system

Abstract

We provide the system. [Solution] Means of obtaining information entered by the user, Methods for analyzing training data, Based on the analysis, means for generating individual learning plans, A means for generating practice problems based on the aforementioned learning plan, A means for generating an explanation for the practice problem, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 Many learners cannot find the optimal learning method for themselves and have difficulty formulating an effective learning plan. In addition, existing individual tutoring services are expensive and difficult to access for a wide range of users. Therefore, there is a problem that learners with economic constraints in particular cannot receive sufficient learning support. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically generates a learning plan tailored to each individual learner by acquiring information input by the user and analyzing learning data. Furthermore, it provides a system that continuously supports learning progress by generating customized practice problems and their explanations based on the plan, and by recording and updating the user's learning history data. This makes it possible to provide optimal learning support to each learner at a low cost. 【0006】 "User" refers to a learner or user of an information system. 【0007】 "Information" encompasses all data and input provided by the user. 【0008】 "Learning data" refers to a series of data related to learning, such as a user's learning history, grades, and learning materials used. 【0009】 "Analysis" refers to the process of using collected training data to evaluate users' learning patterns and tendencies. 【0010】 A "learning plan" refers to a schedule of learning activities and learning materials tailored to the user, generated based on analysis. 【0011】 "Practice problems" refer to assignments or exercises related to the user's learning content. 【0012】 "Explanation" refers to information that provides explanations of how to derive the answers to practice problems and the relevant knowledge. 【0013】 "Learning history data" refers to data about a user's past learning activities and their results. 【0014】 "Dynamic adjustment" refers to the process of automatically changing the content of the learning plan in response to changes in the user's situation. [Brief explanation of the drawing] 【0015】 [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined. 【Embodiments for Carrying Out the Invention】 【0016】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0017】 First, the terms used in the following description will be explained. 【0018】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0019】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0020】 In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0021】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0022】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0023】 [First Embodiment] 【0024】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0025】 As shown in Figure 1, the 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. 【0026】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0027】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0028】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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. 【0029】 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0030】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0031】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0032】 As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30. 【0033】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0034】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0035】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0036】 The present invention is implemented as an online learning system accessed via a user's terminal. This system, centered around a server, is capable of comprehensively analyzing user learning data and generating individually optimized learning plans and practice problems. Specific embodiments are described below. 【0037】 When a user logs into the system via their device, the server retrieves new data from the user, previously collected learning history data, test results, and other information. The server then feeds this information into an analysis algorithm to perform a detailed analysis of the user's current learning status and academic level. 【0038】 The analysis results identify specific academic areas and areas of weakness, and the server uses this information to generate an optimal learning plan for the user. This learning plan is scheduled to match the user's lifestyle and study time, and includes a variety of learning materials (video materials, text materials, etc.). 【0039】 Furthermore, the server generates practice problems that focus on the user's weak subjects and areas. These practice problems are of appropriate difficulty and are designed to effectively check the user's learning. In the explanation section, the server provides detailed solutions and related knowledge to help deepen the user's understanding. 【0040】 As a concrete example, consider a middle school student who struggles with a specific area of ​​mathematics (e.g., functions). When this student accesses the system, the server automatically identifies their weak area based on their past grades and test results. The server then proposes a learning schedule tailored to the user and provides online lessons and practice problems on functions at a consistent pace each week. The problem explanations include visual aids such as diagrams and videos at key points to support the user's understanding. 【0041】 Thus, the present invention enables flexible learning support tailored to the user's individuality and learning situation, and makes it possible to provide advanced educational services at a low cost. 【0042】 The following describes the processing flow. 【0043】 Step 1: 【0044】 The user logs into the system using a terminal. The terminal sends the user's authentication information to the server. The server verifies the authentication information and allows access to the user's profile data. 【0045】 Step 2: 【0046】 The server receives user input and past learning history data. This includes the user's most recently completed test results and learning time. The server stores this data in a database and updates it to the latest state. 【0047】 Step 3: 【0048】 The server executes machine learning algorithms and analyzes the collected training data. The server identifies the user's learning patterns, weaknesses, and strengths, and evaluates the user's academic ability. 【0049】 Step 4: 【0050】 Based on these analyses, the server generates an optimal learning plan. This plan includes recommended learning materials, schedules, and study methods. The server then sends this information to the terminal. 【0051】 Step 5: 【0052】 The server generates practice problems that focus on the user's weak areas. The difficulty and format of the problems are customized to the user's skill level. The server also creates detailed explanations for each problem. 【0053】 Step 6: 【0054】 The user works through the learning plan and practice problems provided via the device. The device records the user's progress and sends feedback to the server. 【0055】 Step 7: 【0056】 The server analyzes user feedback and progress data, updating or adjusting the learning plan as needed. This information is then reflected in the next learning cycle. 【0057】 (Example 1) 【0058】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0059】 In today's educational environment, providing learning plans and materials tailored to individual learners is crucial for efficient learning. However, general learning systems often lack the flexibility to accommodate individual learning needs and progress, and frequently fail to provide adequate support, particularly for areas of weakness. As a result, learners often do not receive learning experiences that are suitable for improving their academic abilities. 【0060】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0061】 In this invention, the server includes means for acquiring information input by the user, means for analyzing learning data, means for generating an individualized learning plan, means for generating practice problems that focus on the user's weak areas, means for generating detailed explanations, means for performing data analysis and content generation using generational AI technology, and means for visualizing the analysis results. As a result, the user can receive a learning plan and learning materials optimized for their learning situation and needs, enabling them to efficiently improve their academic ability. 【0062】 "Means of obtaining user input" refers to methods of collecting personal information and data related to learning content that users provide to the system, via communication technology. 【0063】 "Means of analyzing learning data" refers to computational processing that analyzes a user's learning history, test results, etc., to evaluate their learning tendencies and level of understanding. 【0064】 "Means for generating personalized learning plans" refers to a method of creating a dedicated learning program tailored to each user's learning goals and progress, based on analyzed learning data. 【0065】 "A means of generating practice problems that focus on the user's weak areas" refers to the ability to identify areas where the user lacks understanding and automatically create problems specifically tailored to those areas. 【0066】 "Means for generating detailed explanations" refers to document creation techniques for clearly explaining the solutions and related knowledge for the generated practice problems. 【0067】 "Methods for performing data analysis and content generation using generative AI technology" refers to methods that utilize artificial intelligence technology to rapidly analyze large amounts of data and generate useful information. 【0068】 "Methods for visualizing analysis results" refer to techniques for displaying the results obtained from data analysis in visual formats such as diagrams and graphs. 【0069】 This invention is a system for providing user-optimized learning plans and individualized instruction in an online learning environment. It consists of a multi-functional program that supports learning activities by accessing a server through the user's terminal. 【0070】 When a user accesses the system from their device, the server retrieves the user's input information using a secure communication protocol. Specifically, the user's learning history and new information are collected and stored in a database. The server performs data analysis using Python or R, formats the data using the Pandas library, and generates statistical information using NumPy. This analysis makes it possible to evaluate the user's academic ability and learning tendencies. 【0071】 Based on the analyzed data, the server uses the SciKit-learn machine learning library to generate a personalized learning plan. This plan includes online learning materials tailored to the user's needs and is scheduled to allow the user to learn efficiently. It also designs a dynamically adjusting learning program using Python and generates practice problems using generative AI technology. The generated practice problems focus on the user's weak areas and provide interactive explanations using the Nomjs library. 