts the difficulty and dialogue scripts of competitors.

[0524] (Application example 2)

[0525] 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."

[0526] Conventional learning systems often provide a uniform learning environment without considering the learner's emotional state or stress level. This makes it difficult for some learners to learn effectively, hindering efficient acquisition. Furthermore, it is not possible to provide optimal competition for each individual learner, leaving challenges in maintaining motivation and improving comprehension.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0528] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the competition results to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings, means for transmitting adjustment data of the virtual competitor to the terminal, means for analyzing the learner's emotional state during learning using an emotion engine and dynamically adjusting the learning environment, and means for analyzing the learner's stress level in real time based on raw data and adjusting interactions during learning. This provides an optimal learning environment that takes the learner's emotional state and stress level into consideration, enabling efficient learning and maximizing learning effects.

[0529] "Learner" refers to a person who acquires knowledge and skills in accordance with an educational program or curriculum.

[0530] "Basic information" refers to information for identifying a learner, such as the learner's name, age, and school information.

[0531] "Learning history" is a record of a learner's past mock test results, progress in classes, and so on.

[0532] "Server" refers to a computer system that stores data, analyzes data, generates feedback, etc.

[0533] A "database" is a system that organizes and stores data such as basic information and learning history.

[0534] A "virtual competitor" refers to a virtual entity that competes with learners in learning progress, mock exams, etc.

[0535] "Devices" refer to information devices such as smartphones, tablets, and personal computers used by learners.

[0536] An "emotion engine" is an algorithm or program that analyzes a learner's emotional state from their facial expressions, voice, etc.

[0537] "Stress level" refers to the degree of mental tension a learner feels while studying.

[0538] "Feedback" refers to advice and evaluation provided based on learners' responses and competition results.

[0539] "Interaction" refers to the process of interaction between learners and virtual competitors during learning.

[0540] System Overview

[0541] This invention is a system related to "student," "basic information," "learning history," "server," "database," "virtual competitor," "terminal," "emotion engine," "stress level," "feedback," and "interaction." The aim is to maximize the learning effect of learners, and in particular to provide an optimal learning environment by utilizing the virtual competitor and emotion engine.

[0542] Technology used

[0543] The system is implemented using the following technologies:

[0544] 1. Database Management System: MySQL

[0545] 2. Backend: Python (Django Framework)

[0546] 3. Frontend: React Native

[0547] 4. Emotion engine: OpenAI (registered trademark) API (emotion analysis model)

[0548] 5. Real-time communication: WebSocket

[0549] Process Overview

[0550] 1. User registration and information entry

[0551] Learners enter basic information (such as name, age, and school information) through their devices. The data entered on the devices is sent to and stored in a MySQL database through the back-end Django framework.

[0552] 2. Collecting learning history

[0553] Students enter their mock exam results and class progress information into the terminal, and the input data is stored in a MySQL database via a Django application.

[0554] 3. Emotional Data Collection and Analysis

[0555] During training, facial and voice data is collected via the device's camera and microphone. The collected data is then analyzed using the OpenAI API, and the results are sent to the server in real time.

[0556] 4. Creating Virtual Competitors

[0557] A machine learning algorithm built in Python uses stored basic information, learning history, and emotional data to generate the optimal virtual competitor.

[0558] 5. Dialogue and Competition

[0559] The virtual competitor data is displayed on a terminal interface built with React Native, and WebSocket is used to realize real-time interaction between learners and virtual competitors.

[0560] 6. Feedback and Adjustments

[0561] Feedback generated based on the competition results and the learner's stress level is sent to the device, which monitors the learner's stress level in real time and dynamically adjusts the virtual competitor's settings.

[0562] Specific examples

[0563] For example, when a learner starts a math mock test, the device's camera and microphone collect emotional data through facial expressions and voice, which is then analyzed through the OpenAI API. The analysis results are sent to the server, which generates the optimal virtual competitor. The virtual competitor then solves the mock test together in real time, which is displayed via React Native. Feedback is generated based on the learner's responses and the competition results, and sent to the device. The difficulty level of the virtual competitor and the dialogue script are dynamically adjusted based on the learner's stress level.

[0564] Prompt statement

[0565] Below are some example prompts for sentiment analysis:

[0566] Please rate the test taker's level of impatience and concentration based on the following statements:

[0567] "Throughout the exam, he would often take deep breaths and stare at the questions with furrowed brows. After a moment, he would grip his pen tighter, clearly confused."

[0568] Through these methods, an optimal learning environment is provided that takes into account the learner's emotional state and stress level.

[0569] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0570] Step 1:

[0571] The user enters basic information

[0572] The user enters basic information (such as name, age, school information, etc.) through the terminal. This input data is temporarily saved on the terminal and then sent to the server. Specifically, a basic information form is displayed, the user fills in the required fields, and when the user presses the data submit button, the data is sent to the server via the Django framework.

[0573] Input: Basic information data

[0574] Output: Basic information sent to the server

[0575] Step 2:

[0576] The server stores basic information in a database

[0577] The server stores the received basic information in a database, and the Django framework generates and executes commands to insert the received data into a MySQL database.

[0578] Input: Received basic information data

[0579] Output: Basic information stored in the database

[0580] Step 3:

[0581] The user enters their learning history

[0582] Users enter their mock test results and progress in classes into their devices. The data entered by the user is temporarily saved and then sent to the server. After filling out the form on the device, the data is sent to the server and received.

[0583] Input: Learning history data

[0584] Output: Learning history sent to the server

[0585] Step 4:

[0586] The server saves the learning history in a database

[0587] The server stores the received learning history data in a database. The Django framework generates and executes commands to insert the received data into a MySQL database.

[0588] Input: Received learning history data

[0589] Output: Learning history stored in the database

[0590] Step 5:

[0591] Collect user sentiment data

[0592] During learning, the camera and microphone on the user's device (smartphone, smart glasses, head-mounted display) collect facial expressions and voice. This data is temporarily stored in the device's local memory. Specifically, the camera and microphone are programmed to automatically start collecting data as soon as learning begins.

[0593] Input: facial expression and voice data

[0594] Output: Temporarily saved emotion data

[0595] Step 6:

[0596] Analyzing emotional data with an emotion engine

[0597] The emotion data stored on the device is analyzed by the emotion engine using the OpenAI API, and the analysis results are output as stress levels and emotional states and sent to the server.

[0598] Input: Temporarily saved emotion data

[0599] Output: Analyzed emotional data (stress level, emotional state)

[0600] Step 7:

[0601] The server analyzes basic information, learning history, and emotional data.

[0602] The server uses machine learning algorithms to analyze the basic information, learning history, and emotional data stored in the database. As a result, it generates the most suitable virtual competitor for the learner. Specifically, a machine learning algorithm written in Python is used to analyze the data and generate a model.

[0603] Input: Basic information, learning history, emotional data

[0604] Output: Virtual competitor data

[0605] Step 8:

[0606] The server sends the virtual competitor data to the terminal.

[0607] The server sends the generated virtual competitor data to the terminal using the Django framework and WebSocket for real-time communication.

[0608] Input: Virtual competitor data

[0609] Output: Virtual competitor data sent to the terminal

[0610] Step 9:

[0611] Users can interact and compete with virtual competitors

[0612] Users interact and compete with virtual opponents displayed on their devices, and interactions are managed in real time through React Native, including answering multiple-choice questions and chat-style conversations.

[0613] Input: Virtual competitor data sent to the terminal

[0614] Output: Interaction and competition results

[0615] Step 10:

[0616] The device sends the results of the competition to the server.

[0617] The user's competition results are sent from the terminal to the server. Data during the competition is collected in real time and sent to the server through the Django framework.

[0618] Input: Dialogue and competition results

[0619] Output: Interaction and competition results sent to the server

[0620] Step 11:

[0621] The server generates feedback and sends it to the device

[0622] The server generates feedback based on the received competition result data. The feedback includes points scored, incorrect answers, and study advice. The generated feedback is sent to the device.

[0623] Input: Dialogue and competition results

[0624] Output: Feedback data

[0625] Step 12:

[0626] Users can review the feedback and apply it to their next learning.

[0627] Users can check the feedback displayed on their devices and use it to improve their learning, leading to more effective learning in the next session. Specifically, they can use the feedback to revise and improve their learning plan.

[0628] Input: Feedback data

[0629] Output: Maximized learning effect

[0630] 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.

[0631] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0632] 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.

[0633] [Second embodiment]

[0634] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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."

[0646] System Overview and Operation

[0647] This system inputs basic information and learning history of a learner and analyzes that data to generate a virtual opponent that is optimal for the learner. This system provides a moderate competitive environment, maximizing learning effectiveness while managing stress.

[0648] Program processing overview

[0649] Initial Setup and Data Collection

[0650] 1. User Registration

[0651] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[0652] The terminal sends the entered basic information to the server, which stores it in a database.

[0653] 2. Collecting learning history

[0654] Users enter the results of mock exams and progress in classes into the terminal.

[0655] The terminal sends the collected learning history data to the server, which stores it in a database.

[0656] Data analysis and virtual competitor generation

[0657] 3. Data Analysis

[0658] The server analyzes the learner's basic information and learning history stored in the database, and identifies the learner's strong and weak subjects and learning patterns.

[0659] This analysis uses machine learning algorithms to accurately evaluate the learner's characteristics.

[0660] 4. Creating Virtual Competitors

[0661] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[0662] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[0663] Interface, Interaction and Competition

[0664] 5. Transmission of competitor data

[0665] The server transmits data of the generated virtual competitor to the terminal.

[0666] The receiving terminal displays the virtual competitor on the user interface.

[0667] 6. Dialogue and Competition

[0668] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[0669] The terminal compiles the user's answers and those of the virtual competitors in real time and provides feedback to the user.

[0670] Specific examples

[0671] 1. Example of entering basic user information

[0672] Candidate B is using the system for the first time, so he enters his name, age, school name, etc. on the terminal.

[0673] The device sends this basic information to the server, which stores it in a database.

[0674] 2. Learning history input and analysis example

[0675] Candidate B takes the mock test and enters the results into the terminal. The results are recorded in detail, including the score, answer time, and questions answered incorrectly.

[0676] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[0677] 3. Example of Virtual Competitor Generation

[0678] The analysis results indicate that candidate B is good at math but not so good at English.

[0679] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[0680] 4. Examples of dialogue and competition

[0681] When Candidate B takes a mock test on his device, a scenario is displayed in which a virtual competitor is also taking the test at the same time.

[0682] Results are displayed in real time and feedback is provided based on this.

[0683] Feedback and Adjustments

[0684] Stress level feedback from users

[0685] Candidate B enters the stress level he or she felt during the competition.

[0686] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[0687] Strengthening or weakening virtual competitors

[0688] The server will comprehensively evaluate the stress level and learning effect of test-taker B and adjust the settings of the next virtual competitor.

[0689] For example, if you feel too stressed, lower the difficulty of your competitors, and conversely, if you have more time, increase the difficulty.

[0690] In this way, the present invention is designed to allow test takers to study hard in an optimal learning environment, and to maximize the learning effect through moderate competition.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[0694] Step 2:

[0695] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[0696] Step 3:

[0697] The server analyzes the basic information and learning history stored in the database and uses machine learning algorithms to identify the learner's strengths, weaknesses, and learning patterns.

[0698] Step 4:

[0699] Based on the analysis results, the server generates the virtual competitor that is best suited for the learner. The server creates the virtual competitor's data (character settings, behavior patterns, difficulty level, etc.).

[0700] Step 5:

[0701] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[0702] Step 6:

[0703] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0704] Step 7:

[0705] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[0706] Step 8:

[0707] The device then provides the user with feedback based on the calculated score, including points, explanations of incorrect answers, and study advice.

[0708] Step 9:

[0709] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[0710] Step 10:

[0711] The server adjusts the settings of the virtual competitor based on the user's stress level and learning effect. For example, if the user's stress level is high, the difficulty of the competitor is lowered, and if the stress level is low, the difficulty is increased.

[0712] Step 11:

[0713] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[0714] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[0715] Example 1

[0716] 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."

[0717] In today's educational environment, efficient and effective learning requires personalized approaches tailored to individual strengths and weaknesses. It is also important to provide learners with a competitive environment to maintain their motivation and maximize their learning outcomes. Furthermore, stress levels must be monitored and adjusted to avoid excessive stress while learning. However, there is still a lack of learning support systems that meet these requirements.

[0718] 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.

[0719] In this invention, the server includes: means for inputting a learner's basic information and learning history; means for transmitting the basic information and learning history to the server; means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner; means for transmitting data on the virtual competitor to the learner's device; means for interacting with and competing with the virtual competitor on the device; means for transmitting the learner's responses and the competition results to the server; means for generating feedback on the learner's responses and the competition results and transmitting the feedback to the device; means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings; means for transmitting the virtual competitor adjustment data to the device; means for setting and adjusting the virtual competitor's behavior pattern and difficulty level using a generative AI model; and means for providing feedback to the learner via a user interface. This provides a personalized competitive environment for the learner, maximizing learning effectiveness through appropriate competition. Furthermore, real-time feedback and adjustments according to the learner's stress level maintain an optimal learning environment.

[0720] A "learner" is an individual who is studying to receive an education.

[0721] "Basic information" refers to basic data about the learner, such as name, age, and school information.

[0722] "Learning history" is information about a learner's learning activities, such as mock test results and progress in classes.

[0723] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0724] A "server" is a computer system used to store and analyze data, generate virtual competitors, and so on.

[0725] A "database" is a collection of data that stores basic information and learning history of learners, managed by a server.

[0726] "Analysis" is the process of examining data to extract patterns and characteristics.

[0727] A "virtual competitor" is a virtual opponent that is generated using machine learning algorithms or generative AI models and competes against the learner.

[0728] "Feedback" is information about a learner's achievements or performance that is provided based on the learner's responses or competition results.

[0729] "Stress level" is a value that indicates the degree of mental stress that a learner feels while studying or competing.

[0730] A "generative AI model" is a type of algorithm or technique that uses artificial intelligence technology to generate data.

[0731] A "user interface" is a screen or operating means that allows a user to operate a system and receive information.

[0732] This invention is a system that collects and analyzes a learner's basic information and learning history to generate a virtual competitor that is optimal for the learner. This system provides a moderate competitive environment, maximizing the effectiveness of learning while managing the learner's stress.

[0733] Initial Setup and Data Collection

[0734] 1. User Registration

[0735] User: The user enters basic information such as their name, age, and school information into the terminal on the initial screen of the system. For example, they might enter "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[0736] Terminal: The terminal generates an HTTP request to send the entered basic information to the server and sends the data to the server.

[0737] Server: The server stores the received basic information in a database and returns a response indicating successful registration to the device.

[0738] 2. Collecting learning history

[0739] User: The user enters the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[0740] Terminal: The terminal sends the input learning history data to the server.

[0741] Server: The server stores the received learning history data in a database.

[0742] Data analysis and virtual competitor generation

[0743] 3. Data Analysis

[0744] Server: The server retrieves basic information and learning history data of the learner from the database and analyzes it using machine learning algorithms (for example, Python's Scikit-learn library). It identifies the learner's strong and weak subjects and learning patterns.

[0745] 4. Creating Virtual Competitors

[0746] Server: Based on the analysis results, the server uses a generative AI model to generate the optimal virtual competitor for the learner. Specifically, it sets the competitor's strong and weak subjects and behavioral patterns.

[0747] Interface, Interaction and Competition

[0748] 5. Transmission of competitor data

[0749] Server: The server sends the data of the generated virtual competitor to the terminal.

[0750] Terminal: The terminal displays the received data on the user interface, allowing the user to check the information of the virtual competitors.

[0751] 6. Dialogue and Competition

[0752] User: A user competes against a virtual opponent through a terminal, such as a mock test. For example, the user starts a mock test and enters their answers to each question.

[0753] Terminal: The terminal compiles the user's answers in real time and simultaneously displays the answers of their virtual competitors.

[0754] Server: The server compiles all answer data in real time and sends the results to the device.

[0755] Feedback and Adjustments

[0756] 7. Stress level feedback

[0757] User: The user enters the stress level they felt during the race into the terminal. For example, they enter "Stress level: 4 (scale of 1 to 5)."

[0758] Device: The device sends the input stress level to the server.

[0759] Server: The server stores the received stress data in a database.