【0072】 As a concrete example, if a middle school student struggles with the topic of functions in mathematics, the server analyzes past performance data and creates a personalized learning schedule and supplementary problems for that student. An example of a prompt in this case would be, "Generate practice problems including visual explanations on functions, which is a difficult topic for middle school students in mathematics." The generated content is delivered to the user's terminal and supports interactive, visual learning. 【0073】 This system aims to help improve academic performance by providing personalized education that is tailored to each user's different learning needs. 【0074】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0075】 Step 1: 【0076】 Users log in to the system via their terminal. During this process, authentication information and the user's most recent learning activity data are sent to the server as input. The server securely stores the received user information in a database using encryption technology. This allows the user's account to be identified and access to their past learning records. 【0077】 Step 2: 【0078】 The server retrieves user learning history data stored in the database and newly entered learning activity data. Using this as input, it converts it into a DataFrame using the Python Pandas library and performs data preprocessing. Specifically, this includes data cleaning and missing value imputation. The output of this process is an analyzable dataset. 【0079】 Step 3: 【0080】 The server analyzes the dataset obtained in the previous step. Here, NumPy is used to analyze the data using statistical methods. As a result, the user's academic level and learning tendencies are output. Based on these analysis results, the user's strengths and weaknesses are visualized. 【0081】 Step 4: 【0082】 The server uses SciKit-learn to build a machine learning model and generates a user-optimized learning plan based on the analysis results. The input consists of the user's current learning progress data and past learning history, which is used to predict learning patterns. The output is a user-specific learning schedule, including the format of learning materials and exercises. 【0083】 Step 5: 【0084】 The server uses a generative AI model to generate practice problems tailored to the user's weak areas. Past test results and progress are used as input, and the generated problems are adjusted to an optimal difficulty level. The output consists of practice problems and accompanying detailed explanations. 【0085】 Step 6: 【0086】 The server delivers practice problems and explanations to the terminal. When the user solves a problem, the result is sent back to the server as input. The server evaluates the result and updates the user's current level of understanding. Specifically, this includes visualizing the user's progress on an interactive dashboard. This result is used to dynamically adjust the next learning plan. 【0087】 (Application Example 1) 【0088】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0089】 In online learning systems, a challenge is providing a dynamically optimized learning experience tailored to each user's individual learning needs. In particular, the lack of functionality to adjust learning content in real time using the user's visual information is a problem that hinders user learning efficiency. 【0090】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0091】 In this invention, the server includes means for acquiring data input by the user, means for analyzing learning information, and means for generating individualized learning plans based on the analysis. This makes it possible to optimize learning content in real time based on the user's visual information. 【0092】 A "user" is an individual who uses the system to access educational content and practice problems. 【0093】 "Data" refers to information entered by the user and learning-related information used by the server for analysis. 【0094】 "Learning information" refers to data related to a user's learning history and current learning status. 【0095】 "Analysis" is the process by which a server analyzes a user's learning information and evaluates their academic ability and learning tendencies. 【0096】 An "educational plan" is a plan that provides a learning schedule and materials optimized for the user. 【0097】 "Practice problems" are assignments generated to deepen the user's understanding of the learning material. 【0098】 "Visual information" refers to data related to facial expressions and eye movements acquired by users using smart glasses or similar devices. 【0099】 "Dynamic optimization" means adaptively adjusting educational content based on the user's real-time learning progress. 【0100】 The system for implementing this invention aims to provide users with a personalized learning experience using smart glasses or other devices. A server acquires input data from the user and analyzes the learning information in detail. This analysis generates an individualized learning plan, and based on that plan, practice problems optimized for the user are created. 【0101】 The server monitors the user's learning progress in real time by detecting visual information. This includes facial expression and gaze data obtained from cameras built into smart glasses. This data is analyzed using image processing libraries such as OpenCV, along with Emotion Detection and Eye Tracking modules. This allows the server to measure the user's concentration and comprehension levels and dynamically optimize the learning content. 【0102】 As a concrete example, imagine a student wearing smart glasses during a math class. If the student's facial expression shows signs of confusion during the class, the server immediately detects this and adjusts the learning content accordingly, displaying corresponding support videos and diagrams on the HUD. This allows the user to receive real-time support for problem-solving. 【0103】 An example of a prompt message could be: "Instantly optimize the learning content based on the user's facial expressions and gaze information. For example, if the user shows a confused expression during learning, insert a short explanatory video." By inputting this prompt message into the AI ​​generation model, appropriate learning content will be suggested. 【0104】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0105】 Step 1: 【0106】 When a user logs into a device, the device sends the user's authentication information to the server. Based on this input, the server retrieves the user's learning history and past learning data from the database and outputs it as learning information. 【0107】 Step 2: 【0108】 The server executes an analysis algorithm based on the acquired learning information. It analyzes the input learning information in detail to evaluate the user's current academic level and learning tendencies. This analysis generates an individualized educational plan. As a result, it outputs an educational plan optimized for the user. 【0109】 Step 3: 【0110】 The terminal sends a request to the server to generate practice problems based on the educational plan. The server receives this request, selects appropriate practice problems based on the educational plan, and outputs that set of problems to the user's terminal. 【0111】 Step 4: 【0112】 When a user uses smart glasses to work on practice problems, the device detects visual information using the camera built into the smart glasses. It inputs gaze and facial expression data acquired from the camera and analyzes the user's concentration level and emotions in real time. This analysis result is then sent to a server. 【0113】 Step 5: 【0114】 The server receives the results of visual information analysis and uses a generative AI model to optimize the learning content. For example, if the user is confused, it automatically suggests supplementary explanatory videos or additional learning materials based on the prompt text. This modified learning content is then output to the user's device. 【0115】 Step 6: 【0116】 The device displays optimized learning content sent from the server on the HUD. This allows users to progress through the learning process while receiving visual aids to deepen their understanding of the material in real time. 【0117】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0118】 The present invention is implemented as an online learning system accessed through a user's terminal. This system is server-centric and incorporates an emotion engine that recognizes the user's emotions, enabling individually optimized learning support. A specific embodiment of this system is described below. 【0119】 When a user logs into the system using a device, the server collects the user's learning data and emotional information. Emotional information is acquired in real time through the device's camera, microphone, sensors, etc. The server inputs this emotional data into the emotional engine to determine the user's current emotional state. 【0120】 Based on the determined emotional state, the server further analyzes the user's learning data. In particular, it identifies the emotional patterns the user exhibits during learning and provides a corresponding learning plan. For example, if the server determines that the user is feeling frustrated while working on a difficult problem, it adjusts the learning plan, temporarily lowering the difficulty level or providing content that helps with relaxation. 【0121】 Furthermore, the server dynamically generates practice problems based on the user's emotions, and adjusts the explanations to match those emotions. By combining these emotion engines, it becomes possible to provide a learning experience that aligns with the user's emotional state. 【0122】 As a concrete example, imagine a high school student intensely studying a specific section of history before a test. If the system detects signs of frustration, the server will modify the study schedule and provide edutainment content to boost motivation. It will also add explanations for difficult sections to help the user calmly return to their studies. 【0123】 This invention aims to create an advanced learning environment that not only supports the user's academic performance but also takes into account emotional support. 【0124】 The following describes the processing flow. 【0125】 Step 1: 【0126】 The user logs into the system via their device. The device sends the user's authentication information to the server. The server verifies the authentication information and makes it possible to access the user's profile data. 【0127】 Step 2: 【0128】 The server retrieves user learning data and emotional information from the terminal. Emotional information is collected in real time via the camera and microphone. This includes facial recognition and voice tone analysis. 【0129】 Step 3: 【0130】 The server analyzes the acquired training data and emotional data. The emotional engine determines the user's current emotional state and evaluates factors such as stress levels and concentration. 【0131】 Step 4: 【0132】 The server adjusts the learning plan based on the user's emotional state. If the user's emotional state is negative, the server will either change the difficulty level of the learning material or suggest relaxation content. 【0133】 Step 5: 【0134】 The server generates practice problems based on the user's emotions and learning history. The difficulty and format of the problems are adjusted to match the user's emotional state. Furthermore, the explanations for the problems are customized to be easily understood by the user. 【0135】 Step 6: 【0136】 Users work on practice problems and study plans through their devices. The devices feed back the user's progress and new sentiment data to the server. 【0137】 Step 7: 【0138】 The server analyzes feedback and dynamically updates the learning plan as needed. Real-time adjustments are made to optimize the user's learning experience. 【0139】 (Example 2) 【0140】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0141】 Traditional online learning systems require personalized learning support to maximize user learning efficiency, but they lack systems that take into account users' emotional states, resulting in challenges in improving learning motivation and continuity. In particular, it has been difficult to adequately address frustration and decreased motivation that occur during learning. 【0142】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0143】 In this invention, the server includes means for collecting known bodily signals using a biometric information acquisition device, means for determining the emotional state based on an AI model that generates the collected bodily signals, and means for analyzing the learning data. This makes it possible to provide a learning experience that is individually optimized according to the user's emotional state. 【0144】 A "user" refers to an individual who uses the system to engage in online learning. 【0145】 "Means of acquiring information" refers to methods of collecting data entered by users and login information. 【0146】 A "biometric information acquisition device" refers to a device that collects a user's physical signals using cameras, microphones, sensors, etc. 【0147】 "Physiological signals" refer to physiological data related to determining an emotional state, such as the user's facial expressions, voice tone, and heart rate. 【0148】 A "generative AI model" refers to an artificial intelligence model that uses machine learning to analyze and predict emotional states. 【0149】 "Emotional state" refers to the state that indicates the user's psychological feelings and emotional tendencies. 【0150】 "Learning data" refers to information such as the user's learning history, grades, and progress. 【0151】 A "learning plan" refers to an individually optimized learning schedule and content created based on analyzed learning data. 【0152】 "Practice problems" refer to questions provided to assist users in their learning and to check their level of understanding. 【0153】 "Means of generating explanations" refers to methods of providing explanations and hints for practice problems to deepen the user's understanding. 【0154】 This invention is an online learning system that provides individually optimized learning support that takes into account the user's emotional state. This system is mainly server-based, and the user and terminal work together in cooperation. 【0155】 When a user logs into the online learning system via their device, the server first collects the user's learning data. This data includes past learning history and current progress. Simultaneously, the device utilizes its built-in camera, microphone, and various sensors to collect biometric information in real time. This allows the server to understand the user's facial expressions, voice tone, heart rate, and other characteristics. 【0156】 Next, the server uses a generative AI model to determine the user's emotional state based on the collected bodily signals. At this stage, the user's emotional tendencies, such as whether they are relaxed or feeling frustrated, are revealed. 【0157】 By integrating this emotional state data with training data, the server performs a comprehensive analysis and automatically generates an individually optimized learning plan. This includes selecting practice exercises that match the user's emotions and providing content to promote relaxation. 【0158】 For example, suppose a high school student is studying history and encounters a section they find difficult to understand, and the system detects their frustration. In this case, the server can provide new practice problems with adjusted difficulty levels and dynamically generate explanations to further aid understanding. It can also recommend video content incorporating edutainment elements to help boost their motivation to learn. 【0159】 An example of a prompt message might be: "The user is feeling frustrated. Generate easier practice exercises and provide relaxing content." 【0160】 In this way, the system can improve the quality and efficiency of learning by providing a flexible learning experience while taking user emotions into consideration. 【0161】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0162】 Step 1: 【0163】 The user logs into the online learning system. The user uses their device to enter their account information and begin accessing the system. At this stage, the server receives the input, performs an authentication process, and confirms successful login. The output is the user's learning dashboard. 【0164】 Step 2: 【0165】 Upon successful login, the server collects the user's learning history data and real-time biometric data. Cameras, microphones, and sensors on the device are used for data collection. Input consists of the user's past learning history and current biometric signals. This data is transformed, and integrated information is output. 【0166】 Step 3: 【0167】 The server uses integrated information to run a generative AI model that determines the user's current emotional state. The input here is biosignal data. This data is analyzed and outputted as the user's emotion, such as relaxed, tense, or frustrated. 【0168】 Step 4: 【0169】 After determining the user's emotional state, the server analyzes the user's training data and generates an optimized training plan. The input consists of the user's training history and emotional state. Based on this information, data calculations are performed, and an individual training plan is output. This plan includes training content tailored to the user's emotional state. 【0170】 Step 5: 【0171】 The server creates practice problems and their explanations based on the generated training plan. The input is the training plan. Based on this, a generative AI model is used to automatically generate and output the problem settings and explanation content. 【0172】 Step 6: 【0173】 The server suggests edutainment and relaxation content that matches the user's emotional state. Equal inputs are the emotional state and the user's learning progress. Based on this, the server provides output content that enhances the user's motivation. 【0174】 Step 7: 【0175】 Users progress through their learning based on the provided learning plans, practice problems, and content. They receive system output via their devices and engage in individually optimized learning. Finally, the user's learning progress is fed back as input, and the system continues to operate. 【0176】 (Application Example 2) 【0177】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0178】 Modern online learning systems demand personalized learning experiences. However, traditional systems lack learning adjustments and content recommendations based on user emotional states, making it difficult to maximize user learning efficiency. Therefore, a system is needed that dynamically adjusts learning plans according to user emotions and recommends entertainment content in conjunction with these adjustments. 【0179】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0180】 In this invention, the server includes means for acquiring user input information, means for analyzing learning information, means for generating individualized learning plans based on the analysis, and means for recognizing the user's emotional state and dynamically recommending content based on that emotional state. This makes it possible to maximize the user's learning efficiency while providing an optimal learning experience and content tailored to their emotions. 【0181】 "User input information" refers to all information provided by users in an online learning system, such as text data and selected data. 【0182】 "Learning information" refers to data related to educational materials and learning content provided for educational purposes. 【0183】 An "educational plan" refers to an educational and learning schedule and curriculum that is individually set to help users achieve their learning goals. 【0184】 "Practice exercises" refer to problems and exercises provided to test the knowledge and skills that users have acquired. 【0185】 "Explanation" refers to text or data that provides answers or explanations related to the practice exercises. 【0186】 "Emotional state" refers to the emotional reactions or psychological conditions a user exhibits at a particular point in time. 【0187】 "Dynamic content recommendation" refers to a system that selects and presents appropriate entertainment and educational content in real time based on the user's current emotional state. 【0188】 The system for realizing this invention includes a mechanism in which the user's terminal is equipped with a camera, microphone, and various sensors, and acquires user input information and emotional state through these. The server receives the data transmitted from these terminals and executes a program to analyze the learned information. Specifically, it estimates the emotional state from the user's facial expressions and voice using an image processing library such as OpenCV and software components specialized for emotion recognition. 【0189】 The server dynamically generates educational plans and practice tasks based on the user's emotional state. This generation utilizes a generative AI model, adjusting explanations and tasks as needed, taking into account the user's learning history and current progress. Furthermore, it enriches the learning experience by selecting and recommending optimal entertainment content based on the user's emotional state. 【0190】 This system, for example, detects when a user feels stressed while tackling a difficult task, and temporarily adjusts the learning plan. It also recommends relaxing music or videos to alleviate the stress. A specific example of a prompt might be, "The user is feeling relaxed. Please provide a list of movies or music that best suit this feeling," and the server will select appropriate content based on this. 【0191】 In this way, the primary objective of this system is to improve user learning efficiency and satisfaction. 【0192】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0193】 Step 1: 【0194】 The device uses a camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server as input data to evaluate the user's emotional state. 【0195】 Step 2: 【0196】 The server analyzes image data received from the terminal using OpenCV and estimates the user's emotions from their facial expressions. In this process, facial expression patterns exhibiting specific psychological characteristics are compared with a database, and the emotional state is output. 【0197】 Step 3: 【0198】 The server uses emotion recognition software to analyze voice data, associating emotions with the user's speech and intonation. It extracts features from the voice data and determines the emotional nuances expressed in the speech. This result is also output as an emotional state and integrated with the results of facial expression analysis. 