[0760] 8. Adjusting the next competitor

[0761] Server: The server will comprehensively evaluate the received stress level data and learning effect and adjust the settings of the next virtual competitor. For example, if the stress level is high, the number of favorite subjects for the next competitor will be reduced.

[0762] Prompt Sentence Examples

[0763] 1. Enter basic user information

[0764] "Please enter your name, age, and school name as a new user."

[0765] 2. Enter your learning history

[0766] "Please enter your mock test results (score, answer time, and questions you got wrong)."

[0767] 3. Setting up a virtual competitor

[0768] "Virtual competitor data received. Start the conversation."

[0769] 4. Enter your stress level

[0770] "Please rate the stress level you felt during the competition on a scale of 1 to 5 and enter it."

[0771] The system allows learners to effectively learn with virtual competitors that are optimized for their individual needs, and also provides appropriate stress-level measures to maximize learning outcomes.

[0772] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0773] Step 1: User Registration

[0774] Input: The user enters basic information such as name, age, and school information into the terminal. For example, "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[0775] Operation:

[0776] User: Enter your name, age, and school information.

[0777] Terminal: Generates an HTTP request and sends the entered basic information to the server.

[0778] Server: Saves the received basic information in the database. If saving is successful, generates a response indicating successful registration and sends it to the device.

[0779] Output: A successful registration response from the server is displayed on the terminal.

[0780] Step 2: Collecting learning history

[0781] Input: The user inputs the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[0782] Operation:

[0783] User: Enter mock test results and class progress.

[0784] Terminal: Generates an HTTP request and sends the entered learning history data to the server.

[0785] Server: Stores the received learning history data in a database.

[0786] Output: Learning history data stored on the server.

[0787] Step 3: Data analysis

[0788] Input: The server retrieves the learner's basic information and learning history data from the database.

[0789] Operation:

[0790] Server: Performs analysis using machine learning algorithms (e.g., Python's Scikit-learn library) to identify learners' strengths and weaknesses and learning patterns.

[0791] Output: The analysis results provide data on the learner's strong and weak subjects, as well as their learning patterns.

[0792] Step 4: Generate a virtual competitor

[0793] Input: The server bases the parsed results.

[0794] Operation:

[0795] Server: Using a generative AI model, it generates a virtual competitor that is optimal for the learner, based on, for example, their strong and weak subjects, behavioral patterns, etc.

[0796] Output: Virtual competitor data is generated.

[0797] Step 5: Submit competitor data

[0798] Input: Server-generated virtual competitor data.

[0799] Operation:

[0800] Server: Sends the virtual competitor data to the device.

[0801] Terminal: Displays the received data in a user interface.

[0802] Output: Information about your virtual competitors will be displayed on your terminal.

[0803] Step 6: Dialogue and competition

[0804] Input: Practice test answers that users enter into the terminal.

[0805] Operation:

[0806] User: Answer practice test questions.

[0807] Terminal: User answers are collected in real time and the answers of virtual competitors are displayed simultaneously.

[0808] Server: Aggregates all answer data in real time.

[0809] Output: Mock test results are displayed in real time and feedback is provided.

[0810] Step 7: Stress Level Feedback

[0811] Input: The user enters their stress level into the device.

[0812] Operation:

[0813] User: Rate their stress level on a scale of 1 to 5 and enter it into the device.

[0814] Device: Sends stress level data to the server.

[0815] Server: Stores the received stress data in a database.

[0816] Output: Stress level data stored on the server.

[0817] Step 8: Adjust your next competitor

[0818] Input: Stress level data and learning effect data stored by the server.

[0819] Operation:

[0820] Server: Comprehensively evaluates the received stress level data and learning effect, and adjusts the settings of the next virtual competitor. For example, if the stress level is high, reduce the number of favorite subjects.

[0821] Output: The configuration data for the next virtual competitor is generated.

[0822] (Application example 1)

[0823] 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."

[0824] In today's educational environment, learners are required to study in an optimal competitive environment. However, real interactions and competitors are not always available, making it difficult for learners to maintain their motivation and learning efficiency. Furthermore, existing systems may not adequately manage stress levels or optimize learning outcomes. A new system using virtual competitors to solve these issues and enable learners to study efficiently and effectively is needed.

[0825] 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.

[0826] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting data of the virtual competitor to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting settings of the virtual competitor, means for transmitting adjustment data of the virtual competitor to the terminal, means for displaying the virtual competitor in three dimensions using a head-mounted display, and means for the learner to experience a realistic competition via the head-mounted display. This allows the learner to efficiently and effectively progress in their learning in an appropriate competitive environment, maximizing learning effectiveness and minimizing stress.

[0827] "Basic information of learners" refers to information that identifies individuals, such as the learner's name, age, and affiliated institution.

[0828] "Learning history" refers to data that records the content, grades, and progress of a learner's past learning.

[0829] A "server" is a computer system for storing, managing, and analyzing data.

[0830] A "database" is a collection of information that systematically stores and manages learners' basic information and learning history.

[0831] A "virtual competitor" is a virtual character or avatar created to compete with the learner.

[0832] A "terminal" is a computing device operated by a learner to exchange data with a server.

[0833] A "head-mounted display" is an output device worn on the head to display visual information.

[0834] "3D display" is a technique for displaying objects in three dimensions, providing the user with a sense of depth.

[0835] "Stress level" is an indicator of the degree of psychological and physiological stress felt by learners.

[0836] "Learning effect" refers to the degree of improvement in knowledge and skills that a learner gains through learning.

[0837] "Response" refers to a reply or answer given by a learner to a task or question.

[0838] "Feedback" refers to evaluation and advice provided based on learner responses and competition results.

[0839] "Adjustment data" refers to specific parameters and information for changing the settings of a virtual competitor.

[0840] "Analysis" is the process of clarifying patterns and characteristics of data using basic information and learning history of learners.

[0841] An "immersive competitive experience" is an experience that allows players to compete in a virtual environment with a feeling close to reality.

[0842] A "generative AI model" is a computational model that uses machine learning algorithms to create new virtual competitors based on data.

[0843] A "prompt" is an instruction or question input to an AI model.

[0844] The present invention is a system that inputs basic information and learning history of a learner, analyzes the data, generates an optimal virtual competitor, and provides the learner with an appropriate competitive environment. A specific method for implementing this system will be described.

[0845] System configuration

[0846] 1. User terminal and head-mounted display

[0847] Learners use smartphones and head-mounted displays (HMDs).

[0848] Provides an interface for entering basic information and learning history of learners.

[0849] 2. Server

[0850] A cloud server (e.g., AWS) for storing, managing, and analyzing data.

[0851] A database (e.g., Amazon RDS) to store learner data.

[0852] Machine learning algorithms (e.g., TensorFlow) for data analysis and virtual competitor generation.

[0853] 3. Database

[0854] Systematically store learner's basic information and learning history.

[0855] It is designed to allow quick access to and analysis of the data you need.

[0856] Program processing

[0857] Initial Setup and Data Collection

[0858] 1. User Registration

[0859] The user uses the terminal to enter basic information (such as name, age, and learning institution information).

[0860] The terminal sends the entered basic information to the server, which stores it in a database.

[0861] 2. Collecting learning history

[0862] Users enter the results of mock exams and progress in classes into the terminal.

[0863] The terminal sends the collected learning history data to the server, which stores it in a database.

[0864] Data analysis and virtual competitor generation

[0865] 3. Data Analysis

[0866] The server analyzes the learner's basic information and learning history stored in the database.

[0867] Using a machine learning algorithm (TensorFlow), we identify learners' strengths, weaknesses, and learning patterns.

[0868] 4. Creating Virtual Competitors

[0869] Based on the analysis results, the most suitable virtual competitor for the learner is generated.

[0870] The virtual competitors are set with difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[0871] Interface, Interaction and Competition

[0872] 5. Transmission of competitor data

[0873] The server transmits data of the generated virtual competitor to the terminal.

[0874] The user uses a head-mounted display to visually see their virtual opponent in 3D.

[0875] 6. Dialogue and Competition

[0876] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[0877] The terminal compiles the user's responses and the answers of the virtual competitors in real time and provides feedback.

[0878] Feedback and Adjustments

[0879] 7. Stress Level Monitoring

[0880] An interface is provided for users to input the stress level they felt during the competition.

[0881] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[0882] 8. Strengthening or weakening virtual competitors

[0883] The server adjusts the settings of the next virtual competitor based on the received data.

[0884] Dynamically adjust the difficulty of the virtual competitor according to the learner's perceived stress level and learning effectiveness.

[0885] Specific examples

[0886] 1. Example of entering basic user information

[0887] When a new candidate uses the system, they enter their name, age, name of their learning institution, etc. into the terminal.

[0888] The device sends this basic information to the server, which stores it in a database.

[0889] 2. Learning history input and analysis example

[0890] Candidates take the mock test and enter the results into a terminal, which records the score, answer time, and questions answered incorrectly in detail.

[0891] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[0892] 3. Example of Virtual Competitor Generation

[0893] The analysis results indicate that the test-taker is good at mathematics but weak at English.

[0894] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[0895] 4. Examples of dialogue and competition

[0896] When a candidate takes a mock test on their device, they are presented with a scenario in which a virtual competitor is also taking the test at the same time.

[0897] When the user uses a head-mounted display, the virtual opponent is displayed in three dimensions and provides real-time feedback.

[0898] Prompt Sentence Examples

[0899] Describe the steps for users to enter their learning history and save it on a cloud server. Next, develop a system that uses a machine learning algorithm to generate a virtual opponent based on that data and competes with the learner in real time. Specifically, describe the flow, including analysis using TensorFlow, data storage on AWS, and real-time updates to the user interface.

[0900] In this way, the present invention is designed to help learners study efficiently and effectively, and by providing an immersive competitive experience using a head-mounted display, it is possible to maximize learning effectiveness while minimizing stress.

[0901] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0902] Step 1:

[0903] User Registration

[0904] The user uses a smartphone or head-mounted display to input basic information (such as name, age, and information about the institution of study). The input basic information is sent from the device to the server. The server stores the received basic information in a database. The input is basic information, and the output is the basic information stored in the database.

[0905] Step 2:

[0906] Collection of learning history

[0907] Users enter mock test results and lesson progress into their terminal. The entered learning history data is sent from the terminal to the server. The server stores the received learning history data in a database. The input is learning history data, and the output is the learning history stored in the database.

[0908] Step 3:

[0909] Data analysis

[0910] The server retrieves the learner's basic information and learning history stored in the database. Using a machine learning algorithm (TensorFlow), it performs analysis to identify the learner's strong and weak subjects and learning patterns. The input is basic information and learning history data, and the output is the analysis results of the learner's strong and weak subjects and learning patterns.

[0911] Step 4:

[0912] Virtual Competitor Creation

[0913] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The generated virtual competitor is registered with settings, personality, and behavior patterns that correspond to the learner's strong and weak subjects. The input is the analysis results, and the output is data on the generated virtual competitor.

[0914] Step 5:

[0915] Submitting competitor data

[0916] The server sends the generated virtual competitor data to the terminal. The user can visually confirm the virtual competitor in 3D using a head-mounted display. The input is the virtual competitor data, and the output is the 3D virtual competitor displayed on the head-mounted display.

[0917] Step 6:

[0918] Dialogue and Competition

[0919] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions. The terminals compile the user's responses and the answers of the virtual competitors in real time and send them to a server. The input is the responses of the user and the virtual competitors, and the output is the compiled results.

[0920] Step 7:

[0921] Generate feedback

[0922] The server generates feedback based on the learner's responses and the competition results. The generated feedback is sent to the terminal and provided to the user. The inputs are the learner's responses and the competition results, and the output is the generated feedback.

[0923] Step 8:

[0924] Stress level monitoring

[0925] Users input the stress level they felt during the competition. The input stress level data is sent from the device to the server. The server uses this data to adjust future dialogue settings and the difficulty of the competition. The input is stress level data, and the output is the adjusted difficulty setting for the competition.

[0926] Step 9:

[0927] Strengthening or weakening virtual competitors

[0928] The server adjusts the settings of the next virtual competitor based on the received data. It dynamically adjusts the difficulty of the virtual competitor according to the learner's stress level and learning effect. The input is the received data and feedback, and the output is the adjusted settings of the virtual competitor.

[0929] 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.

[0930] System Overview and Operation

[0931] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[0932] Program processing overview

[0933] Initial Setup and Data Collection

[0934] 1. User Registration

[0935] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[0936] The terminal sends the entered basic information to the server, which stores it in a database.

[0937] 2. Collecting learning history

[0938] Users enter the results of mock exams and progress in classes into the terminal.

[0939] The terminal sends the collected learning history data to the server, which stores it in a database.

[0940] 3. Collecting Emotional Data

[0941] While the user is using the device to study or take a practice test, the device collects facial and voice data through its camera and microphone.

[0942] The emotion engine analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[0943] The terminal transmits the emotion data analyzed by the emotion engine to the server.

[0944] Data analysis and virtual competitor generation

[0945] 4. Data Analysis

[0946] The server analyzes the basic information, learning history, and emotional data stored in the database.

[0947] The server uses machine learning algorithms to identify a learner's strengths and weaknesses, learning patterns, and emotional state.

[0948] 5. Creating Virtual Competitors

[0949] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[0950] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[0951] Interface, Interaction and Competition

[0952] 6. Transmission of competitor data

[0953] The server transmits data of the generated virtual competitor to the terminal.

[0954] The terminal prepares to display the virtual competitor on the user interface based on the received data.

[0955] 7. Dialogue and Competition

[0956] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0957] The user and the virtual competitor proceed through mock tests and study sessions.

[0958] Feedback and Adjustments

[0959] 1. Providing Feedback

[0960] The device compiles the results of practice tests and study sessions and provides feedback to the user, including scores, explanations of incorrect answers, and study advice.

[0961] 2. Utilizing Emotional Data

[0962] The emotion engine monitors the user's emotional state during the learning session and transmits it to the server.

[0963] The server dynamically adjusts the behavior and dialogue scripts of the virtual competitors based on the emotional data.

[0964] 3. Stress management and difficulty adjustment

[0965] Based on the user's stress level and learning effect, the server adjusts the virtual competitor's settings. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the stress level is low, the server raises the difficulty.

[0966] Specific examples

[0967] 1. Example of entering basic information and learning history

[0968] To use the system for the first time, examinee C enters basic information and the results of the mock test on a terminal. The terminal sends this data to the server, which then stores it in a database.

[0969] 2. Emotion data collection and analysis example

[0970] While Candidate C is taking the mock exam, the device's camera and microphone collect facial and voice data, which the emotion engine analyzes to assess stress and concentration levels.

[0971] The analysis results (e.g., "I'm anxious during the exam," "I'm concentrating," etc.) are sent to the server.

[0972] 3. Virtual Competitor Creation and Interaction Examples

[0973] Based on the analysis results, the server generates the optimal virtual competitor for test-taker C. For example, it sets a well-balanced competitor who is good at English and also fairly good at mathematics.

[0974] When Test Taker C takes a mock test with the virtual competitor in his next study session, the competitor answers in real time, and the dialogue continues.

[0975] 4. Feedback and Adjustment Examples

[0976] After the mock test is completed, the device displays the results (score, explanations of incorrect answers, etc.) and also provides feedback based on emotional data.

[0977] When Test Taker C enters his / her satisfaction and stress level from the study session into his / her device, the server uses this information to adjust the settings of the virtual competitor and reflect them in the next session.

[0978] In this way, the present invention, which is combined with an emotion engine, can provide an optimal learning environment while taking into account the user's emotional state, thereby maximizing learning effectiveness.

[0979] The processing flow will be explained below.

[0980] Step 1:

[0981] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[0982] Step 2:

[0983] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[0984] Step 3:

[0985] While a user is using the device to study or take a practice test, the device transmits facial and voice data via a camera and microphone to the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[0986] Step 4:

[0987] The device sends the emotional data analyzed by the emotion engine to the server, which stores it in a database and integrates it with previous learning history for further analysis.

[0988] Step 5:

[0989] The server analyzes the basic information, learning history, and emotional data stored in the database, and uses machine learning algorithms to identify the learner's strengths and weaknesses, learning patterns, and emotional state.