【0199】 Step 4: 【0200】 Based on the user's emotional state, the server re-evaluates the user's learning information and adjusts the educational plan. Using a generative AI model, it generates individually optimized educational procedures that take into account the user's learning history and current progress, and outputs them as an educational plan. 【0201】 Step 5: 【0202】 The server dynamically selects entertainment content based on prompts using an AI model that considers the user's emotional state. It determines the most suitable content based on emotional data and outputs a list of content to present to the user. For example, a prompt might be: "The user wants to relax. Please provide a list of movies and music that best suit this emotion." 【0203】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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. 【0204】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0205】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0206】 [Second Embodiment] 【0207】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0208】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0209】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0210】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0211】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0212】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0213】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0214】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0215】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0216】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0217】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0218】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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". 【0219】 The present invention is implemented as an online learning system accessed via a user's terminal. This system, centered around a server, is capable of comprehensively analyzing user learning data and generating individually optimized learning plans and practice problems. Specific embodiments are described below. 【0220】 When a user logs into the system via their device, the server retrieves new data from the user, previously collected learning history data, test results, and other information. The server then feeds this information into an analysis algorithm to perform a detailed analysis of the user's current learning status and academic level. 【0221】 The analysis results identify specific academic areas and areas of weakness, and the server uses this information to generate an optimal learning plan for the user. This learning plan is scheduled to match the user's lifestyle and study time, and includes a variety of learning materials (video materials, text materials, etc.). 【0222】 Furthermore, the server generates practice problems that focus on the user's weak subjects and areas. These practice problems are of appropriate difficulty and are designed to effectively check the user's learning. In the explanation section, the server provides detailed solutions and related knowledge to help deepen the user's understanding. 【0223】 As a concrete example, consider a middle school student who struggles with a specific area of ​​mathematics (e.g., functions). When this student accesses the system, the server automatically identifies their weak area based on their past grades and test results. The server then proposes a learning schedule tailored to the user and provides online lessons and practice problems on functions at a consistent pace each week. The problem explanations include visual aids such as diagrams and videos at key points to support the user's understanding. 【0224】 Thus, the present invention enables flexible learning support tailored to the user's individuality and learning situation, and makes it possible to provide advanced educational services at a low cost. 【0225】 The following describes the processing flow. 【0226】 Step 1: 【0227】 The user logs into the system using a terminal. The terminal sends the user's authentication information to the server. The server verifies the authentication information and allows access to the user's profile data. 【0228】 Step 2: 【0229】 The server receives user input and past learning history data. This includes the user's most recently completed test results and learning time. The server stores this data in a database and updates it to the latest state. 【0230】 Step 3: 【0231】 The server executes machine learning algorithms and analyzes the collected training data. The server identifies the user's learning patterns, weaknesses, and strengths, and evaluates the user's academic ability. 【0232】 Step 4: 【0233】 Based on these analyses, the server generates an optimal learning plan. This plan includes recommended learning materials, schedules, and study methods. The server then sends this information to the terminal. 【0234】 Step 5: 【0235】 The server generates practice problems that focus on the user's weak areas. The difficulty and format of the problems are customized to the user's skill level. The server also creates detailed explanations for each problem. 【0236】 Step 6: 【0237】 The user works through the learning plan and practice problems provided via the device. The device records the user's progress and sends feedback to the server. 【0238】 Step 7: 【0239】 The server analyzes user feedback and progress data, updating or adjusting the learning plan as needed. This information is then reflected in the next learning cycle. 【0240】 (Example 1) 【0241】 Next, we will describe Example 1. 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." 【0242】 In today's educational environment, providing learning plans and materials tailored to individual learners is crucial for efficient learning. However, general learning systems often lack the flexibility to accommodate individual learning needs and progress, and frequently fail to provide adequate support, particularly for areas of weakness. As a result, learners often do not receive learning experiences that are suitable for improving their academic abilities. 【0243】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0244】 In this invention, the server includes means for acquiring information input by the user, means for analyzing learning data, means for generating an individualized learning plan, means for generating practice problems that focus on the user's weak areas, means for generating detailed explanations, means for performing data analysis and content generation using generational AI technology, and means for visualizing the analysis results. As a result, the user can receive a learning plan and learning materials optimized for their learning situation and needs, enabling them to efficiently improve their academic ability. 【0245】 "Means of obtaining user input" refers to methods of collecting personal information and data related to learning content that users provide to the system, via communication technology. 【0246】 "Means of analyzing learning data" refers to computational processing that analyzes a user's learning history, test results, etc., to evaluate their learning tendencies and level of understanding. 【0247】 "Means for generating personalized learning plans" refers to a method of creating a dedicated learning program tailored to each user's learning goals and progress, based on analyzed learning data. 【0248】 "A means of generating practice problems that focus on the user's weak areas" refers to the ability to identify areas where the user lacks understanding and automatically create problems specifically tailored to those areas. 【0249】 "Means for generating detailed explanations" refers to document creation techniques for clearly explaining the solutions and related knowledge for the generated practice problems. 【0250】 "Methods for performing data analysis and content generation using generative AI technology" refers to methods that utilize artificial intelligence technology to rapidly analyze large amounts of data and generate useful information. 【0251】 "Methods for visualizing analysis results" refer to techniques for displaying the results obtained from data analysis in visual formats such as diagrams and graphs. 【0252】 This invention is a system for providing user-optimized learning plans and individualized instruction in an online learning environment. It consists of a multi-functional program that supports learning activities by accessing a server through the user's terminal. 【0253】 When a user accesses the system from their device, the server retrieves the user's input information using a secure communication protocol. Specifically, the user's learning history and new information are collected and stored in a database. The server performs data analysis using Python or R, formats the data using the Pandas library, and generates statistical information using NumPy. This analysis makes it possible to evaluate the user's academic ability and learning tendencies. 【0254】 Based on the analyzed data, the server uses the SciKit-learn machine learning library to generate a personalized learning plan. This plan includes online learning materials tailored to the user's needs and is scheduled to allow the user to learn efficiently. It also designs a dynamically adjusting learning program using Python and generates practice problems using generative AI technology. The generated practice problems focus on the user's weak areas and provide interactive explanations using the Nomjs library. 【0255】 As a concrete example, if a middle school student struggles with the topic of functions in mathematics, the server analyzes past performance data and creates a personalized learning schedule and supplementary problems for that student. An example of a prompt in this case would be, "Generate practice problems including visual explanations on functions, which is a difficult topic for middle school students in mathematics." The generated content is delivered to the user's terminal and supports interactive, visual learning. 【0256】 This system aims to help improve academic performance by providing personalized education that is tailored to each user's different learning needs. 【0257】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0258】 Step 1: 【0259】 Users log in to the system via their terminal. During this process, authentication information and the user's most recent learning activity data are sent to the server as input. The server securely stores the received user information in a database using encryption technology. This allows the user's account to be identified and access to their past learning records. 【0260】 Step 2: 【0261】 The server retrieves user learning history data stored in the database and newly entered learning activity data. Using this as input, it converts it into a DataFrame using the Python Pandas library and performs data preprocessing. Specifically, this includes data cleaning and missing value imputation. The output of this process is an analyzable dataset. 【0262】 Step 3: 【0263】 The server analyzes the dataset obtained in the previous step. Here, NumPy is used to analyze the data using statistical methods. As a result, the user's academic level and learning tendencies are output. Based on these analysis results, the user's strengths and weaknesses are visualized. 【0264】 Step 4: 【0265】 The server uses SciKit-learn to build a machine learning model and generates a user-optimized learning plan based on the analysis results. The input consists of the user's current learning progress data and past learning history, which is used to predict learning patterns. The output is a user-specific learning schedule, including the format of learning materials and exercises. 【0266】 Step 5: 【0267】 The server uses a generative AI model to generate practice problems tailored to the user's weak areas. Past test results and progress are used as input, and the generated problems are adjusted to an optimal difficulty level. The output consists of practice problems and accompanying detailed explanations. 【0268】 Step 6: 【0269】 The server delivers practice problems and explanations to the terminal. When the user solves a problem, the result is sent back to the server as input. The server evaluates the result and updates the user's current level of understanding. Specifically, this includes visualizing the user's progress on an interactive dashboard. This result is used to dynamically adjust the next learning plan. 【0270】 (Application Example 1) 【0271】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0272】 In online learning systems, a challenge is providing a dynamically optimized learning experience tailored to each user's individual learning needs. In particular, the lack of functionality to adjust learning content in real time using the user's visual information is a problem that hinders user learning efficiency. 【0273】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0274】 In this invention, the server includes means for acquiring data input by the user, means for analyzing learning information, and means for generating individualized learning plans based on the analysis. This makes it possible to optimize learning content in real time based on the user's visual information. 【0275】 A "user" is an individual who uses the system to access educational content and practice problems. 【0276】 "Data" refers to information entered by the user and learning-related information used by the server for analysis. 【0277】 "Learning information" refers to data related to a user's learning history and current learning status. 【0278】 "Analysis" refers to the process in which the server analyzes the user's learning information and evaluates academic ability and learning tendencies. 【0279】 "Educational plan" refers to a learning schedule and teaching material provision plan optimized for the user. 【0280】 "Practice problems" refer to tasks generated to deepen the user's understanding of the learning content. 【0281】 "Visual information" refers to data related to expressions and eye movements that the user obtains using smart glasses or other terminals. 【0282】 "Dynamically optimize" means adaptively adjusting the educational content based on the user's real-time learning situation. 【0283】 The system for implementing this invention aims to enable the user to obtain an individually optimized learning experience by using smart glasses or other terminals. The server acquires input data from the user and analyzes the learning information in detail. Based on this analysis, an individual educational plan is generated, and optimal practice problems for the user are created according to the educational plan. 【0284】 The server monitors the user's learning situation in real time by detecting visual information. This includes facial expression and eye movement data obtained by the camera built into the smart glasses. These data are analyzed using image processing libraries such as OpenCV and emotion detection and eye tracking modules. This measures the user's concentration and understanding, and dynamically optimizes the learning content. 【0285】 As a specific example, assume a student wears smart glasses and takes a math class. If confusion is seen in the expression during the class, the server immediately detects the situation, adjusts the learning content, and displays corresponding understanding support videos and illustrations on the HUD. This enables the user to receive real-time problem-solving support. 【0286】 As an example of a prompt sentence, a format such as "Please instantly optimize the learning content based on the user's expression and gaze information. For example, if the user shows a confused expression during learning, insert a simple explanatory video." can be considered. By inputting this prompt sentence into the generation AI model, appropriate learning content proposals are made. 【0287】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0288】 Step 1: 【0289】 When the user logs in to the terminal, the terminal sends the user's authentication information to the server. Based on this input, the server retrieves the user's learning history and past learning data from the database and outputs it as learning information. 【0290】 Step 2: 【0291】 The server executes an analysis algorithm based on the acquired learning information. It analyzes the input learning information in detail and evaluates the user's current academic level and learning tendency. Through this analysis, an individual education plan is generated. As a result, an education plan optimized for the user is output. 【0292】 Step 3: 【0293】 The terminal sends a request to the server to generate practice questions based on the education plan. The server receives this request, selects appropriate practice questions based on the education plan, and outputs the question set to the user's terminal. 【0294】 Step 4: 【0295】 When the user uses smart glasses to work on practice questions, the terminal uses the camera built into the smart glasses to detect visual information. It inputs the gaze and expression data obtained from the camera and analyzes the user's concentration and emotions in real time. This analysis result is sent to the server. 【0296】 Step 5: 【0297】 The server receives the results of visual information analysis and uses a generative AI model to optimize the learning content. For example, if the user is confused, it automatically suggests supplementary explanatory videos or additional learning materials based on the prompt text. This modified learning content is then output to the user's device. 【0298】 Step 6: 【0299】 The device displays optimized learning content sent from the server on the HUD. This allows users to progress through the learning process while receiving visual aids to deepen their understanding of the material in real time. 【0300】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0301】 The present invention is implemented as an online learning system accessed through a user's terminal. This system is server-centric and incorporates an emotion engine that recognizes the user's emotions, enabling individually optimized learning support. A specific embodiment of this system is described below. 【0302】 When a user logs into the system using a device, the server collects the user's learning data and emotional information. Emotional information is acquired in real time through the device's camera, microphone, sensors, etc. The server inputs this emotional data into the emotional engine to determine the user's current emotional state. 【0303】 Based on the determined emotional state, the server further analyzes the user's learning data. In particular, it grasps the emotional patterns shown by the user during learning and provides a corresponding learning plan. For example, if it is determined that the user is feeling frustrated when dealing with difficult problems, the server adjusts the learning plan, temporarily lowers the difficulty level, or provides content helpful for relaxation. 【0304】 Furthermore, the server dynamically generates practice questions based on the user's emotions and also adjusts the explanations for them to content suitable for the emotions. In this way, by combining the emotion engine, it becomes possible to provide a learning experience in line with the user's emotional state. 【0305】 As a specific example, suppose a high school student is concentrating on studying a specific range before a history test. If the system senses signs of frustration, the server changes the learning schedule and provides edutainment content to boost motivation. Also, it adds explanations for difficult sections to support the user to calmly return to learning. 【0306】 Thereby, the present invention supports the improvement of the user's academic ability and realizes an advanced learning environment that also takes into account emotional support. 【0307】 The following describes the processing flow. 【0308】 Step 1: 【0309】 The user logs in to the system through the terminal. The terminal sends the user's authentication information to the server. The server verifies the authentication information and makes it possible to access the user's profile data. 【0310】 Step 2: 【0311】 The server retrieves user learning data and emotional information from the terminal. Emotional information is collected in real time via the camera and microphone. This includes facial recognition and voice tone analysis. 【0312】 Step 3: 【0313】 The server analyzes the acquired training data and emotional data. The emotional engine determines the user's current emotional state and evaluates factors such as stress levels and concentration. 【0314】 Step 4: 【0315】 The server adjusts the learning plan based on the user's emotional state. If the user's emotional state is negative, the server will either change the difficulty level of the learning material or suggest relaxation content. 【0316】 Step 5: 【0317】 The server generates practice problems based on the user's emotions and learning history. The difficulty and format of the problems are adjusted to match the user's emotional state. Furthermore, the explanations for the problems are customized to be easily understood by the user. 【0318】 Step 6: 【0319】 Users work on practice problems and study plans through their devices. The devices feed back the user's progress and new sentiment data to the server. 【0320】 Step 7: 【0321】 The server analyzes feedback and dynamically updates the learning plan as needed. Real-time adjustments are made to optimize the user's learning experience. 【0322】 (Example 2) 【0323】 Next, we will describe Example 2. 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". 【0324】 Traditional online learning systems require personalized learning support to maximize user learning efficiency, but they lack systems that take into account users' emotional states, resulting in challenges in improving learning motivation and continuity. In particular, it has been difficult to adequately address frustration and decreased motivation that occur during learning. 【0325】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0326】 In this invention, the server includes means for collecting known bodily signals using a biometric information acquisition device, means for determining the emotional state based on an AI model that generates the collected bodily signals, and means for analyzing the learning data. This makes it possible to provide a learning experience that is individually optimized according to the user's emotional state. 【0327】 A "user" refers to an individual who uses the system to engage in online learning. 【0328】 "Means of acquiring information" refers to methods of collecting data entered by users and login information. 【0329】 A "biometric information acquisition device" refers to a device that collects a user's physical signals using cameras, microphones, sensors, etc. 【0330】 "Physiological signals" refer to physiological data related to determining an emotional state, such as the user's facial expressions, voice tone, and heart rate. 