[0990] Step 6:

[0991] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The virtual competitor is set to a level of difficulty, personality, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[0992] Step 7:

[0993] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[0994] Step 8:

[0995] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[0996] Step 9:

[0997] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[0998] Step 10:

[0999] The device compiles the test results and emotional data and provides feedback to the user, including the score, explanations of incorrect answers, and study advice.

[1000] Step 11:

[1001] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[1002] Step 12:

[1003] The server adjusts the virtual competitor's settings based on the user's stress level, learning effect, and emotional data. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the user's stress level is low, the server raises the difficulty.

[1004] Step 13:

[1005] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[1006] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[1007] Example 2

[1008] 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."

[1009] Today's learners face diverse learning environments, requiring optimal learning support tailored to their individual learning styles and emotional states. However, traditional learning systems do not take the user's emotional state into account, making it difficult to provide a personalized, competitive environment that maximizes learning efficiency. Furthermore, there are a lack of methods to enhance learning effectiveness while appropriately managing learners' stress levels. This makes it difficult for learners to maintain their motivation to study.

[1010] 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.

[1011] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for collecting emotional data from the user's terminal during learning and practice tests, means for transmitting the emotional data to the server, means for analyzing the basic information, learning history, and emotional data from the database and generating a virtual competitor optimal for the learner, means for transmitting data on the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the results of the competition to the server, means for generating feedback on the learner's responses, the results of the competition, and the emotional data and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the settings of the virtual competitor, and means for transmitting adjustment data on the virtual competitor to the terminal. This makes it possible to provide an optimal learning environment and manage stress to maximize learning efficiency while taking the learner's emotional state into consideration.

[1012] "Learner" refers to the person receiving education and the entity using the system.

[1013] "Basic information" refers to personal information such as the learner's name, age, and school information.

[1014] "Learning history" refers to information about a learner's past learning activities, such as mock test results and class progress.

[1015] A "terminal" is a device used by learners to input and output information. Examples include personal computers and smartphones.

[1016] A "server" refers to a computer system that performs processes such as storing, analyzing, sending and receiving data.

[1017] A "database" refers to a system that systematically stores and manages data such as basic information, learning history, and emotional data.

[1018] "Emotional data" refers to data on the emotional state of a learner obtained from facial expressions, voice, etc.

[1019] "Emotion engine" refers to software or algorithms used to analyze emotion data and identify a learner's emotional state.

[1020] "Virtual competitor" refers to a virtual competitor corresponding to a learner, which is generated according to the characteristics of the learner.

[1021] "Dialogue script" refers to the language and behavioural scenarios that a virtual competitor uses in dialogue with learners.

[1022] "Feedback" refers to evaluations and advice provided based on learners' learning results and emotional data.

[1023] "Stress level" refers to the degree of stress a learner feels while studying.

[1024] "Learning outcomes" refer to the results and improvement in knowledge that learners achieve through learning activities.

[1025] "Adjustment Data" refers to data for modifying the settings of a virtual competitor.

[1026] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[1027] Hardware and software used

[1028] The present invention uses the following hardware and software:

[1029] Device: The device used by the learner, such as a computer, tablet, or smartphone.

[1030] Server: A computer system that stores, analyzes, sends and receives data. For example, a cloud-based server can be used.

[1031] Database: A system that systematically stores and manages basic information, learning history, emotional data, etc. Specifically, database systems such as MySQL and MongoDB are used.

[1032] Emotion engine: Software or algorithms for analyzing emotion data and identifying the learner's emotional state, specifically using Python's OpenCV and Google's Cloud Speech-to-Text API.

[1033] Machine learning algorithm: The algorithm used for analysis processing, specifically Scikit-learn and TensorFlow.

[1034] Specific explanation of the system

[1035] User registration and basic information entry

[1036] The user uses the terminal to enter basic information (such as name, age, school information, etc.). The user enters this information into the input form displayed on the terminal screen and presses the "Submit" button. The entered basic information is sent from the terminal to the server, which then stores it in a database.

[1037] Collection of learning history

[1038] Users enter their mock test results and progress in classes into the device. The device then sends the entered learning history data to the server, which then stores it in a database. For example, this data might include "Math: 85 points, English: 90 points, Science: 78 points, Social Studies: 82 points."

[1039] Emotion data collection and analysis

[1040] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data. The emotion engine analyzes this data in real time to identify the user's emotional state. For example, emotions such as "nervous" or "concentrated" may be identified, and the analysis results are sent from the device to the server.

[1041] Data analysis and virtual competitor generation

[1042] The server analyzes the basic information, learning history, and emotional data stored in the database. It uses machine learning algorithms to identify the learner's strong and weak subjects, learning patterns, and emotional state. Based on this, it generates the optimal virtual competitor. For example, if a learner is weak in English but good at math, it will generate a virtual competitor accordingly.

[1043] User Interface and Competitor View

[1044] The server transmits data about the generated virtual competitor to the terminal. The terminal prepares to display the virtual competitor on the user interface based on the received data. The user can then start interacting with the virtual competitor via the terminal and proceed with the mock test or learning session.

[1045] Providing feedback and making adjustments

[1046] The results of mock tests and study sessions are sent from the device to a server. The server then generates feedback based on this information and provides it to the learner. The feedback includes the student's score, explanations for incorrect answers, and study advice. Furthermore, the system dynamically adjusts the virtual competitor's settings based on the emotional data and reflects them in the next session. For example, if the user's stress level is high, the system may adjust the difficulty of the virtual competitor.

[1047] Specific examples

[1048] 1. After entering user information

[1049] Name: Yamada Taro

[1050] Age: 17

[1051] School information: 〇〇High School

[1052] 2. Example of mock test result input

[1053] Mock exam results:

[1054] Mathematics: 85 points

[1055] English: 90 points

[1056] Science: 78 points

[1057] Social: 82 points

[1058] 3. Example of emotion data analysis

[1059] Emotions during exams: Impatience

[1060] Concentration: High

[1061] Expression: Tense

[1062] 4. Examples of Providing Feedback

[1063] Mock exam results:

[1064] Score: 85 points

[1065] Wrong answer: Question 5, Question 8

[1066] Study advice: Focus on grammar next time

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1:

[1069] User Registration

[1070] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[1071] Input: The user enters their name, age, and school information into the input form on the device and presses the "Submit" button.

[1072] Data processing and calculation: The device formats this information and sends it to the server using the HTTPS protocol.

[1073] Output: The server stores the received basic information in a database.

[1074] Specific behavior: The device detects user input in real time and displays a confirmation message after submission.

[1075] Step 2:

[1076] Collection of learning history

[1077] Users enter the results of mock exams and progress in classes into the terminal.

[1078] Input: The user enters the scores for each subject in the mock test and presses the submit button.

[1079] Data processing and calculation: The terminal converts the input data into JSON format and sends it to the server.

[1080] Output: The server stores the received learning history in a database.

[1081] What happens: The terminal validates the input data, displays warning messages if necessary, and displays a confirmation message after the data has been sent.

[1082] Step 3:

[1083] Collecting Emotional Data

[1084] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data.

[1085] Input: The device collects the user's facial expressions and voice in real time using a camera and microphone while learning.

[1086] Data processing and calculation: The emotion engine processes the collected facial expression data and analyzes the voice data to identify the user's emotional state (e.g., joy, tension, impatience).

[1087] Output: The analysis results (emotion data) are sent to the server and stored in a database.

[1088] Specific operation: The device periodically collects data and sends it to the server at each collection interval. The device is designed not to notify the user when data is collected.

[1089] Step 4:

[1090] Data analysis

[1091] The server analyzes the basic information, learning history, and emotional data stored in the database.

[1092] Input: The server retrieves basic information, learning history, and emotion data from the database.

[1093] Data processing and computation: Use machine learning algorithms (e.g., Scikit-learn, TensorFlow) to identify strengths and weaknesses, learning patterns, and emotional states.

[1094] Output: The analysis results are output as data that can be used to generate virtual competitors.

[1095] Specific operation: The server periodically executes the analysis task and stores the results in a database. The server is also configured to provide immediate feedback to the learner on the analysis results.

[1096] Step 5:

[1097] Virtual Competitor Creation

[1098] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[1099] Input: Basic information, learning history, and analysis results of emotion data.

[1100] Data processing and calculation: Based on the analysis results, the server sets the virtual competitor's strong and weak subjects, personality, and behavioral patterns.

[1101] Output: Virtual competitor data is generated and sent to the terminal.

[1102] What it does: The server automatically adjusts the virtual competitor settings to generate a competitor customized to the user's learning needs.

[1103] Step 6:

[1104] Submitting and Displaying Competitor Data

[1105] The server transmits data of the generated virtual competitor to the terminal.

[1106] Input: Virtual competitor data.

[1107] Data processing and calculation: The server converts the data into an appropriate format and sends it to the terminal.

[1108] Output: The terminal receives data to display the virtual competitors in the user interface.

[1109] Specific operation: When the terminal receives the competitor's data, it displays it on the screen and provides an interface that allows the user to interact with the competitor.

[1110] Step 7:

[1111] Dialogue and Competition

[1112] The user initiates a dialogue with a virtual competitor via the terminal.

[1113] Input: User interactions and responses to competitions.

[1114] Data processing and calculation: The terminal generates responses based on the dialogue script received from the server and processes the competition results in real time.

[1115] Output: The device sends the progress of the interaction and competition to the server.

[1116] Specific operation: The terminal processes user input in real time and displays the responses of virtual competitors according to the dialogue script. The competition results are periodically sent to the server.

[1117] Step 8:

[1118] Providing feedback

[1119] The server generates feedback based on the results of the learning session.

[1120] Input: Competition results, sentiment data, user responses.

[1121] Data processing and calculation: The server aggregates this data and generates feedback, including incorrect answers and study advice.

[1122] Output: The generated feedback is sent to the device.

[1123] What happens: The device notifies the user of the feedback and displays details on the screen, including the score and areas for improvement.

[1124] Step 9:

[1125] Monitor and regulate stress levels

[1126] The emotion engine monitors the user's stress level and transmits it to the server.

[1127] Input: Facial and voice data of the user during training.

[1128] Data processing and computation: Analyzes emotional state to identify stress levels and adjusts virtual competitor settings accordingly.

[1129] Output: The adjustment data is sent to the device and reflected in the next training session.

[1130] How it works: The server analyzes emotional data in real time and dynamically adjusts the difficulty and dialogue scripts of competitors.

[1131] (Application example 2)

[1132] 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."

[1133] Conventional learning systems often provide a uniform learning environment without considering the learner's emotional state or stress level. This makes it difficult for some learners to learn effectively, hindering efficient acquisition. Furthermore, it is not possible to provide optimal competition for each individual learner, leaving challenges in maintaining motivation and improving comprehension.

[1134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1135] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the competition results to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings, means for transmitting adjustment data of the virtual competitor to the terminal, means for analyzing the learner's emotional state during learning using an emotion engine and dynamically adjusting the learning environment, and means for analyzing the learner's stress level in real time based on raw data and adjusting interactions during learning. This provides an optimal learning environment that takes the learner's emotional state and stress level into consideration, enabling efficient learning and maximizing learning effects.

[1136] "Learner" refers to a person who acquires knowledge and skills in accordance with an educational program or curriculum.

[1137] "Basic information" refers to information for identifying a learner, such as the learner's name, age, and school information.

[1138] "Learning history" is a record of a learner's past mock test results, progress in classes, and so on.

[1139] "Server" refers to a computer system that stores data, analyzes data, generates feedback, etc.

[1140] A "database" is a system that organizes and stores data such as basic information and learning history.

[1141] A "virtual competitor" refers to a virtual entity that competes with learners in learning progress, mock exams, etc.

[1142] "Devices" refer to information devices such as smartphones, tablets, and personal computers used by learners.

[1143] An "emotion engine" is an algorithm or program that analyzes a learner's emotional state from their facial expressions, voice, etc.

[1144] "Stress level" refers to the degree of mental tension a learner feels while studying.

[1145] "Feedback" refers to advice and evaluation provided based on learners' responses and competition results.

[1146] "Interaction" refers to the process of interaction between learners and virtual competitors during learning.

[1147] System Overview

[1148] This invention is a system related to "student," "basic information," "learning history," "server," "database," "virtual competitor," "terminal," "emotion engine," "stress level," "feedback," and "interaction." The aim is to maximize the learning effect of learners, and in particular to provide an optimal learning environment by utilizing the virtual competitor and emotion engine.

[1149] Technology used

[1150] The system is implemented using the following technologies:

[1151] 1. Database Management System: MySQL

[1152] 2. Backend: Python (Django Framework)

[1153] 3. Frontend: React Native

[1154] 4. Emotion engine: OpenAI API (emotion analysis model)

[1155] 5. Real-time communication: WebSocket

[1156] Process Overview

[1157] 1. User registration and information entry

[1158] Learners enter basic information (such as name, age, and school information) through their devices. The data entered on the devices is sent to and stored in a MySQL database through the back-end Django framework.

[1159] 2. Collecting learning history

[1160] Students enter their mock exam results and class progress information into the terminal, and the input data is stored in a MySQL database via a Django application.

[1161] 3. Emotional Data Collection and Analysis

[1162] During training, facial and voice data is collected via the device's camera and microphone. The collected data is then analyzed using the OpenAI API, and the results are sent to the server in real time.

[1163] 4. Creating Virtual Competitors

[1164] A machine learning algorithm built in Python uses stored basic information, learning history, and emotional data to generate the optimal virtual competitor.

[1165] 5. Dialogue and Competition

[1166] The virtual competitor data is displayed on a terminal interface built with React Native, and WebSocket is used to realize real-time interaction between learners and virtual competitors.

[1167] 6. Feedback and Adjustments

[1168] Feedback generated based on the competition results and the learner's stress level is sent to the device, which monitors the learner's stress level in real time and dynamically adjusts the virtual competitor's settings.

[1169] Specific examples

[1170] For example, when a learner starts a math mock test, the device's camera and microphone collect emotional data through facial expressions and voice, which is then analyzed through the OpenAI API. The analysis results are sent to the server, which generates the optimal virtual competitor. The virtual competitor then solves the mock test together in real time, which is displayed via React Native. Feedback is generated based on the learner's responses and the competition results, and sent to the device. The difficulty level of the virtual competitor and the dialogue script are dynamically adjusted based on the learner's stress level.

[1171] Prompt statement

[1172] Below are some example prompts for sentiment analysis:

[1173] Please rate the test taker's level of impatience and concentration based on the following statements:

[1174] "Throughout the exam, he would often take deep breaths and stare at the questions with furrowed brows. After a moment, he would grip his pen tighter, clearly confused."

[1175] Through these methods, an optimal learning environment is provided that takes into account the learner's emotional state and stress level.

[1176] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1177] Step 1:

[1178] The user enters basic information

[1179] The user enters basic information (such as name, age, school information, etc.) through the terminal. This input data is temporarily saved on the terminal and then sent to the server. Specifically, a basic information form is displayed, the user fills in the required fields, and when the user presses the data submit button, the data is sent to the server via the Django framework.

[1180] Input: Basic information data

[1181] Output: Basic information sent to the server

[1182] Step 2:

[1183] The server stores basic information in a database

[1184] The server stores the received basic information in a database, and the Django framework generates and executes commands to insert the received data into a MySQL database.

[1185] Input: Received basic information data

[1186] Output: Basic information stored in the database

[1187] Step 3:

[1188] The user enters their learning history

[1189] Users enter their mock test results and progress in classes into their devices. The data entered by the user is temporarily saved and then sent to the server. After filling out the form on the device, the data is sent to the server and received.

[1190] Input: Learning history data

[1191] Output: Learning history sent to the server

[1192] Step 4:

[1193] The server saves the learning history in a database

[1194] The server stores the received learning history data in a database. The Django framework generates and executes commands to insert the received data into a MySQL database.

[1195] Input: Received learning history data

[1196] Output: Learning history stored in the database

[1197] Step 5:

[1198] Collect user sentiment data

[1199] During learning, the camera and microphone on the user's device (smartphone, smart glasses, head-mounted display) collect facial expressions and voice. This data is temporarily stored in the device's local memory. Specifically, the camera and microphone are programmed to automatically start collecting data as soon as learning begins.