【0331】 A "generative AI model" refers to an artificial intelligence model that uses machine learning to analyze and predict emotional states. 【0332】 "Emotional state" refers to the state that indicates the user's psychological feelings and emotional tendencies. 【0333】 "Learning data" refers to information such as the user's learning history, grades, and progress. 【0334】 A "learning plan" refers to an individually optimized learning schedule and content created based on analyzed learning data. 【0335】 "Practice problems" refer to questions provided to assist users in their learning and to check their level of understanding. 【0336】 "Means of generating explanations" refers to methods of providing explanations and hints for practice problems to deepen the user's understanding. 【0337】 This invention is an online learning system that provides individually optimized learning support that takes into account the user's emotional state. This system is mainly server-based, and the user and terminal work together in cooperation. 【0338】 When a user logs into the online learning system via their device, the server first collects the user's learning data. This data includes past learning history and current progress. Simultaneously, the device utilizes its built-in camera, microphone, and various sensors to collect biometric information in real time. This allows the server to understand the user's facial expressions, voice tone, heart rate, and other characteristics. 【0339】 Next, the server uses a generative AI model to determine the user's emotional state based on the collected bodily signals. At this stage, the user's emotional tendencies, such as whether they are relaxed or feeling frustrated, are revealed. 【0340】 By integrating this emotional state data with training data, the server performs a comprehensive analysis and automatically generates an individually optimized learning plan. This includes selecting practice exercises that match the user's emotions and providing content to promote relaxation. 【0341】 For example, suppose a high school student is studying history and encounters a section they find difficult to understand, and the system detects their frustration. In this case, the server can provide new practice problems with adjusted difficulty levels and dynamically generate explanations to further aid understanding. It can also recommend video content incorporating edutainment elements to help boost their motivation to learn. 【0342】 An example of a prompt message might be: "The user is feeling frustrated. Generate easier practice exercises and provide relaxing content." 【0343】 In this way, the system can improve the quality and efficiency of learning by providing a flexible learning experience while taking user emotions into consideration. 【0344】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0345】 Step 1: 【0346】 The user logs into the online learning system. The user uses their device to enter their account information and begin accessing the system. At this stage, the server receives the input, performs an authentication process, and confirms successful login. The output is the user's learning dashboard. 【0347】 Step 2: 【0348】 Upon successful login, the server collects the user's learning history data and real-time biometric data. Cameras, microphones, and sensors on the device are used for data collection. Input consists of the user's past learning history and current biometric signals. This data is transformed, and integrated information is output. 【0349】 Step 3: 【0350】 The server uses integrated information to run a generative AI model that determines the user's current emotional state. The input here is biosignal data. This data is analyzed and outputted as the user's emotion, such as relaxed, tense, or frustrated. 【0351】 Step 4: 【0352】 After determining the user's emotional state, the server analyzes the user's training data and generates an optimized training plan. The input consists of the user's training history and emotional state. Based on this information, data calculations are performed, and an individual training plan is output. This plan includes training content tailored to the user's emotional state. 【0353】 Step 5: 【0354】 The server creates practice problems and their explanations based on the generated training plan. The input is the training plan. Based on this, a generative AI model is used to automatically generate and output the problem settings and explanation content. 【0355】 Step 6: 【0356】 The server suggests edutainment and relaxation content that matches the user's emotional state. Equal inputs are the emotional state and the user's learning progress. Based on this, the server provides output content that enhances the user's motivation. 【0357】 Step 7: 【0358】 Users progress through their learning based on the provided learning plans, practice problems, and content. They receive system output via their devices and engage in individually optimized learning. Finally, the user's learning progress is fed back as input, and the system continues to operate. 【0359】 (Application Example 2) 【0360】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0361】 Modern online learning systems demand personalized learning experiences. However, traditional systems lack learning adjustments and content recommendations based on user emotional states, making it difficult to maximize user learning efficiency. Therefore, a system is needed that dynamically adjusts learning plans according to user emotions and recommends entertainment content in conjunction with these adjustments. 【0362】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0363】 In this invention, the server includes means for acquiring user input information, means for analyzing learning information, means for generating individualized learning plans based on the analysis, and means for recognizing the user's emotional state and dynamically recommending content based on that emotional state. This makes it possible to maximize the user's learning efficiency while providing an optimal learning experience and content tailored to their emotions. 【0364】 "User input information" refers to all information provided by users in an online learning system, such as text data and selected data. 【0365】 "Learning information" refers to data related to educational materials and learning content provided for educational purposes. 【0366】 An "educational plan" refers to an educational and learning schedule and curriculum that is individually set to help users achieve their learning goals. 【0367】 "Practice exercises" refer to problems and exercises provided to test the knowledge and skills that users have acquired. 【0368】 "Explanation" refers to text or data that provides answers or explanations related to the practice exercises. 【0369】 "Emotional state" refers to the emotional reactions or psychological conditions a user exhibits at a particular point in time. 【0370】 "Dynamic content recommendation" refers to a system that selects and presents appropriate entertainment and educational content in real time based on the user's current emotional state. 【0371】 The system for realizing this invention includes a mechanism in which the user's terminal is equipped with a camera, microphone, and various sensors, and acquires user input information and emotional state through these. The server receives the data transmitted from these terminals and executes a program to analyze the learned information. Specifically, it estimates the emotional state from the user's facial expressions and voice using an image processing library such as OpenCV and software components specialized for emotion recognition. 【0372】 The server dynamically generates educational plans and practice tasks based on the user's emotional state. This generation utilizes a generative AI model, adjusting explanations and tasks as needed, taking into account the user's learning history and current progress. Furthermore, it enriches the learning experience by selecting and recommending optimal entertainment content based on the user's emotional state. 【0373】 This system, for example, detects when a user feels stressed while tackling a difficult task, and temporarily adjusts the learning plan. It also recommends relaxing music or videos to alleviate the stress. A specific example of a prompt might be, "The user is feeling relaxed. Please provide a list of movies or music that best suit this feeling," and the server will select appropriate content based on this. 【0374】 In this way, the primary objective of this system is to improve user learning efficiency and satisfaction. 【0375】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0376】 Step 1: 【0377】 The device uses a camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server as input data to evaluate the user's emotional state. 【0378】 Step 2: 【0379】 The server analyzes image data received from the terminal using OpenCV and estimates the user's emotions from their facial expressions. In this process, facial expression patterns exhibiting specific psychological characteristics are compared with a database, and the emotional state is output. 【0380】 Step 3: 【0381】 The server uses emotion recognition software to analyze voice data, associating emotions with the user's speech and intonation. It extracts features from the voice data and determines the emotional nuances expressed in the speech. This result is also output as an emotional state and integrated with the results of facial expression analysis. 【0382】 Step 4: 【0383】 Based on the user's emotional state, the server re-evaluates the user's learning information and adjusts the educational plan. Using a generative AI model, it generates individually optimized educational procedures that take into account the user's learning history and current progress, and outputs them as an educational plan. 【0384】 Step 5: 【0385】 The server dynamically selects entertainment content based on prompts using an AI model that considers the user's emotional state. It determines the most suitable content based on emotional data and outputs a list of content to present to the user. For example, a prompt might be: "The user wants to relax. Please provide a list of movies and music that best suit this emotion." 【0386】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0387】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0388】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0389】 [Third Embodiment] 【0390】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0391】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0392】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0393】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0394】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0395】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0396】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0397】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0398】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0399】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0400】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0401】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0402】 The present invention is implemented as an online learning system accessed via a user's terminal. This system, centered around a server, is capable of comprehensively analyzing user learning data and generating individually optimized learning plans and practice problems. Specific embodiments are described below. 