[1200] Input: facial expression and voice data

[1201] Output: Temporarily saved emotion data

[1202] Step 6:

[1203] Analyzing emotional data with an emotion engine

[1204] The emotion data stored on the device is analyzed by the emotion engine using the OpenAI API, and the analysis results are output as stress levels and emotional states and sent to the server.

[1205] Input: Temporarily saved emotion data

[1206] Output: Analyzed emotional data (stress level, emotional state)

[1207] Step 7:

[1208] The server analyzes basic information, learning history, and emotional data.

[1209] The server uses machine learning algorithms to analyze the basic information, learning history, and emotional data stored in the database. As a result, it generates the most suitable virtual competitor for the learner. Specifically, a machine learning algorithm written in Python is used to analyze the data and generate a model.

[1210] Input: Basic information, learning history, emotional data

[1211] Output: Virtual competitor data

[1212] Step 8:

[1213] The server sends the virtual competitor data to the terminal.

[1214] The server sends the generated virtual competitor data to the terminal using the Django framework and WebSocket for real-time communication.

[1215] Input: Virtual competitor data

[1216] Output: Virtual competitor data sent to the terminal

[1217] Step 9:

[1218] Users can interact and compete with virtual competitors

[1219] Users interact and compete with virtual opponents displayed on their devices, and interactions are managed in real time through React Native, including answering multiple-choice questions and chat-style conversations.

[1220] Input: Virtual competitor data sent to the terminal

[1221] Output: Interaction and competition results

[1222] Step 10:

[1223] The device sends the results of the competition to the server.

[1224] The user's competition results are sent from the terminal to the server. Data during the competition is collected in real time and sent to the server through the Django framework.

[1225] Input: Dialogue and competition results

[1226] Output: Interaction and competition results sent to the server

[1227] Step 11:

[1228] The server generates feedback and sends it to the device

[1229] The server generates feedback based on the received competition result data. The feedback includes points scored, incorrect answers, and study advice. The generated feedback is sent to the device.

[1230] Input: Dialogue and competition results

[1231] Output: Feedback data

[1232] Step 12:

[1233] Users can review the feedback and apply it to their next learning.

[1234] Users can check the feedback displayed on their devices and use it to improve their learning, leading to more effective learning in the next session. Specifically, they can use the feedback to revise and improve their learning plan.

[1235] Input: Feedback data

[1236] Output: Maximized learning effect

[1237] 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.

[1238] 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.

[1239] 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.

[1240] [Third embodiment]

[1241] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1242] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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."

[1253] System Overview and Operation

[1254] This system inputs basic information and learning history of a learner and analyzes that data to generate a virtual opponent that is optimal for the learner. This system provides a moderate competitive environment, maximizing learning effectiveness while managing stress.

[1255] Program processing overview

[1256] Initial Setup and Data Collection

[1257] 1. User Registration

[1258] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[1259] The terminal sends the entered basic information to the server, which stores it in a database.

[1260] 2. Collecting learning history

[1261] Users enter the results of mock exams and progress in classes into the terminal.

[1262] The terminal sends the collected learning history data to the server, which stores it in a database.

[1263] Data analysis and virtual competitor generation

[1264] 3. Data Analysis

[1265] The server analyzes the learner's basic information and learning history stored in the database, and identifies the learner's strong and weak subjects and learning patterns.

[1266] This analysis uses machine learning algorithms to accurately evaluate the learner's characteristics.

[1267] 4. Creating Virtual Competitors

[1268] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[1269] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[1270] Interface, Interaction and Competition

[1271] 5. Transmission of competitor data

[1272] The server transmits data of the generated virtual competitor to the terminal.

[1273] The receiving terminal displays the virtual competitor on the user interface.

[1274] 6. Dialogue and Competition

[1275] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[1276] The terminal compiles the user's answers and those of the virtual competitors in real time and provides feedback to the user.

[1277] Specific examples

[1278] 1. Example of entering basic user information

[1279] Candidate B is using the system for the first time, so he enters his name, age, school name, etc. on the terminal.

[1280] The device sends this basic information to the server, which stores it in a database.

[1281] 2. Learning history input and analysis example

[1282] Candidate B takes the mock test and enters the results into the terminal. The results are recorded in detail, including the score, answer time, and questions answered incorrectly.

[1283] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[1284] 3. Example of Virtual Competitor Generation

[1285] The analysis results indicate that candidate B is good at math but not so good at English.

[1286] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[1287] 4. Examples of dialogue and competition

[1288] When Candidate B takes a mock test on his device, a scenario is displayed in which a virtual competitor is also taking the test at the same time.

[1289] Results are displayed in real time and feedback is provided based on this.

[1290] Feedback and Adjustments

[1291] Stress level feedback from users

[1292] Candidate B enters the stress level he or she felt during the competition.

[1293] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[1294] Strengthening or weakening virtual competitors

[1295] The server will comprehensively evaluate the stress level and learning effect of test-taker B and adjust the settings of the next virtual competitor.

[1296] For example, if you feel too stressed, lower the difficulty of your competitors, and conversely, if you have more time, increase the difficulty.

[1297] In this way, the present invention is designed to allow test takers to study hard in an optimal learning environment, and to maximize the learning effect through moderate competition.

[1298] The processing flow will be explained below.

[1299] Step 1:

[1300] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[1301] Step 2:

[1302] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[1303] Step 3:

[1304] The server analyzes the basic information and learning history stored in the database and uses machine learning algorithms to identify the learner's strengths, weaknesses, and learning patterns.

[1305] Step 4:

[1306] Based on the analysis results, the server generates the virtual competitor that is best suited for the learner. The server creates the virtual competitor's data (character settings, behavior patterns, difficulty level, etc.).

[1307] Step 5:

[1308] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[1309] Step 6:

[1310] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[1311] Step 7:

[1312] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[1313] Step 8:

[1314] The device then provides the user with feedback based on the calculated score, including points, explanations of incorrect answers, and study advice.

[1315] Step 9:

[1316] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[1317] Step 10:

[1318] The server adjusts the settings of the virtual competitor based on the user's stress level and learning effect. For example, if the user's stress level is high, the difficulty of the competitor is lowered, and if the stress level is low, the difficulty is increased.

[1319] Step 11:

[1320] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[1321] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[1322] Example 1

[1323] 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."

[1324] In today's educational environment, efficient and effective learning requires personalized approaches tailored to individual strengths and weaknesses. It is also important to provide learners with a competitive environment to maintain their motivation and maximize their learning outcomes. Furthermore, stress levels must be monitored and adjusted to avoid excessive stress while learning. However, there is still a lack of learning support systems that meet these requirements.

[1325] 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.

[1326] In this invention, the server includes: means for inputting a learner's basic information and learning history; means for transmitting the basic information and learning history to the server; means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner; means for transmitting data on the virtual competitor to the learner's device; means for interacting with and competing with the virtual competitor on the device; means for transmitting the learner's responses and the competition results to the server; means for generating feedback on the learner's responses and the competition results and transmitting the feedback to the device; means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings; means for transmitting the virtual competitor adjustment data to the device; means for setting and adjusting the virtual competitor's behavior pattern and difficulty level using a generative AI model; and means for providing feedback to the learner via a user interface. This provides a personalized competitive environment for the learner, maximizing learning effectiveness through appropriate competition. Furthermore, real-time feedback and adjustments according to the learner's stress level maintain an optimal learning environment.

[1327] A "learner" is an individual who is studying to receive an education.

[1328] "Basic information" refers to basic data about the learner, such as name, age, and school information.

[1329] "Learning history" is information about a learner's learning activities, such as mock test results and progress in classes.

[1330] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[1331] A "server" is a computer system used to store and analyze data, generate virtual competitors, and so on.

[1332] A "database" is a collection of data that stores basic information and learning history of learners, managed by a server.

[1333] "Analysis" is the process of examining data to extract patterns and characteristics.

[1334] A "virtual competitor" is a virtual opponent that is generated using machine learning algorithms or generative AI models and competes against the learner.

[1335] "Feedback" is information about a learner's achievements or performance that is provided based on the learner's responses or competition results.

[1336] "Stress level" is a value that indicates the degree of mental stress that a learner feels while studying or competing.

[1337] A "generative AI model" is a type of algorithm or technique that uses artificial intelligence technology to generate data.

[1338] A "user interface" is a screen or operating means that allows a user to operate a system and receive information.

[1339] This invention is a system that collects and analyzes a learner's basic information and learning history to generate a virtual competitor that is optimal for the learner. This system provides a moderate competitive environment, maximizing the effectiveness of learning while managing the learner's stress.

[1340] Initial Setup and Data Collection

[1341] 1. User Registration

[1342] User: The user enters basic information such as their name, age, and school information into the terminal on the initial screen of the system. For example, they might enter "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[1343] Terminal: The terminal generates an HTTP request to send the entered basic information to the server and sends the data to the server.

[1344] Server: The server stores the received basic information in a database and returns a response indicating successful registration to the device.

[1345] 2. Collecting learning history

[1346] User: The user enters the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[1347] Terminal: The terminal sends the input learning history data to the server.

[1348] Server: The server stores the received learning history data in a database.

[1349] Data analysis and virtual competitor generation

[1350] 3. Data Analysis

[1351] Server: The server retrieves basic information and learning history data of the learner from the database and analyzes it using machine learning algorithms (for example, Python's Scikit-learn library). It identifies the learner's strong and weak subjects and learning patterns.

[1352] 4. Creating Virtual Competitors

[1353] Server: Based on the analysis results, the server uses a generative AI model to generate the optimal virtual competitor for the learner. Specifically, it sets the competitor's strong and weak subjects and behavioral patterns.

[1354] Interface, Interaction and Competition

[1355] 5. Transmission of competitor data

[1356] Server: The server sends the data of the generated virtual competitor to the terminal.

[1357] Terminal: The terminal displays the received data on the user interface, allowing the user to check the information of the virtual competitors.

[1358] 6. Dialogue and Competition

[1359] User: A user competes against a virtual opponent through a terminal, such as a mock test. For example, the user starts a mock test and enters their answers to each question.

[1360] Terminal: The terminal compiles the user's answers in real time and simultaneously displays the answers of their virtual competitors.

[1361] Server: The server compiles all answer data in real time and sends the results to the device.

[1362] Feedback and Adjustments

[1363] 7. Stress level feedback

[1364] User: The user enters the stress level they felt during the race into the terminal. For example, they enter "Stress level: 4 (scale of 1 to 5)."

[1365] Device: The device sends the input stress level to the server.

[1366] Server: The server stores the received stress data in a database.

[1367] 8. Adjusting the next competitor

[1368] Server: The server will comprehensively evaluate the received stress level data and learning effect and adjust the settings of the next virtual competitor. For example, if the stress level is high, the number of favorite subjects for the next competitor will be reduced.

[1369] Prompt Sentence Examples

[1370] 1. Enter basic user information

[1371] "Please enter your name, age, and school name as a new user."

[1372] 2. Enter your learning history

[1373] "Please enter your mock test results (score, answer time, and questions you got wrong)."

[1374] 3. Setting up a virtual competitor

[1375] "Virtual competitor data received. Start the conversation."

[1376] 4. Enter your stress level

[1377] "Please rate the stress level you felt during the competition on a scale of 1 to 5 and enter it."

[1378] The system allows learners to effectively learn with virtual competitors that are optimized for their individual needs, and also provides appropriate stress-level measures to maximize learning outcomes.

[1379] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1380] Step 1: User Registration

[1381] Input: The user enters basic information such as name, age, and school information into the terminal. For example, "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[1382] Operation:

[1383] User: Enter your name, age, and school information.

[1384] Terminal: Generates an HTTP request and sends the entered basic information to the server.

[1385] Server: Saves the received basic information in the database. If saving is successful, generates a response indicating successful registration and sends it to the device.

[1386] Output: A successful registration response from the server is displayed on the terminal.

[1387] Step 2: Collecting learning history

[1388] Input: The user inputs the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[1389] Operation:

[1390] User: Enter mock test results and class progress.

[1391] Terminal: Generates an HTTP request and sends the entered learning history data to the server.

[1392] Server: Stores the received learning history data in a database.

[1393] Output: Learning history data stored on the server.

[1394] Step 3: Data analysis

[1395] Input: The server retrieves the learner's basic information and learning history data from the database.

[1396] Operation:

[1397] Server: Performs analysis using machine learning algorithms (e.g., Python's Scikit-learn library) to identify learners' strengths and weaknesses and learning patterns.

[1398] Output: The analysis results provide data on the learner's strong and weak subjects, as well as their learning patterns.

[1399] Step 4: Generate a virtual competitor

[1400] Input: The server bases the parsed results.

[1401] Operation:

[1402] Server: Using a generative AI model, it generates a virtual competitor that is optimal for the learner, based on, for example, their strong and weak subjects, behavioral patterns, etc.

[1403] Output: Virtual competitor data is generated.

[1404] Step 5: Submit competitor data

[1405] Input: Server-generated virtual competitor data.

[1406] Operation:

[1407] Server: Sends the virtual competitor data to the device.

[1408] Terminal: Displays the received data in a user interface.

[1409] Output: Information about your virtual competitors will be displayed on your terminal.

[1410] Step 6: Dialogue and competition

[1411] Input: Practice test answers that users enter into the terminal.

[1412] Operation:

[1413] User: Answer practice test questions.

[1414] Terminal: User answers are collected in real time and the answers of virtual competitors are displayed simultaneously.

[1415] Server: Aggregates all answer data in real time.

[1416] Output: Mock test results are displayed in real time and feedback is provided.

[1417] Step 7: Stress Level Feedback

[1418] Input: The user enters their stress level into the device.

[1419] Operation:

[1420] User: Rate their stress level on a scale of 1 to 5 and enter it into the device.

[1421] Device: Sends stress level data to the server.

[1422] Server: Stores the received stress data in a database.

[1423] Output: Stress level data stored on the server.

[1424] Step 8: Adjust your next competitor

[1425] Input: Stress level data and learning effect data stored by the server.

[1426] Operation:

[1427] Server: Comprehensively evaluates the received stress level data and learning effect, and adjusts the settings of the next virtual competitor. For example, if the stress level is high, reduce the number of favorite subjects.

[1428] Output: The configuration data for the next virtual competitor is generated.

[1429] (Application example 1)

[1430] 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."

[1431] In today's educational environment, learners are required to study in an optimal competitive environment. However, real interactions and competitors are not always available, making it difficult for learners to maintain their motivation and learning efficiency. Furthermore, existing systems may not adequately manage stress levels or optimize learning outcomes. A new system using virtual competitors to solve these issues and enable learners to study efficiently and effectively is needed.

[1432] 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.

[1433] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting data of the virtual competitor to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting settings of the virtual competitor, means for transmitting adjustment data of the virtual competitor to the terminal, means for displaying the virtual competitor in three dimensions using a head-mounted display, and means for the learner to experience a realistic competition via the head-mounted display. This allows the learner to efficiently and effectively progress in their learning in an appropriate competitive environment, maximizing learning effectiveness and minimizing stress.

[1434] "Basic information of learners" refers to information that identifies individuals, such as the learner's name, age, and affiliated institution.

[1435] "Learning history" refers to data that records the content, grades, and progress of a learner's past learning.

[1436] A "server" is a computer system for storing, managing, and analyzing data.

[1437] A "database" is a collection of information that systematically stores and manages learners' basic information and learning history.

[1438] A "virtual competitor" is a virtual character or avatar created to compete with the learner.

[1439] A "terminal" is a computing device operated by a learner to exchange data with a server.

[1440] A "head-mounted display" is an output device worn on the head to display visual information.

[1441] "3D display" is a technique for displaying objects in three dimensions, providing the user with a sense of depth.

[1442] "Stress level" is an indicator of the degree of psychological and physiological stress felt by learners.

[1443] "Learning effect" refers to the degree of improvement in knowledge and skills that a learner gains through learning.

[1444] "Response" refers to a reply or answer given by a learner to a task or question.

[1445] "Feedback" refers to evaluation and advice provided based on learner responses and competition results.

[1446] "Adjustment data" refers to specific parameters and information for changing the settings of a virtual competitor.

[1447] "Analysis" is the process of clarifying patterns and characteristics of data using basic information and learning history of learners.

[1448] An "immersive competitive experience" is an experience that allows players to compete in a virtual environment with a feeling close to reality.

[1449] A "generative AI model" is a computational model that uses machine learning algorithms to create new virtual competitors based on data.

[1450] A "prompt" is an instruction or question input to an AI model.

[1451] The present invention is a system that inputs basic information and learning history of a learner, analyzes the data, generates an optimal virtual competitor, and provides the learner with an appropriate competitive environment. A specific method for implementing this system will be described.

[1452] System configuration

[1453] 1. User terminal and head-mounted display

[1454] Learners use smartphones and head-mounted displays (HMDs).

[1455] Provides an interface for entering basic information and learning history of learners.

[1456] 2. Server

[1457] A cloud server (e.g., AWS) for storing, managing, and analyzing data.

[1458] A database (e.g., Amazon RDS) to store learner data.

[1459] Machine learning algorithms (e.g., TensorFlow) for data analysis and virtual competitor generation.

[1460] 3. Database

[1461] Systematically store learner's basic information and learning history.

[1462] It is designed to allow quick access to and analysis of the data you need.

[1463] Program processing

[1464] Initial Setup and Data Collection

[1465] 1. User Registration

[1466] The user uses the terminal to enter basic information (such as name, age, and learning institution information).

[1467] The terminal sends the entered basic information to the server, which stores it in a database.

[1468] 2. Collecting learning history

[1469] Users enter the results of mock exams and progress in classes into the terminal.

[1470] The terminal sends the collected learning history data to the server, which stores it in a database.

[1471] Data analysis and virtual competitor generation

[1472] 3. Data Analysis

[1473] The server analyzes the learner's basic information and learning history stored in the database.

[1474] Using a machine learning algorithm (TensorFlow), we identify learners' strengths, weaknesses, and learning patterns.

[1475] 4. Creating Virtual Competitors

[1476] Based on the analysis results, the most suitable virtual competitor for the learner is generated.

[1477] The virtual competitors are set with difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[1478] Interface, Interaction and Competition

[1479] 5. Transmission of competitor data

[1480] The server transmits data of the generated virtual competitor to the terminal.

[1481] The user uses a head-mounted display to visually see their virtual opponent in 3D.

[1482] 6. Dialogue and Competition

[1483] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[1484] The terminal compiles the user's responses and the answers of the virtual competitors in real time and provides feedback.

[1485] Feedback and Adjustments

[1486] 7. Stress Level Monitoring

[1487] An interface is provided for users to input the stress level they felt during the competition.

[1488] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[1489] 8. Strengthening or weakening virtual competitors

[1490] The server adjusts the settings of the next virtual competitor based on the received data.

[1491] Dynamically adjust the difficulty of the virtual competitor according to the learner's perceived stress level and learning effectiveness.

[1492] Specific examples

[1493] 1. Example of entering basic user information

[1494] When a new candidate uses the system, they enter their name, age, name of their learning institution, etc. into the terminal.

[1495] The device sends this basic information to the server, which stores it in a database.

[1496] 2. Learning history input and analysis example

[1497] Candidates take the mock test and enter the results into a terminal, which records the score, answer time, and questions answered incorrectly in detail.

[1498] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[1499] 3. Example of Virtual Competitor Generation

[1500] The analysis results indicate that the test-taker is good at mathematics but weak at English.

[1501] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[1502] 4. Examples of dialogue and competition

[1503] When a candidate takes a mock test on their device, they are presented with a scenario in which a virtual competitor is also taking the test at the same time.

[1504] When the user uses a head-mounted display, the virtual opponent is displayed in three dimensions and provides real-time feedback.

[1505] Prompt Sentence Examples

[1506] Describe the steps for users to enter their learning history and save it on a cloud server. Next, develop a system that uses a machine learning algorithm to generate a virtual opponent based on that data and competes with the learner in real time. Specifically, describe the flow, including analysis using TensorFlow, data storage on AWS, and real-time updates to the user interface.

[1507] In this way, the present invention is designed to help learners study efficiently and effectively, and by providing an immersive competitive experience using a head-mounted display, it is possible to maximize learning effectiveness while minimizing stress.

[1508] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1509] Step 1:

[1510] User Registration

[1511] The user uses a smartphone or head-mounted display to input basic information (such as name, age, and information about the institution of study). The input basic information is sent from the device to the server. The server stores the received basic information in a database. The input is basic information, and the output is the basic information stored in the database.

[1512] Step 2:

[1513] Collection of learning history

[1514] Users enter mock test results and lesson progress into their terminal. The entered learning history data is sent from the terminal to the server. The server stores the received learning history data in a database. The input is learning history data, and the output is the learning history stored in the database.

[1515] Step 3:

[1516] Data analysis

[1517] The server retrieves the learner's basic information and learning history stored in the database. Using a machine learning algorithm (TensorFlow), it performs analysis to identify the learner's strong and weak subjects and learning patterns. The input is basic information and learning history data, and the output is the analysis results of the learner's strong and weak subjects and learning patterns.

[1518] Step 4:

[1519] Virtual Competitor Creation

[1520] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The generated virtual competitor is registered with settings, personality, and behavior patterns that correspond to the learner's strong and weak subjects. The input is the analysis results, and the output is data on the generated virtual competitor.

[1521] Step 5:

[1522] Submitting competitor data

[1523] The server sends the generated virtual competitor data to the terminal. The user can visually confirm the virtual competitor in 3D using a head-mounted display. The input is the virtual competitor data, and the output is the 3D virtual competitor displayed on the head-mounted display.

[1524] Step 6:

[1525] Dialogue and Competition

[1526] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions. The terminals compile the user's responses and the answers of the virtual competitors in real time and send them to a server. The input is the responses of the user and the virtual competitors, and the output is the compiled results.

[1527] Step 7:

[1528] Generate feedback

[1529] The server generates feedback based on the learner's responses and the competition results. The generated feedback is sent to the terminal and provided to the user. The inputs are the learner's responses and the competition results, and the output is the generated feedback.

[1530] Step 8:

[1531] Stress level monitoring

[1532] Users input the stress level they felt during the competition. The input stress level data is sent from the device to the server. The server uses this data to adjust future dialogue settings and the difficulty of the competition. The input is stress level data, and the output is the adjusted difficulty setting for the competition.

[1533] Step 9:

[1534] Strengthening or weakening virtual competitors

[1535] The server adjusts the settings of the next virtual competitor based on the received data. It dynamically adjusts the difficulty of the virtual competitor according to the learner's stress level and learning effect. The input is the received data and feedback, and the output is the adjusted settings of the virtual competitor.

[1536] 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.

[1537] System Overview and Operation

[1538] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[1539] Program processing overview

[1540] Initial Setup and Data Collection

[1541] 1. User Registration

[1542] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[1543] The terminal sends the entered basic information to the server, which stores it in a database.

[1544] 2. Collecting learning history

[1545] Users enter the results of mock exams and progress in classes into the terminal.

[1546] The terminal sends the collected learning history data to the server, which stores it in a database.

[1547] 3. Collecting Emotional Data

[1548] While the user is using the device to study or take a practice test, the device collects facial and voice data through its camera and microphone.

[1549] The emotion engine analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[1550] The terminal transmits the emotion data analyzed by the emotion engine to the server.

[1551] Data analysis and virtual competitor generation

[1552] 4. Data Analysis

[1553] The server analyzes the basic information, learning history, and emotional data stored in the database.

[1554] The server uses machine learning algorithms to identify a learner's strengths and weaknesses, learning patterns, and emotional state.

[1555] 5. Creating Virtual Competitors

[1556] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[1557] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[1558] Interface, Interaction and Competition

[1559] 6. Transmission of competitor data

[1560] The server transmits data of the generated virtual competitor to the terminal.

[1561] The terminal prepares to display the virtual competitor on the user interface based on the received data.

[1562] 7. Dialogue and Competition

[1563] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[1564] The user and the virtual competitor proceed through mock tests and study sessions.

[1565] Feedback and Adjustments

[1566] 1. Providing Feedback

[1567] The device compiles the results of practice tests and study sessions and provides feedback to the user, including scores, explanations of incorrect answers, and study advice.

[1568] 2. Utilizing Emotional Data

[1569] The emotion engine monitors the user's emotional state during the learning session and transmits it to the server.

[1570] The server dynamically adjusts the behavior and dialogue scripts of the virtual competitors based on the emotional data.

[1571] 3. Stress management and difficulty adjustment

[1572] Based on the user's stress level and learning effect, the server adjusts the virtual competitor's settings. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the stress level is low, the server raises the difficulty.

[1573] Specific examples

[1574] 1. Example of entering basic information and learning history

[1575] To use the system for the first time, examinee C enters basic information and the results of the mock test on a terminal. The terminal sends this data to the server, which then stores it in a database.

[1576] 2. Emotion data collection and analysis example

[1577] While Candidate C is taking the mock exam, the device's camera and microphone collect facial and voice data, which the emotion engine analyzes to assess stress and concentration levels.

[1578] The analysis results (e.g., "I'm anxious during the exam," "I'm concentrating," etc.) are sent to the server.

[1579] 3. Virtual Competitor Creation and Interaction Examples

[1580] Based on the analysis results, the server generates the optimal virtual competitor for test-taker C. For example, it sets a well-balanced competitor who is good at English and also fairly good at mathematics.

[1581] When Test Taker C takes a mock test with the virtual competitor in his next study session, the competitor answers in real time, and the dialogue continues.

[1582] 4. Feedback and Adjustment Examples

[1583] After the mock test is completed, the device displays the results (score, explanations of incorrect answers, etc.) and also provides feedback based on emotional data.

[1584] When Test Taker C enters his / her satisfaction and stress level from the study session into his / her device, the server uses this information to adjust the settings of the virtual competitor and reflect them in the next session.

[1585] In this way, the present invention, which is combined with an emotion engine, can provide an optimal learning environment while taking into account the user's emotional state, thereby maximizing learning effectiveness.

[1586] The processing flow will be explained below.

[1587] Step 1:

[1588] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[1589] Step 2:

[1590] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[1591] Step 3:

[1592] While a user is using the device to study or take a practice test, the device transmits facial and voice data via a camera and microphone to the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[1593] Step 4:

[1594] The device sends the emotional data analyzed by the emotion engine to the server, which stores it in a database and integrates it with previous learning history for further analysis.

[1595] Step 5:

[1596] The server analyzes the basic information, learning history, and emotional data stored in the database, and uses machine learning algorithms to identify the learner's strengths and weaknesses, learning patterns, and emotional state.

[1597] Step 6:

[1598] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The virtual competitor is set to a level of difficulty, personality, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[1599] Step 7:

[1600] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[1601] Step 8:

[1602] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[1603] Step 9:

[1604] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[1605] Step 10:

[1606] The device compiles the test results and emotional data and provides feedback to the user, including the score, explanations of incorrect answers, and study advice.

[1607] Step 11:

[1608] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[1609] Step 12:

[1610] The server adjusts the virtual competitor's settings based on the user's stress level, learning effect, and emotional data. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the user's stress level is low, the server raises the difficulty.

[1611] Step 13:

[1612] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[1613] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[1614] Example 2

[1615] 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."

[1616] Today's learners face diverse learning environments, requiring optimal learning support tailored to their individual learning styles and emotional states. However, traditional learning systems do not take the user's emotional state into account, making it difficult to provide a personalized, competitive environment that maximizes learning efficiency. Furthermore, there are a lack of methods to enhance learning effectiveness while appropriately managing learners' stress levels. This makes it difficult for learners to maintain their motivation to study.

[1617] 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.

[1618] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for collecting emotional data from the user's terminal during learning and practice tests, means for transmitting the emotional data to the server, means for analyzing the basic information, learning history, and emotional data from the database and generating a virtual competitor optimal for the learner, means for transmitting data on the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the results of the competition to the server, means for generating feedback on the learner's responses, the results of the competition, and the emotional data and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the settings of the virtual competitor, and means for transmitting adjustment data on the virtual competitor to the terminal. This makes it possible to provide an optimal learning environment and manage stress to maximize learning efficiency while taking the learner's emotional state into consideration.

[1619] "Learner" refers to the person receiving education and the entity using the system.

[1620] "Basic information" refers to personal information such as the learner's name, age, and school information.

[1621] "Learning history" refers to information about a learner's past learning activities, such as mock test results and class progress.

[1622] A "terminal" is a device used by learners to input and output information. Examples include personal computers and smartphones.

[1623] A "server" refers to a computer system that performs processes such as storing, analyzing, sending and receiving data.

[1624] A "database" refers to a system that systematically stores and manages data such as basic information, learning history, and emotional data.

[1625] "Emotional data" refers to data on the emotional state of a learner obtained from facial expressions, voice, etc.

[1626] "Emotion engine" refers to software or algorithms used to analyze emotion data and identify a learner's emotional state.

[1627] "Virtual competitor" refers to a virtual competitor corresponding to a learner, which is generated according to the characteristics of the learner.

[1628] "Dialogue script" refers to the language and behavioural scenarios that a virtual competitor uses in dialogue with learners.

[1629] "Feedback" refers to evaluations and advice provided based on learners' learning results and emotional data.

[1630] "Stress level" refers to the degree of stress a learner feels while studying.

[1631] "Learning outcomes" refer to the results and improvement in knowledge that learners achieve through learning activities.

[1632] "Adjustment Data" refers to data for modifying the settings of a virtual competitor.

[1633] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[1634] Hardware and software used

[1635] The present invention uses the following hardware and software:

[1636] Device: The device used by the learner, such as a computer, tablet, or smartphone.

[1637] Server: A computer system that stores, analyzes, sends and receives data. For example, a cloud-based server can be used.

[1638] Database: A system that systematically stores and manages basic information, learning history, emotional data, etc. Specifically, database systems such as MySQL and MongoDB are used.

[1639] Emotion engine: Software or algorithms for analyzing emotion data and identifying the learner's emotional state, specifically using Python's OpenCV and Google's Cloud Speech-to-Text API.

[1640] Machine learning algorithm: The algorithm used for analysis processing, specifically Scikit-learn and TensorFlow.

[1641] Specific explanation of the system

[1642] User registration and basic information entry

[1643] The user uses the terminal to enter basic information (such as name, age, school information, etc.). The user enters this information into the input form displayed on the terminal screen and presses the "Submit" button. The entered basic information is sent from the terminal to the server, which then stores it in a database.

[1644] Collection of learning history

[1645] Users enter their mock test results and progress in classes into the device. The device then sends the entered learning history data to the server, which then stores it in a database. For example, this data might include "Math: 85 points, English: 90 points, Science: 78 points, Social Studies: 82 points."

[1646] Emotion data collection and analysis

[1647] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data. The emotion engine analyzes this data in real time to identify the user's emotional state. For example, emotions such as "nervous" or "concentrated" may be identified, and the analysis results are sent from the device to the server.

[1648] Data analysis and virtual competitor generation

[1649] The server analyzes the basic information, learning history, and emotional data stored in the database. It uses machine learning algorithms to identify the learner's strong and weak subjects, learning patterns, and emotional state. Based on this, it generates the optimal virtual competitor. For example, if a learner is weak in English but good at math, it will generate a virtual competitor accordingly.

[1650] User Interface and Competitor View

[1651] The server transmits data about the generated virtual competitor to the terminal. The terminal prepares to display the virtual competitor on the user interface based on the received data. The user can then start interacting with the virtual competitor via the terminal and proceed with the mock test or learning session.

[1652] Providing feedback and making adjustments

[1653] The results of mock tests and study sessions are sent from the device to a server. The server then generates feedback based on this information and provides it to the learner. The feedback includes the student's score, explanations for incorrect answers, and study advice. Furthermore, the system dynamically adjusts the virtual competitor's settings based on the emotional data and reflects them in the next session. For example, if the user's stress level is high, the system may adjust the difficulty of the virtual competitor.

[1654] Specific examples

[1655] 1. After entering user information

[1656] Name: Yamada Taro

[1657] Age: 17

[1658] School information: 〇〇High School

[1659] 2. Example of mock test result input

[1660] Mock exam results:

[1661] Mathematics: 85 points

[1662] English: 90 points

[1663] Science: 78 points

[1664] Social: 82 points

[1665] 3. Example of emotion data analysis

[1666] Emotions during exams: Impatience

[1667] Concentration: High

[1668] Expression: Tense

[1669] 4. Examples of Providing Feedback

[1670] Mock exam results:

[1671] Score: 85 points

[1672] Wrong answer: Question 5, Question 8

[1673] Study advice: Focus on grammar next time

[1674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1675] Step 1:

[1676] User Registration

[1677] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[1678] Input: The user enters their name, age, and school information into the input form on the device and presses the "Submit" button.