【0403】 When a user logs into the system via their device, the server retrieves new data from the user, previously collected learning history data, test results, and other information. The server then feeds this information into an analysis algorithm to perform a detailed analysis of the user's current learning status and academic level. 【0404】 The analysis results identify specific academic areas and areas of weakness, and the server uses this information to generate an optimal learning plan for the user. This learning plan is scheduled to match the user's lifestyle and study time, and includes a variety of learning materials (video materials, text materials, etc.). 【0405】 Furthermore, the server generates practice problems that focus on the user's weak subjects and areas. These practice problems are of appropriate difficulty and are designed to effectively check the user's learning. In the explanation section, the server provides detailed solutions and related knowledge to help deepen the user's understanding. 【0406】 As a concrete example, consider a middle school student who struggles with a specific area of ​​mathematics (e.g., functions). When this student accesses the system, the server automatically identifies their weak area based on their past grades and test results. The server then proposes a learning schedule tailored to the user and provides online lessons and practice problems on functions at a consistent pace each week. The problem explanations include visual aids such as diagrams and videos at key points to support the user's understanding. 【0407】 Thus, the present invention enables flexible learning support tailored to the user's individuality and learning situation, and makes it possible to provide advanced educational services at a low cost. 【0408】 The following describes the processing flow. 【0409】 Step 1: 【0410】 The user logs into the system using a terminal. The terminal sends the user's authentication information to the server. The server verifies the authentication information and allows access to the user's profile data. 【0411】 Step 2: 【0412】 The server receives user input and past learning history data. This includes the user's most recently completed test results and learning time. The server stores this data in a database and updates it to the latest state. 【0413】 Step 3: 【0414】 The server executes machine learning algorithms and analyzes the collected training data. The server identifies the user's learning patterns, weaknesses, and strengths, and evaluates the user's academic ability. 【0415】 Step 4: 【0416】 Based on these analyses, the server generates an optimal learning plan. This plan includes recommended learning materials, schedules, and study methods. The server then sends this information to the terminal. 【0417】 Step 5: 【0418】 The server generates practice problems that focus on the user's weak areas. The difficulty and format of the problems are customized to the user's skill level. The server also creates detailed explanations for each problem. 【0419】 Step 6: 【0420】 The user works through the learning plan and practice problems provided via the device. The device records the user's progress and sends feedback to the server. 【0421】 Step 7: 【0422】 The server analyzes user feedback and progress data, updating or adjusting the learning plan as needed. This information is then reflected in the next learning cycle. 【0423】 (Example 1) 【0424】 Next, we will describe Example 1. 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." 【0425】 In today's educational environment, providing learning plans and materials tailored to individual learners is crucial for efficient learning. However, general learning systems often lack the flexibility to accommodate individual learning needs and progress, and frequently fail to provide adequate support, particularly for areas of weakness. As a result, learners often do not receive learning experiences that are suitable for improving their academic abilities. 【0426】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0427】 In this invention, the server includes means for acquiring information input by the user, means for analyzing learning data, means for generating an individualized learning plan, means for generating practice problems that focus on the user's weak areas, means for generating detailed explanations, means for performing data analysis and content generation using generational AI technology, and means for visualizing the analysis results. As a result, the user can receive a learning plan and learning materials optimized for their learning situation and needs, enabling them to efficiently improve their academic ability. 【0428】 "Means of obtaining user input" refers to methods of collecting personal information and data related to learning content that users provide to the system, via communication technology. 【0429】 "Means of analyzing learning data" refers to computational processing that analyzes a user's learning history, test results, etc., to evaluate their learning tendencies and level of understanding. 【0430】 "Means for generating personalized learning plans" refers to a method of creating a dedicated learning program tailored to each user's learning goals and progress, based on analyzed learning data. 【0431】 "A means of generating practice problems that focus on the user's weak areas" refers to the ability to identify areas where the user lacks understanding and automatically create problems specifically tailored to those areas. 【0432】 "Means for generating detailed explanations" refers to document creation techniques for clearly explaining the solutions and related knowledge for the generated practice problems. 【0433】 "Methods for performing data analysis and content generation using generative AI technology" refers to methods that utilize artificial intelligence technology to rapidly analyze large amounts of data and generate useful information. 【0434】 "Methods for visualizing analysis results" refer to techniques for displaying the results obtained from data analysis in visual formats such as diagrams and graphs. 【0435】 This invention is a system for providing user-optimized learning plans and individualized instruction in an online learning environment. It consists of a multi-functional program that supports learning activities by accessing a server through the user's terminal. 【0436】 When a user accesses the system from their device, the server retrieves the user's input information using a secure communication protocol. Specifically, the user's learning history and new information are collected and stored in a database. The server performs data analysis using Python or R, formats the data using the Pandas library, and generates statistical information using NumPy. This analysis makes it possible to evaluate the user's academic ability and learning tendencies. 【0437】 Based on the analyzed data, the server uses the SciKit-learn machine learning library to generate a personalized learning plan. This plan includes online learning materials tailored to the user's needs and is scheduled to allow the user to learn efficiently. It also designs a dynamically adjusting learning program using Python and generates practice problems using generative AI technology. The generated practice problems focus on the user's weak areas and provide interactive explanations using the Nomjs library. 【0438】 As a concrete example, if a middle school student struggles with the topic of functions in mathematics, the server analyzes past performance data and creates a personalized learning schedule and supplementary problems for that student. An example of a prompt in this case would be, "Generate practice problems including visual explanations on functions, which is a difficult topic for middle school students in mathematics." The generated content is delivered to the user's terminal and supports interactive, visual learning. 【0439】 This system aims to help improve academic performance by providing personalized education that is tailored to each user's different learning needs. 【0440】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0441】 Step 1: 【0442】 Users log in to the system via their terminal. During this process, authentication information and the user's most recent learning activity data are sent to the server as input. The server securely stores the received user information in a database using encryption technology. This allows the user's account to be identified and access to their past learning records. 【0443】 Step 2: 【0444】 The server retrieves user learning history data stored in the database and newly entered learning activity data. Using this as input, it converts it into a DataFrame using the Python Pandas library and performs data preprocessing. Specifically, this includes data cleaning and missing value imputation. The output of this process is an analyzable dataset. 【0445】 Step 3: 【0446】 The server analyzes the dataset obtained in the previous step. Here, NumPy is used to analyze the data using statistical methods. As a result, the user's academic level and learning tendencies are output. Based on these analysis results, the user's strengths and weaknesses are visualized. 【0447】 Step 4: 【0448】 The server uses SciKit-learn to build a machine learning model and generates a user-optimized learning plan based on the analysis results. The input consists of the user's current learning progress data and past learning history, which is used to predict learning patterns. The output is a user-specific learning schedule, including the format of learning materials and exercises. 【0449】 Step 5: 【0450】 The server uses a generative AI model to generate practice problems tailored to the user's weak areas. Past test results and progress are used as input, and the generated problems are adjusted to an optimal difficulty level. The output consists of practice problems and accompanying detailed explanations. 【0451】 Step 6: 【0452】 The server delivers practice problems and explanations to the terminal. When the user solves a problem, the result is sent back to the server as input. The server evaluates the result and updates the user's current level of understanding. Specifically, this includes visualizing the user's progress on an interactive dashboard. This result is used to dynamically adjust the next learning plan. 【0453】 (Application Example 1) 【0454】 Next, we will explain Application Example 1. In the following explanation, 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." 【0455】 In online learning systems, a challenge is providing a dynamically optimized learning experience tailored to each user's individual learning needs. In particular, the lack of functionality to adjust learning content in real time using the user's visual information is a problem that hinders user learning efficiency. 【0456】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0457】 In this invention, the server includes means for acquiring data input by the user, means for analyzing learning information, and means for generating individualized learning plans based on the analysis. This makes it possible to optimize learning content in real time based on the user's visual information. 【0458】 A "user" is an individual who uses the system to access educational content and practice problems. 