[1679] Data processing and calculation: The device formats this information and sends it to the server using the HTTPS protocol.

[1680] Output: The server stores the received basic information in a database.

[1681] Specific behavior: The device detects user input in real time and displays a confirmation message after submission.

[1682] Step 2:

[1683] Collection of learning history

[1684] Users enter the results of mock exams and progress in classes into the terminal.

[1685] Input: The user enters the scores for each subject in the mock test and presses the submit button.

[1686] Data processing and calculation: The terminal converts the input data into JSON format and sends it to the server.

[1687] Output: The server stores the received learning history in a database.

[1688] What happens: The terminal validates the input data, displays warning messages if necessary, and displays a confirmation message after the data has been sent.

[1689] Step 3:

[1690] Collecting Emotional Data

[1691] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data.

[1692] Input: The device collects the user's facial expressions and voice in real time using a camera and microphone while learning.

[1693] Data processing and calculation: The emotion engine processes the collected facial expression data and analyzes the voice data to identify the user's emotional state (e.g., joy, tension, impatience).

[1694] Output: The analysis results (emotion data) are sent to the server and stored in a database.

[1695] Specific operation: The device periodically collects data and sends it to the server at each collection interval. The device is designed not to notify the user when data is collected.

[1696] Step 4:

[1697] Data analysis

[1698] The server analyzes the basic information, learning history, and emotional data stored in the database.

[1699] Input: The server retrieves basic information, learning history, and emotion data from the database.

[1700] Data processing and computation: Use machine learning algorithms (e.g., Scikit-learn, TensorFlow) to identify strengths and weaknesses, learning patterns, and emotional states.

[1701] Output: The analysis results are output as data that can be used to generate virtual competitors.

[1702] Specific operation: The server periodically executes the analysis task and stores the results in a database. The server is also configured to provide immediate feedback to the learner on the analysis results.

[1703] Step 5:

[1704] Virtual Competitor Creation

[1705] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[1706] Input: Basic information, learning history, and analysis results of emotion data.

[1707] Data processing and calculation: Based on the analysis results, the server sets the virtual competitor's strong and weak subjects, personality, and behavioral patterns.

[1708] Output: Virtual competitor data is generated and sent to the terminal.

[1709] What it does: The server automatically adjusts the virtual competitor settings to generate a competitor customized to the user's learning needs.

[1710] Step 6:

[1711] Submitting and Displaying Competitor Data

[1712] The server transmits data of the generated virtual competitor to the terminal.

[1713] Input: Virtual competitor data.

[1714] Data processing and calculation: The server converts the data into an appropriate format and sends it to the terminal.

[1715] Output: The terminal receives data to display the virtual competitors in the user interface.

[1716] Specific operation: When the terminal receives the competitor's data, it displays it on the screen and provides an interface that allows the user to interact with the competitor.

[1717] Step 7:

[1718] Dialogue and Competition

[1719] The user initiates a dialogue with a virtual competitor via the terminal.

[1720] Input: User interactions and responses to competitions.

[1721] Data processing and calculation: The terminal generates responses based on the dialogue script received from the server and processes the competition results in real time.

[1722] Output: The device sends the progress of the interaction and competition to the server.

[1723] Specific operation: The terminal processes user input in real time and displays the responses of virtual competitors according to the dialogue script. The competition results are periodically sent to the server.

[1724] Step 8:

[1725] Providing feedback

[1726] The server generates feedback based on the results of the learning session.

[1727] Input: Competition results, sentiment data, user responses.

[1728] Data processing and calculation: The server aggregates this data and generates feedback, including incorrect answers and study advice.

[1729] Output: The generated feedback is sent to the device.

[1730] What happens: The device notifies the user of the feedback and displays details on the screen, including the score and areas for improvement.

[1731] Step 9:

[1732] Monitor and regulate stress levels

[1733] The emotion engine monitors the user's stress level and transmits it to the server.

[1734] Input: Facial and voice data of the user during training.

[1735] Data processing and computation: Analyzes emotional state to identify stress levels and adjusts virtual competitor settings accordingly.

[1736] Output: The adjustment data is sent to the device and reflected in the next training session.

[1737] How it works: The server analyzes emotional data in real time and dynamically adjusts the difficulty and dialogue scripts of competitors.

[1738] (Application example 2)

[1739] 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."

[1740] Conventional learning systems often provide a uniform learning environment without considering the learner's emotional state or stress level. This makes it difficult for some learners to learn effectively, hindering efficient acquisition. Furthermore, it is not possible to provide optimal competition for each individual learner, leaving challenges in maintaining motivation and improving comprehension.

[1741] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1742] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the competition results to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings, means for transmitting adjustment data of the virtual competitor to the terminal, means for analyzing the learner's emotional state during learning using an emotion engine and dynamically adjusting the learning environment, and means for analyzing the learner's stress level in real time based on raw data and adjusting interactions during learning. This provides an optimal learning environment that takes the learner's emotional state and stress level into consideration, enabling efficient learning and maximizing learning effects.

[1743] "Learner" refers to a person who acquires knowledge and skills in accordance with an educational program or curriculum.

[1744] "Basic information" refers to information for identifying a learner, such as the learner's name, age, and school information.

[1745] "Learning history" is a record of a learner's past mock test results, progress in classes, and so on.

[1746] "Server" refers to a computer system that stores data, analyzes data, generates feedback, etc.

[1747] A "database" is a system that organizes and stores data such as basic information and learning history.

[1748] A "virtual competitor" refers to a virtual entity that competes with learners in learning progress, mock exams, etc.

[1749] "Devices" refer to information devices such as smartphones, tablets, and personal computers used by learners.

[1750] An "emotion engine" is an algorithm or program that analyzes a learner's emotional state from their facial expressions, voice, etc.

[1751] "Stress level" refers to the degree of mental tension a learner feels while studying.

[1752] "Feedback" refers to advice and evaluation provided based on learners' responses and competition results.

[1753] "Interaction" refers to the process of interaction between learners and virtual competitors during learning.

[1754] System Overview

[1755] This invention is a system related to "student," "basic information," "learning history," "server," "database," "virtual competitor," "terminal," "emotion engine," "stress level," "feedback," and "interaction." The aim is to maximize the learning effect of learners, and in particular to provide an optimal learning environment by utilizing the virtual competitor and emotion engine.

[1756] Technology used

[1757] The system is implemented using the following technologies:

[1758] 1. Database Management System: MySQL

[1759] 2. Backend: Python (Django Framework)

[1760] 3. Frontend: React Native

[1761] 4. Emotion engine: OpenAI API (emotion analysis model)

[1762] 5. Real-time communication: WebSocket

[1763] Process Overview

[1764] 1. User registration and information entry

[1765] Learners enter basic information (such as name, age, and school information) through their devices. The data entered on the devices is sent to and stored in a MySQL database through the back-end Django framework.

[1766] 2. Collecting learning history

[1767] Students enter their mock exam results and class progress information into the terminal, and the input data is stored in a MySQL database via a Django application.

[1768] 3. Emotional Data Collection and Analysis

[1769] During training, facial and voice data is collected via the device's camera and microphone. The collected data is then analyzed using the OpenAI API, and the results are sent to the server in real time.

[1770] 4. Creating Virtual Competitors

[1771] A machine learning algorithm built in Python uses stored basic information, learning history, and emotional data to generate the optimal virtual competitor.

[1772] 5. Dialogue and Competition

[1773] The virtual competitor data is displayed on a terminal interface built with React Native, and WebSocket is used to realize real-time interaction between learners and virtual competitors.

[1774] 6. Feedback and Adjustments

[1775] Feedback generated based on the competition results and the learner's stress level is sent to the device, which monitors the learner's stress level in real time and dynamically adjusts the virtual competitor's settings.

[1776] Specific examples

[1777] For example, when a learner starts a math mock test, the device's camera and microphone collect emotional data through facial expressions and voice, which is then analyzed through the OpenAI API. The analysis results are sent to the server, which generates the optimal virtual competitor. The virtual competitor then solves the mock test together in real time, which is displayed via React Native. Feedback is generated based on the learner's responses and the competition results, and sent to the device. The difficulty level of the virtual competitor and the dialogue script are dynamically adjusted based on the learner's stress level.

[1778] Prompt statement

[1779] Below are some example prompts for sentiment analysis:

[1780] Please rate the test taker's level of impatience and concentration based on the following statements:

[1781] "Throughout the exam, he would often take deep breaths and stare at the questions with furrowed brows. After a moment, he would grip his pen tighter, clearly confused."

[1782] Through these methods, an optimal learning environment is provided that takes into account the learner's emotional state and stress level.

[1783] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1784] Step 1:

[1785] The user enters basic information

[1786] The user enters basic information (such as name, age, school information, etc.) through the terminal. This input data is temporarily saved on the terminal and then sent to the server. Specifically, a basic information form is displayed, the user fills in the required fields, and when the user presses the data submit button, the data is sent to the server via the Django framework.

[1787] Input: Basic information data

[1788] Output: Basic information sent to the server

[1789] Step 2:

[1790] The server stores basic information in a database

[1791] The server stores the received basic information in a database, and the Django framework generates and executes commands to insert the received data into a MySQL database.

[1792] Input: Received basic information data

[1793] Output: Basic information stored in the database

[1794] Step 3:

[1795] The user enters their learning history

[1796] Users enter their mock test results and progress in classes into their devices. The data entered by the user is temporarily saved and then sent to the server. After filling out the form on the device, the data is sent to the server and received.

[1797] Input: Learning history data

[1798] Output: Learning history sent to the server

[1799] Step 4:

[1800] The server saves the learning history in a database

[1801] The server stores the received learning history data in a database. The Django framework generates and executes commands to insert the received data into a MySQL database.

[1802] Input: Received learning history data

[1803] Output: Learning history stored in the database

[1804] Step 5:

[1805] Collect user sentiment data

[1806] During learning, the camera and microphone on the user's device (smartphone, smart glasses, head-mounted display) collect facial expressions and voice. This data is temporarily stored in the device's local memory. Specifically, the camera and microphone are programmed to automatically start collecting data as soon as learning begins.

[1807] Input: facial expression and voice data

[1808] Output: Temporarily saved emotion data

[1809] Step 6:

[1810] Analyzing emotional data with an emotion engine

[1811] The emotion data stored on the device is analyzed by the emotion engine using the OpenAI API, and the analysis results are output as stress levels and emotional states and sent to the server.

[1812] Input: Temporarily saved emotion data

[1813] Output: Analyzed emotional data (stress level, emotional state)

[1814] Step 7:

[1815] The server analyzes basic information, learning history, and emotional data.

[1816] The server uses machine learning algorithms to analyze the basic information, learning history, and emotional data stored in the database. As a result, it generates the most suitable virtual competitor for the learner. Specifically, a machine learning algorithm written in Python is used to analyze the data and generate a model.

[1817] Input: Basic information, learning history, emotional data

[1818] Output: Virtual competitor data

[1819] Step 8:

[1820] The server sends the virtual competitor data to the terminal.

[1821] The server sends the generated virtual competitor data to the terminal using the Django framework and WebSocket for real-time communication.

[1822] Input: Virtual competitor data

[1823] Output: Virtual competitor data sent to the terminal

[1824] Step 9:

[1825] Users can interact and compete with virtual competitors

[1826] Users interact and compete with virtual opponents displayed on their devices, and interactions are managed in real time through React Native, including answering multiple-choice questions and chat-style conversations.

[1827] Input: Virtual competitor data sent to the terminal

[1828] Output: Interaction and competition results

[1829] Step 10:

[1830] The device sends the results of the competition to the server.

[1831] The user's competition results are sent from the terminal to the server. Data during the competition is collected in real time and sent to the server through the Django framework.

[1832] Input: Dialogue and competition results

[1833] Output: Interaction and competition results sent to the server

[1834] Step 11:

[1835] The server generates feedback and sends it to the device

[1836] The server generates feedback based on the received competition result data. The feedback includes points scored, incorrect answers, and study advice. The generated feedback is sent to the device.

[1837] Input: Dialogue and competition results

[1838] Output: Feedback data

[1839] Step 12:

[1840] Users can review the feedback and apply it to their next learning.

[1841] Users can check the feedback displayed on their devices and use it to improve their learning, leading to more effective learning in the next session. Specifically, they can use the feedback to revise and improve their learning plan.

[1842] Input: Feedback data

[1843] Output: Maximized learning effect

[1844] 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.

[1845] 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.

[1846] 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.

[1847] [Fourth embodiment]

[1848] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1849] 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.

[1850] 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).

[1851] 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.

[1852] 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.

[1853] 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).

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] 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.

[1860] 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."

[1861] System Overview and Operation

[1862] This system inputs basic information and learning history of a learner and analyzes that data to generate a virtual opponent that is optimal for the learner. This system provides a moderate competitive environment, maximizing learning effectiveness while managing stress.

[1863] Program processing overview

[1864] Initial Setup and Data Collection

[1865] 1. User Registration

[1866] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[1867] The terminal sends the entered basic information to the server, which stores it in a database.

[1868] 2. Collecting learning history

[1869] Users enter the results of mock exams and progress in classes into the terminal.

[1870] The terminal sends the collected learning history data to the server, which stores it in a database.

[1871] Data analysis and virtual competitor generation

[1872] 3. Data Analysis

[1873] The server analyzes the learner's basic information and learning history stored in the database, and identifies the learner's strong and weak subjects and learning patterns.

[1874] This analysis uses machine learning algorithms to accurately evaluate the learner's characteristics.

[1875] 4. Creating Virtual Competitors

[1876] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[1877] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[1878] Interface, Interaction and Competition

[1879] 5. Transmission of competitor data

[1880] The server transmits data of the generated virtual competitor to the terminal.

[1881] The receiving terminal displays the virtual competitor on the user interface.

[1882] 6. Dialogue and Competition

[1883] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[1884] The terminal compiles the user's answers and those of the virtual competitors in real time and provides feedback to the user.

[1885] Specific examples

[1886] 1. Example of entering basic user information

[1887] Candidate B is using the system for the first time, so he enters his name, age, school name, etc. on the terminal.

[1888] The device sends this basic information to the server, which stores it in a database.

[1889] 2. Learning history input and analysis example

[1890] Candidate B takes the mock test and enters the results into the terminal. The results are recorded in detail, including the score, answer time, and questions answered incorrectly.

[1891] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[1892] 3. Example of Virtual Competitor Generation

[1893] The analysis results indicate that candidate B is good at math but not so good at English.

[1894] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[1895] 4. Examples of dialogue and competition

[1896] When Candidate B takes a mock test on his device, a scenario is displayed in which a virtual competitor is also taking the test at the same time.

[1897] Results are displayed in real time and feedback is provided based on this.

[1898] Feedback and Adjustments

[1899] Stress level feedback from users

[1900] Candidate B enters the stress level he or she felt during the competition.

[1901] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[1902] Strengthening or weakening virtual competitors

[1903] The server will comprehensively evaluate the stress level and learning effect of test-taker B and adjust the settings of the next virtual competitor.

[1904] For example, if you feel too stressed, lower the difficulty of your competitors, and conversely, if you have more time, increase the difficulty.

[1905] In this way, the present invention is designed to allow test takers to study hard in an optimal learning environment, and to maximize the learning effect through moderate competition.

[1906] The processing flow will be explained below.

[1907] Step 1:

[1908] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[1909] Step 2:

[1910] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[1911] Step 3:

[1912] The server analyzes the basic information and learning history stored in the database and uses machine learning algorithms to identify the learner's strengths, weaknesses, and learning patterns.

[1913] Step 4:

[1914] Based on the analysis results, the server generates the virtual competitor that is best suited for the learner. The server creates the virtual competitor's data (character settings, behavior patterns, difficulty level, etc.).

[1915] Step 5:

[1916] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[1917] Step 6:

[1918] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[1919] Step 7:

[1920] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[1921] Step 8:

[1922] The device then provides the user with feedback based on the calculated score, including points, explanations of incorrect answers, and study advice.

[1923] Step 9:

[1924] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[1925] Step 10:

[1926] The server adjusts the settings of the virtual competitor based on the user's stress level and learning effect. For example, if the user's stress level is high, the difficulty of the competitor is lowered, and if the stress level is low, the difficulty is increased.

[1927] Step 11:

[1928] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[1929] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[1930] Example 1

[1931] 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."

[1932] In today's educational environment, efficient and effective learning requires personalized approaches tailored to individual strengths and weaknesses. It is also important to provide learners with a competitive environment to maintain their motivation and maximize their learning outcomes. Furthermore, stress levels must be monitored and adjusted to avoid excessive stress while learning. However, there is still a lack of learning support systems that meet these requirements.

[1933] 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.

[1934] In this invention, the server includes: means for inputting a learner's basic information and learning history; means for transmitting the basic information and learning history to the server; means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner; means for transmitting data on the virtual competitor to the learner's device; means for interacting with and competing with the virtual competitor on the device; means for transmitting the learner's responses and the competition results to the server; means for generating feedback on the learner's responses and the competition results and transmitting the feedback to the device; means for monitoring the learner's stress level and learning effect and adjusting the virtual competitor settings; means for transmitting the virtual competitor adjustment data to the device; means for setting and adjusting the virtual competitor's behavior pattern and difficulty level using a generative AI model; and means for providing feedback to the learner via a user interface. This provides a personalized competitive environment for the learner, maximizing learning effectiveness through appropriate competition. Furthermore, real-time feedback and adjustments according to the learner's stress level maintain an optimal learning environment.

[1935] A "learner" is an individual who is studying to receive an education.

[1936] "Basic information" refers to basic data about the learner, such as name, age, and school information.

[1937] "Learning history" is information about a learner's learning activities, such as mock test results and progress in classes.

[1938] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[1939] A "server" is a computer system used to store and analyze data, generate virtual competitors, and so on.

[1940] A "database" is a collection of data that stores basic information and learning history of learners, managed by a server.

[1941] "Analysis" is the process of examining data to extract patterns and characteristics.

[1942] A "virtual competitor" is a virtual opponent that is generated using machine learning algorithms or generative AI models and competes against the learner.

[1943] "Feedback" is information about a learner's achievements or performance that is provided based on the learner's responses or competition results.

[1944] "Stress level" is a value that indicates the degree of mental stress that a learner feels while studying or competing.

[1945] A "generative AI model" is a type of algorithm or technique that uses artificial intelligence technology to generate data.

[1946] A "user interface" is a screen or operating means that allows a user to operate a system and receive information.

[1947] This invention is a system that collects and analyzes a learner's basic information and learning history to generate a virtual competitor that is optimal for the learner. This system provides a moderate competitive environment, maximizing the effectiveness of learning while managing the learner's stress.

[1948] Initial Setup and Data Collection

[1949] 1. User Registration

[1950] User: The user enters basic information such as their name, age, and school information into the terminal on the initial screen of the system. For example, they might enter "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[1951] Terminal: The terminal generates an HTTP request to send the entered basic information to the server and sends the data to the server.

[1952] Server: The server stores the received basic information in a database and returns a response indicating successful registration to the device.

[1953] 2. Collecting learning history

[1954] User: The user enters the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[1955] Terminal: The terminal sends the input learning history data to the server.

[1956] Server: The server stores the received learning history data in a database.

[1957] Data analysis and virtual competitor generation

[1958] 3. Data Analysis

[1959] Server: The server retrieves basic information and learning history data of the learner from the database and analyzes it using machine learning algorithms (for example, Python's Scikit-learn library). It identifies the learner's strong and weak subjects and learning patterns.

[1960] 4. Creating Virtual Competitors

[1961] Server: Based on the analysis results, the server uses a generative AI model to generate the optimal virtual competitor for the learner. Specifically, it sets the competitor's strong and weak subjects and behavioral patterns.

[1962] Interface, Interaction and Competition

[1963] 5. Transmission of competitor data

[1964] Server: The server sends the data of the generated virtual competitor to the terminal.

[1965] Terminal: The terminal displays the received data on the user interface, allowing the user to check the information of the virtual competitors.

[1966] 6. Dialogue and Competition

[1967] User: A user competes against a virtual opponent through a terminal, such as a mock test. For example, the user starts a mock test and enters their answers to each question.

[1968] Terminal: The terminal compiles the user's answers in real time and simultaneously displays the answers of their virtual competitors.

[1969] Server: The server compiles all answer data in real time and sends the results to the device.

[1970] Feedback and Adjustments

[1971] 7. Stress level feedback

[1972] User: The user enters the stress level they felt during the race into the terminal. For example, they enter "Stress level: 4 (scale of 1 to 5)."

[1973] Device: The device sends the input stress level to the server.

[1974] Server: The server stores the received stress data in a database.

[1975] 8. Adjusting the next competitor

[1976] Server: The server will comprehensively evaluate the received stress level data and learning effect and adjust the settings of the next virtual competitor. For example, if the stress level is high, the number of favorite subjects for the next competitor will be reduced.

[1977] Prompt Sentence Examples

[1978] 1. Enter basic user information

[1979] "Please enter your name, age, and school name as a new user."

[1980] 2. Enter your learning history

[1981] "Please enter your mock test results (score, answer time, and questions you got wrong)."

[1982] 3. Setting up a virtual competitor

[1983] "Virtual competitor data received. Start the conversation."

[1984] 4. Enter your stress level

[1985] "Please rate the stress level you felt during the competition on a scale of 1 to 5 and enter it."

[1986] The system allows learners to effectively learn with virtual competitors that are optimized for their individual needs, and also provides appropriate stress-level measures to maximize learning outcomes.

[1987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1988] Step 1: User Registration

[1989] Input: The user enters basic information such as name, age, and school information into the terminal. For example, "Name: Yamada Taro," "Age: 17 years old," and "School name: Tokyo High School."

[1990] Operation:

[1991] User: Enter your name, age, and school information.

[1992] Terminal: Generates an HTTP request and sends the entered basic information to the server.

[1993] Server: Saves the received basic information in the database. If saving is successful, generates a response indicating successful registration and sends it to the device.

[1994] Output: A successful registration response from the server is displayed on the terminal.

[1995] Step 2: Collecting learning history

[1996] Input: The user inputs the results of the mock exam and the progress of the class into the terminal. For example, "Score: 90 points, Answer time: 30 minutes, Correct answer rate: 90%."

[1997] Operation:

[1998] User: Enter mock test results and class progress.

[1999] Terminal: Generates an HTTP request and sends the entered learning history data to the server.

[2000] Server: Stores the received learning history data in a database.

[2001] Output: Learning history data stored on the server.

[2002] Step 3: Data analysis

[2003] Input: The server retrieves the learner's basic information and learning history data from the database.

[2004] Operation:

[2005] Server: Performs analysis using machine learning algorithms (e.g., Python's Scikit-learn library) to identify learners' strengths and weaknesses and learning patterns.

[2006] Output: The analysis results provide data on the learner's strong and weak subjects, as well as their learning patterns.

[2007] Step 4: Generate a virtual competitor

[2008] Input: The server bases the parsed results.

[2009] Operation:

[2010] Server: Using a generative AI model, it generates a virtual competitor that is optimal for the learner, based on, for example, their strong and weak subjects, behavioral patterns, etc.

[2011] Output: Virtual competitor data is generated.

[2012] Step 5: Submit competitor data

[2013] Input: Server-generated virtual competitor data.

[2014] Operation:

[2015] Server: Sends the virtual competitor data to the device.

[2016] Terminal: Displays the received data in a user interface.

[2017] Output: Information about your virtual competitors will be displayed on your terminal.

[2018] Step 6: Dialogue and competition

[2019] Input: Practice test answers that users enter into the terminal.

[2020] Operation:

[2021] User: Answer practice test questions.

[2022] Terminal: User answers are collected in real time and the answers of virtual competitors are displayed simultaneously.

[2023] Server: Aggregates all answer data in real time.

[2024] Output: Mock test results are displayed in real time and feedback is provided.

[2025] Step 7: Stress Level Feedback

[2026] Input: The user enters their stress level into the device.

[2027] Operation:

[2028] User: Rate their stress level on a scale of 1 to 5 and enter it into the device.

[2029] Device: Sends stress level data to the server.

[2030] Server: Stores the received stress data in a database.

[2031] Output: Stress level data stored on the server.

[2032] Step 8: Adjust your next competitor

[2033] Input: Stress level data and learning effect data stored by the server.

[2034] Operation:

[2035] Server: Comprehensively evaluates the received stress level data and learning effect, and adjusts the settings of the next virtual competitor. For example, if the stress level is high, reduce the number of favorite subjects.

[2036] Output: The configuration data for the next virtual competitor is generated.

[2037] (Application example 1)

[2038] 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."

[2039] In today's educational environment, learners are required to study in an optimal competitive environment. However, real interactions and competitors are not always available, making it difficult for learners to maintain their motivation and learning efficiency. Furthermore, existing systems may not adequately manage stress levels or optimize learning outcomes. A new system using virtual competitors to solve these issues and enable learners to study efficiently and effectively is needed.

[2040] 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.

[2041] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for analyzing the basic information and learning history from the database and generating a virtual competitor optimal for the learner, means for transmitting data of the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting data of the virtual competitor to the server, means for generating feedback on the learner's responses and the competition results on the server and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting settings of the virtual competitor, means for transmitting adjustment data of the virtual competitor to the terminal, means for displaying the virtual competitor in three dimensions using a head-mounted display, and means for the learner to experience a realistic competition via the head-mounted display. This allows the learner to efficiently and effectively progress in their learning in an appropriate competitive environment, maximizing learning effectiveness and minimizing stress.

[2042] "Basic information of learners" refers to information that identifies individuals, such as the learner's name, age, and affiliated institution.

[2043] "Learning history" refers to data that records the content, grades, and progress of a learner's past learning.

[2044] A "server" is a computer system for storing, managing, and analyzing data.

[2045] A "database" is a collection of information that systematically stores and manages learners' basic information and learning history.

[2046] A "virtual competitor" is a virtual character or avatar created to compete with the learner.

[2047] A "terminal" is a computing device operated by a learner to exchange data with a server.

[2048] A "head-mounted display" is an output device worn on the head to display visual information.

[2049] "3D display" is a technique for displaying objects in three dimensions, providing the user with a sense of depth.

[2050] "Stress level" is an indicator of the degree of psychological and physiological stress felt by learners.

[2051] "Learning effect" refers to the degree of improvement in knowledge and skills that a learner gains through learning.

[2052] "Response" refers to a reply or answer given by a learner to a task or question.

[2053] "Feedback" refers to evaluation and advice provided based on learner responses and competition results.

[2054] "Adjustment data" refers to specific parameters and information for changing the settings of a virtual competitor.

[2055] "Analysis" is the process of clarifying patterns and characteristics of data using basic information and learning history of learners.

[2056] An "immersive competitive experience" is an experience that allows players to compete in a virtual environment with a feeling close to reality.

[2057] A "generative AI model" is a computational model that uses machine learning algorithms to create new virtual competitors based on data.

[2058] A "prompt" is an instruction or question input to an AI model.

[2059] The present invention is a system that inputs basic information and learning history of a learner, analyzes the data, generates an optimal virtual competitor, and provides the learner with an appropriate competitive environment. A specific method for implementing this system will be described.

[2060] System configuration

[2061] 1. User terminal and head-mounted display

[2062] Learners use smartphones and head-mounted displays (HMDs).

[2063] Provides an interface for entering basic information and learning history of learners.

[2064] 2. Server

[2065] A cloud server (e.g., AWS) for storing, managing, and analyzing data.

[2066] A database (e.g., Amazon RDS) to store learner data.

[2067] Machine learning algorithms (e.g., TensorFlow) for data analysis and virtual competitor generation.

[2068] 3. Database

[2069] Systematically store learner's basic information and learning history.

[2070] It is designed to allow quick access to and analysis of the data you need.

[2071] Program processing

[2072] Initial Setup and Data Collection

[2073] 1. User Registration

[2074] The user uses the terminal to enter basic information (such as name, age, and learning institution information).

[2075] The terminal sends the entered basic information to the server, which stores it in a database.

[2076] 2. Collecting learning history

[2077] Users enter the results of mock exams and progress in classes into the terminal.

[2078] The terminal sends the collected learning history data to the server, which stores it in a database.

[2079] Data analysis and virtual competitor generation

[2080] 3. Data Analysis

[2081] The server analyzes the learner's basic information and learning history stored in the database.

[2082] Using a machine learning algorithm (TensorFlow), we identify learners' strengths, weaknesses, and learning patterns.

[2083] 4. Creating Virtual Competitors

[2084] Based on the analysis results, the most suitable virtual competitor for the learner is generated.

[2085] The virtual competitors are set with difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses.

[2086] Interface, Interaction and Competition

[2087] 5. Transmission of competitor data

[2088] The server transmits data of the generated virtual competitor to the terminal.

[2089] The user uses a head-mounted display to visually see their virtual opponent in 3D.

[2090] 6. Dialogue and Competition

[2091] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions.

[2092] The terminal compiles the user's responses and the answers of the virtual competitors in real time and provides feedback.

[2093] Feedback and Adjustments

[2094] 7. Stress Level Monitoring

[2095] An interface is provided for users to input the stress level they felt during the competition.

[2096] The device sends this information to the server, which then adjusts future interaction settings and the difficulty of the competition.

[2097] 8. Strengthening or weakening virtual competitors

[2098] The server adjusts the settings of the next virtual competitor based on the received data.

[2099] Dynamically adjust the difficulty of the virtual competitor according to the learner's perceived stress level and learning effectiveness.

[2100] Specific examples

[2101] 1. Example of entering basic user information

[2102] When a new candidate uses the system, they enter their name, age, name of their learning institution, etc. into the terminal.

[2103] The device sends this basic information to the server, which stores it in a database.

[2104] 2. Learning history input and analysis example

[2105] Candidates take the mock test and enter the results into a terminal, which records the score, answer time, and questions answered incorrectly in detail.

[2106] The device sends this data to a server, where it is analyzed using machine learning algorithms.

[2107] 3. Example of Virtual Competitor Generation

[2108] The analysis results indicate that the test-taker is good at mathematics but weak at English.

[2109] Based on this, the server generates a virtual competitor who is good at English and has a balanced level.

[2110] 4. Examples of dialogue and competition

[2111] When a candidate takes a mock test on their device, they are presented with a scenario in which a virtual competitor is also taking the test at the same time.

[2112] When the user uses a head-mounted display, the virtual opponent is displayed in three dimensions and provides real-time feedback.

[2113] Prompt Sentence Examples

[2114] Describe the steps for users to enter their learning history and save it on a cloud server. Next, develop a system that uses a machine learning algorithm to generate a virtual opponent based on that data and competes with the learner in real time. Specifically, describe the flow, including analysis using TensorFlow, data storage on AWS, and real-time updates to the user interface.

[2115] In this way, the present invention is designed to help learners study efficiently and effectively, and by providing an immersive competitive experience using a head-mounted display, it is possible to maximize learning effectiveness while minimizing stress.

[2116] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2117] Step 1:

[2118] User Registration

[2119] The user uses a smartphone or head-mounted display to input basic information (such as name, age, and information about the institution of study). The input basic information is sent from the device to the server. The server stores the received basic information in a database. The input is basic information, and the output is the basic information stored in the database.

[2120] Step 2:

[2121] Collection of learning history

[2122] Users enter mock test results and lesson progress into their terminal. The entered learning history data is sent from the terminal to the server. The server stores the received learning history data in a database. The input is learning history data, and the output is the learning history stored in the database.

[2123] Step 3:

[2124] Data analysis

[2125] The server retrieves the learner's basic information and learning history stored in the database. Using a machine learning algorithm (TensorFlow), it performs analysis to identify the learner's strong and weak subjects and learning patterns. The input is basic information and learning history data, and the output is the analysis results of the learner's strong and weak subjects and learning patterns.

[2126] Step 4:

[2127] Virtual Competitor Creation

[2128] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The generated virtual competitor is registered with settings, personality, and behavior patterns that correspond to the learner's strong and weak subjects. The input is the analysis results, and the output is data on the generated virtual competitor.

[2129] Step 5:

[2130] Submitting competitor data

[2131] The server sends the generated virtual competitor data to the terminal. The user can visually confirm the virtual competitor in 3D using a head-mounted display. The input is the virtual competitor data, and the output is the 3D virtual competitor displayed on the head-mounted display.

[2132] Step 6:

[2133] Dialogue and Competition

[2134] Users interact with virtual competitors via their terminals and compete in mock tests and other competitions. The terminals compile the user's responses and the answers of the virtual competitors in real time and send them to a server. The input is the responses of the user and the virtual competitors, and the output is the compiled results.

[2135] Step 7:

[2136] Generate feedback

[2137] The server generates feedback based on the learner's responses and the competition results. The generated feedback is sent to the terminal and provided to the user. The inputs are the learner's responses and the competition results, and the output is the generated feedback.

[2138] Step 8:

[2139] Stress level monitoring

[2140] Users input the stress level they felt during the competition. The input stress level data is sent from the device to the server. The server uses this data to adjust future dialogue settings and the difficulty of the competition. The input is stress level data, and the output is the adjusted difficulty setting for the competition.

[2141] Step 9:

[2142] Strengthening or weakening virtual competitors

[2143] The server adjusts the settings of the next virtual competitor based on the received data. It dynamically adjusts the difficulty of the virtual competitor according to the learner's stress level and learning effect. The input is the received data and feedback, and the output is the adjusted settings of the virtual competitor.

[2144] 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.

[2145] System Overview and Operation

[2146] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[2147] Program processing overview

[2148] Initial Setup and Data Collection

[2149] 1. User Registration

[2150] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[2151] The terminal sends the entered basic information to the server, which stores it in a database.

[2152] 2. Collecting learning history

[2153] Users enter the results of mock exams and progress in classes into the terminal.

[2154] The terminal sends the collected learning history data to the server, which stores it in a database.

[2155] 3. Collecting Emotional Data

[2156] While the user is using the device to study or take a practice test, the device collects facial and voice data through its camera and microphone.

[2157] The emotion engine analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[2158] The terminal transmits the emotion data analyzed by the emotion engine to the server.

[2159] Data analysis and virtual competitor generation

[2160] 4. Data Analysis

[2161] The server analyzes the basic information, learning history, and emotional data stored in the database.

[2162] The server uses machine learning algorithms to identify a learner's strengths and weaknesses, learning patterns, and emotional state.

[2163] 5. Creating Virtual Competitors

[2164] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[2165] The virtual competitors are set to have difficulty levels, personalities, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[2166] Interface, Interaction and Competition

[2167] 6. Transmission of competitor data

[2168] The server transmits data of the generated virtual competitor to the terminal.

[2169] The terminal prepares to display the virtual competitor on the user interface based on the received data.

[2170] 7. Dialogue and Competition

[2171] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[2172] The user and the virtual competitor proceed through mock tests and study sessions.

[2173] Feedback and Adjustments

[2174] 1. Providing Feedback

[2175] The device compiles the results of practice tests and study sessions and provides feedback to the user, including scores, explanations of incorrect answers, and study advice.

[2176] 2. Utilizing Emotional Data

[2177] The emotion engine monitors the user's emotional state during the learning session and transmits it to the server.

[2178] The server dynamically adjusts the behavior and dialogue scripts of the virtual competitors based on the emotional data.

[2179] 3. Stress management and difficulty adjustment

[2180] Based on the user's stress level and learning effect, the server adjusts the virtual competitor's settings. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the stress level is low, the server raises the difficulty.

[2181] Specific examples

[2182] 1. Example of entering basic information and learning history

[2183] To use the system for the first time, examinee C enters basic information and the results of the mock test on a terminal. The terminal sends this data to the server, which then stores it in a database.

[2184] 2. Emotion data collection and analysis example

[2185] While Candidate C is taking the mock exam, the device's camera and microphone collect facial and voice data, which the emotion engine analyzes to assess stress and concentration levels.

[2186] The analysis results (e.g., "I'm anxious during the exam," "I'm concentrating," etc.) are sent to the server.

[2187] 3. Virtual Competitor Creation and Interaction Examples

[2188] Based on the analysis results, the server generates the optimal virtual competitor for test-taker C. For example, it sets a well-balanced competitor who is good at English and also fairly good at mathematics.

[2189] When Test Taker C takes a mock test with the virtual competitor in his next study session, the competitor answers in real time, and the dialogue continues.

[2190] 4. Feedback and Adjustment Examples

[2191] After the mock test is completed, the device displays the results (score, explanations of incorrect answers, etc.) and also provides feedback based on emotional data.

[2192] When Test Taker C enters his / her satisfaction and stress level from the study session into his / her device, the server uses this information to adjust the settings of the virtual competitor and reflect them in the next session.

[2193] In this way, the present invention, which is combined with an emotion engine, can provide an optimal learning environment while taking into account the user's emotional state, thereby maximizing learning effectiveness.

[2194] The processing flow will be explained below.

[2195] Step 1:

[2196] The user uses the terminal to input basic information (such as name, age, school information, etc.) The terminal sends the input basic information to the server, which then stores it in a database.

[2197] Step 2:

[2198] Users enter their mock test results and progress in classes into their devices. The devices then send the collected learning history data to the server, which then stores the received learning history data in a database.

[2199] Step 3:

[2200] While a user is using the device to study or take a practice test, the device transmits facial and voice data via a camera and microphone to the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, impatience).

[2201] Step 4:

[2202] The device sends the emotional data analyzed by the emotion engine to the server, which stores it in a database and integrates it with previous learning history for further analysis.

[2203] Step 5:

[2204] The server analyzes the basic information, learning history, and emotional data stored in the database, and uses machine learning algorithms to identify the learner's strengths and weaknesses, learning patterns, and emotional state.

[2205] Step 6:

[2206] Based on the analysis results, the server generates a virtual competitor that is optimal for the learner. The virtual competitor is set to a level of difficulty, personality, and behavioral patterns that correspond to the learner's strengths and weaknesses in subjects and emotional state.

[2207] Step 7:

[2208] The server transmits data of the generated virtual competitor to the terminal, and the terminal prepares to display the virtual competitor on the user interface based on the received data.

[2209] Step 8:

[2210] The user initiates a dialogue with a virtual competitor via the terminal, which generates responses based on dialogue scripts received from the server and manages the interaction with the user.

[2211] Step 9:

[2212] The user takes a mock test, and the device operates so that the user and the virtual competitor are simultaneously taking the test, tallying each other's answers in real time.

[2213] Step 10:

[2214] The device compiles the test results and emotional data and provides feedback to the user, including the score, explanations of incorrect answers, and study advice.

[2215] Step 11:

[2216] Users input their stress levels and learning satisfaction through the device, which then sends this data to the server.

[2217] Step 12:

[2218] The server adjusts the virtual competitor's settings based on the user's stress level, learning effect, and emotional data. For example, if the user's stress level is high, the server lowers the difficulty of the competitor, and if the user's stress level is low, the server raises the difficulty.

[2219] Step 13:

[2220] The server retransmits the adjusted virtual competitor data to the terminal, which prepares to display the adjusted virtual competitor during the next learning session.

[2221] In this way, the server, terminals, and users work together at each step to create a system that provides an optimal learning environment and moderate competition.

[2222] Example 2

[2223] 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."

[2224] Today's learners face diverse learning environments, requiring optimal learning support tailored to their individual learning styles and emotional states. However, traditional learning systems do not take the user's emotional state into account, making it difficult to provide a personalized, competitive environment that maximizes learning efficiency. Furthermore, there are a lack of methods to enhance learning effectiveness while appropriately managing learners' stress levels. This makes it difficult for learners to maintain their motivation to study.

[2225] 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.

[2226] In this invention, the server includes means for inputting a learner's basic information and learning history, means for transmitting the basic information and learning history to the server, means for storing the received basic information and learning history in a database, means for collecting emotional data from the user's terminal during learning and practice tests, means for transmitting the emotional data to the server, means for analyzing the basic information, learning history, and emotional data from the database and generating a virtual competitor optimal for the learner, means for transmitting data on the virtual competitor to the learner's terminal, means for interacting with and competing with the virtual competitor on the terminal, means for transmitting the learner's responses and the results of the competition to the server, means for generating feedback on the learner's responses, the results of the competition, and the emotional data and transmitting the feedback to the terminal, means for monitoring the learner's stress level and learning effect and adjusting the settings of the virtual competitor, and means for transmitting adjustment data on the virtual competitor to the terminal. This makes it possible to provide an optimal learning environment and manage stress to maximize learning efficiency while taking the learner's emotional state into consideration.

[2227] "Learner" refers to the person receiving education and the entity using the system.

[2228] "Basic information" refers to personal information such as the learner's name, age, and school information.

[2229] "Learning history" refers to information about a learner's past learning activities, such as mock test results and class progress.

[2230] A "terminal" is a device used by learners to input and output information. Examples include personal computers and smartphones.

[2231] A "server" refers to a computer system that performs processes such as storing, analyzing, sending and receiving data.

[2232] A "database" refers to a system that systematically stores and manages data such as basic information, learning history, and emotional data.

[2233] "Emotional data" refers to data on the emotional state of a learner obtained from facial expressions, voice, etc.

[2234] "Emotion engine" refers to software or algorithms used to analyze emotion data and identify a learner's emotional state.

[2235] "Virtual competitor" refers to a virtual competitor corresponding to a learner, which is generated according to the characteristics of the learner.

[2236] "Dialogue script" refers to the language and behavioural scenarios that a virtual competitor uses in dialogue with learners.

[2237] "Feedback" refers to evaluations and advice provided based on learners' learning results and emotional data.

[2238] "Stress level" refers to the degree of stress a learner feels while studying.

[2239] "Learning outcomes" refer to the results and improvement in knowledge that learners achieve through learning activities.

[2240] "Adjustment Data" refers to data for modifying the settings of a virtual competitor.

[2241] This system provides an optimal learning environment by inputting a learner's basic information and learning history and combining it with an emotion engine. This system analyzes the learner's emotional state, provides a moderately competitive environment, manages stress, and maximizes learning effectiveness.

[2242] Hardware and software used

[2243] The present invention uses the following hardware and software:

[2244] Device: The device used by the learner, such as a computer, tablet, or smartphone.

[2245] Server: A computer system that stores, analyzes, sends and receives data. For example, a cloud-based server can be used.

[2246] Database: A system that systematically stores and manages basic information, learning history, emotional data, etc. Specifically, database systems such as MySQL and MongoDB are used.

[2247] Emotion engine: Software or algorithms for analyzing emotion data and identifying the learner's emotional state, specifically using Python's OpenCV and Google's Cloud Speech-to-Text API.

[2248] Machine learning algorithm: The algorithm used for analysis processing, specifically Scikit-learn and TensorFlow.

[2249] Specific explanation of the system

[2250] User registration and basic information entry

[2251] The user uses the terminal to enter basic information (such as name, age, school information, etc.). The user enters this information into the input form displayed on the terminal screen and presses the "Submit" button. The entered basic information is sent from the terminal to the server, which then stores it in a database.

[2252] Collection of learning history

[2253] Users enter their mock test results and progress in classes into the device. The device then sends the entered learning history data to the server, which then stores it in a database. For example, this data might include "Math: 85 points, English: 90 points, Science: 78 points, Social Studies: 82 points."

[2254] Emotion data collection and analysis

[2255] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data. The emotion engine analyzes this data in real time to identify the user's emotional state. For example, emotions such as "nervous" or "concentrated" may be identified, and the analysis results are sent from the device to the server.

[2256] Data analysis and virtual competitor generation

[2257] The server analyzes the basic information, learning history, and emotional data stored in the database. It uses machine learning algorithms to identify the learner's strong and weak subjects, learning patterns, and emotional state. Based on this, it generates the optimal virtual competitor. For example, if a learner is weak in English but good at math, it will generate a virtual competitor accordingly.

[2258] User Interface and Competitor View

[2259] The server transmits data about the generated virtual competitor to the terminal. The terminal prepares to display the virtual competitor on the user interface based on the received data. The user can then start interacting with the virtual competitor via the terminal and proceed with the mock test or learning session.

[2260] Providing feedback and making adjustments

[2261] The results of mock tests and study sessions are sent from the device to a server. The server then generates feedback based on this information and provides it to the learner. The feedback includes the student's score, explanations for incorrect answers, and study advice. Furthermore, the system dynamically adjusts the virtual competitor's settings based on the emotional data and reflects them in the next session. For example, if the user's stress level is high, the system may adjust the difficulty of the virtual competitor.

[2262] Specific examples

[2263] 1. After entering user information

[2264] Name: Yamada Taro

[2265] Age: 17

[2266] School information: 〇〇High School

[2267] 2. Example of mock test result input

[2268] Mock exam results:

[2269] Mathematics: 85 points

[2270] English: 90 points

[2271] Science: 78 points

[2272] Social: 82 points

[2273] 3. Example of emotion data analysis

[2274] Emotions during exams: Impatience

[2275] Concentration: High

[2276] Expression: Tense

[2277] 4. Examples of Providing Feedback

[2278] Mock exam results:

[2279] Score: 85 points

[2280] Wrong answer: Question 5, Question 8

[2281] Study advice: Focus on grammar next time

[2282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2283] Step 1:

[2284] User Registration

[2285] The user uses the terminal to enter basic information (such as name, age, school information, etc.).

[2286] Input: The user enters their name, age, and school information into the input form on the device and presses the "Submit" button.

[2287] Data processing and calculation: The device formats this information and sends it to the server using the HTTPS protocol.

[2288] Output: The server stores the received basic information in a database.

[2289] Specific behavior: The device detects user input in real time and displays a confirmation message after submission.

[2290] Step 2:

[2291] Collection of learning history

[2292] Users enter the results of mock exams and progress in classes into the terminal.

[2293] Input: The user enters the scores for each subject in the mock test and presses the submit button.

[2294] Data processing and calculation: The terminal converts the input data into JSON format and sends it to the server.

[2295] Output: The server stores the received learning history in a database.

[2296] What happens: The terminal validates the input data, displays warning messages if necessary, and displays a confirmation message after the data has been sent.

[2297] Step 3:

[2298] Collecting Emotional Data

[2299] While the user is studying or taking a practice test, the device's camera and microphone collect facial and voice data.

[2300] Input: The device collects the user's facial expressions and voice in real time using a camera and microphone while learning.

[2301] Data processing and calculation: The emotion engine processes the collected facial expression data and analyzes the voice data to identify the user's emotional state (e.g., joy, tension, impatience).

[2302] Output: The analysis results (emotion data) are sent to the server and stored in a database.

[2303] Specific operation: The device periodically collects data and sends it to the server at each collection interval. The device is designed not to notify the user when data is collected.

[2304] Step 4:

[2305] Data analysis

[2306] The server analyzes the basic information, learning history, and emotional data stored in the database.

[2307] Input: The server retrieves basic information, learning history, and emotion data from the database.

[2308] Data processing and computation: Use machine learning algorithms (e.g., Scikit-learn, TensorFlow) to identify strengths and weaknesses, learning patterns, and emotional states.

[2309] Output: The analysis results are output as data that can be used to generate virtual competitors.

[2310] Specific operation: The server periodically executes the analysis task and stores the results in a database. The server is also configured to provide immediate feedback to the learner on the analysis results.

[2311] Step 5:

[2312] Virtual Competitor Creation

[2313] Based on the analysis results, the server generates the most suitable virtual competitor for the learner.

[2314] Input: Basic information, learning history, and analysis results of emotion data.

[2315] Data processing and calculation: Based on the analysis results...

Claims

1. A means for inputting basic information and learning history of the learner; means for transmitting the basic information and learning history to a server; A means for storing the received basic information and learning history in a database; means for analyzing the basic information and learning history from the database and generating a virtual competitor that is optimal for the learner; means for transmitting data of the virtual competitor to a learner's terminal; means for interacting and competing with said virtual competitors at said terminal; means for transmitting learner responses and competition results to a server; a means for generating feedback based on the learner's responses and the competition results in the server and transmitting the feedback to the terminal; a means of monitoring learners' stress levels and learning effectiveness and adjusting virtual competitor settings; The system includes means for transmitting the virtual competitor adjustment data to a terminal.

2. 2. The system according to claim 1, wherein the virtual competitor is set based on data on the learner's strengths and weaknesses in subjects.

3. 3. The system according to claim 1, wherein the terminal includes means for monitoring the stress level of the learner and transmitting the data to a server.

Images