【0459】 "Data" refers to information entered by the user and learning-related information used by the server for analysis. 【0460】 "Learning information" refers to data related to a user's learning history and current learning status. 【0461】 "Analysis" is the process by which a server analyzes a user's learning information and evaluates their academic ability and learning tendencies. 【0462】 An "educational plan" is a plan that provides a learning schedule and materials optimized for the user. 【0463】 "Practice problems" are assignments generated to deepen the user's understanding of the learning material. 【0464】 "Visual information" refers to data related to facial expressions and eye movements acquired by users using smart glasses or similar devices. 【0465】 "Dynamic optimization" means adaptively adjusting educational content based on the user's real-time learning progress. 【0466】 The system for implementing this invention aims to provide users with a personalized learning experience using smart glasses or other devices. A server acquires input data from the user and analyzes the learning information in detail. This analysis generates an individualized learning plan, and based on that plan, practice problems optimized for the user are created. 【0467】 The server monitors the user's learning progress in real time by detecting visual information. This includes facial expression and gaze data obtained from cameras built into smart glasses. This data is analyzed using image processing libraries such as OpenCV, along with Emotion Detection and Eye Tracking modules. This allows the server to measure the user's concentration and comprehension levels and dynamically optimize the learning content. 【0468】 As a concrete example, imagine a student wearing smart glasses during a math class. If the student's facial expression shows signs of confusion during the class, the server immediately detects this and adjusts the learning content accordingly, displaying corresponding support videos and diagrams on the HUD. This allows the user to receive real-time support for problem-solving. 【0469】 An example of a prompt message could be: "Instantly optimize the learning content based on the user's facial expressions and gaze information. For example, if the user shows a confused expression during learning, insert a short explanatory video." By inputting this prompt message into the AI ​​generation model, appropriate learning content will be suggested. 【0470】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0471】 Step 1: 【0472】 When a user logs into a device, the device sends the user's authentication information to the server. Based on this input, the server retrieves the user's learning history and past learning data from the database and outputs it as learning information. 【0473】 Step 2: 【0474】 The server executes an analysis algorithm based on the acquired learning information. It analyzes the input learning information in detail to evaluate the user's current academic level and learning tendencies. This analysis generates an individualized educational plan. As a result, it outputs an educational plan optimized for the user. 【0475】 Step 3: 【0476】 The terminal sends a request to the server to generate practice problems based on the educational plan. The server receives this request, selects appropriate practice problems based on the educational plan, and outputs that set of problems to the user's terminal. 【0477】 Step 4: 【0478】 When a user uses smart glasses to work on practice problems, the device detects visual information using the camera built into the smart glasses. It inputs gaze and facial expression data acquired from the camera and analyzes the user's concentration level and emotions in real time. This analysis result is then sent to a server. 【0479】 Step 5: 【0480】 The server receives the results of visual information analysis and uses a generative AI model to optimize the learning content. For example, if the user is confused, it automatically suggests supplementary explanatory videos or additional learning materials based on the prompt text. This modified learning content is then output to the user's device. 【0481】 Step 6: 【0482】 The device displays optimized learning content sent from the server on the HUD. This allows users to progress through the learning process while receiving visual aids to deepen their understanding of the material in real time. 【0483】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0484】 The present invention is implemented as an online learning system accessed through a user's terminal. This system is server-centric and incorporates an emotion engine that recognizes the user's emotions, enabling individually optimized learning support. A specific embodiment of this system is described below. 【0485】 When a user logs into the system using a device, the server collects the user's learning data and emotional information. Emotional information is acquired in real time through the device's camera, microphone, sensors, etc. The server inputs this emotional data into the emotional engine to determine the user's current emotional state. 【0486】 Based on the determined emotional state, the server further analyzes the user's learning data. In particular, it identifies the emotional patterns the user exhibits during learning and provides a corresponding learning plan. For example, if the server determines that the user is feeling frustrated while working on a difficult problem, it adjusts the learning plan, temporarily lowering the difficulty level or providing content that helps with relaxation. 【0487】 Furthermore, the server dynamically generates practice problems based on the user's emotions, and adjusts the explanations to match those emotions. By combining these emotion engines, it becomes possible to provide a learning experience that aligns with the user's emotional state. 【0488】 As a concrete example, imagine a high school student intensely studying a specific section of history before a test. If the system detects signs of frustration, the server will modify the study schedule and provide edutainment content to boost motivation. It will also add explanations for difficult sections to help the user calmly return to their studies. 【0489】 This invention aims to create an advanced learning environment that not only supports the user's academic performance but also takes into account emotional support. 【0490】 The following describes the processing flow. 【0491】 Step 1: 【0492】 The user logs into the system via their device. The device sends the user's authentication information to the server. The server verifies the authentication information and makes it possible to access the user's profile data. 【0493】 Step 2: 【0494】 The server retrieves user learning data and emotional information from the terminal. Emotional information is collected in real time via the camera and microphone. This includes facial recognition and voice tone analysis. 【0495】 Step 3: 【0496】 The server analyzes the acquired training data and emotional data. The emotional engine determines the user's current emotional state and evaluates factors such as stress levels and concentration. 【0497】 Step 4: 【0498】 The server adjusts the learning plan based on the user's emotional state. If the user's emotional state is negative, the server will either change the difficulty level of the learning material or suggest relaxation content. 【0499】 Step 5: 【0500】 The server generates practice problems based on the user's emotions and learning history. The difficulty and format of the problems are adjusted to match the user's emotional state. Furthermore, the explanations for the problems are customized to be easily understood by the user. 【0501】 Step 6: 【0502】 Users work on practice problems and study plans through their devices. The devices feed back the user's progress and new sentiment data to the server. 【0503】 Step 7: 【0504】 The server analyzes feedback and dynamically updates the learning plan as needed. Real-time adjustments are made to optimize the user's learning experience. 【0505】 (Example 2) 【0506】 Next, we will describe Example 2. 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." 【0507】 Traditional online learning systems require personalized learning support to maximize user learning efficiency, but they lack systems that take into account users' emotional states, resulting in challenges in improving learning motivation and continuity. In particular, it has been difficult to adequately address frustration and decreased motivation that occur during learning. 【0508】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0509】 In this invention, the server includes means for collecting known bodily signals using a biometric information acquisition device, means for determining the emotional state based on an AI model that generates the collected bodily signals, and means for analyzing the learning data. This makes it possible to provide a learning experience that is individually optimized according to the user's emotional state. 【0510】 A "user" refers to an individual who uses the system to engage in online learning. 【0511】 "Means of acquiring information" refers to methods of collecting data entered by users and login information. 【0512】 A "biometric information acquisition device" refers to a device that collects a user's physical signals using cameras, microphones, sensors, etc. 【0513】 "Physiological signals" refer to physiological data related to determining an emotional state, such as the user's facial expressions, voice tone, and heart rate. 【0514】 A "generative AI model" refers to an artificial intelligence model that uses machine learning to analyze and predict emotional states. 【0515】 "Emotional state" refers to the state that indicates the user's psychological feelings and emotional tendencies. 【0516】 "Learning data" refers to information such as the user's learning history, grades, and progress. 【0517】 A "learning plan" refers to an individually optimized learning schedule and content created based on analyzed learning data. 【0518】 "Practice problems" refer to questions provided to assist users in their learning and to check their level of understanding. 【0519】 "Means of generating explanations" refers to methods of providing explanations and hints for practice problems to deepen the user's understanding. 【0520】 This invention is an online learning system that provides individually optimized learning support that takes into account the user's emotional state. This system is mainly server-based, and the user and terminal work together in cooperation. 【0521】 When a user logs into the online learning system via their device, the server first collects the user's learning data. This data includes past learning history and current progress. Simultaneously, the device utilizes its built-in camera, microphone, and various sensors to collect biometric information in real time. This allows the server to understand the user's facial expressions, voice tone, heart rate, and other characteristics. 【0522】 Next, the server uses a generative AI model to determine the user's emotional state based on the collected bodily signals. At this stage, the user's emotional tendencies, such as whether they are relaxed or feeling frustrated, are revealed. 【0523】 By integrating this emotional state data with training data, the server performs a comprehensive analysis and automatically generates an individually optimized learning plan. This includes selecting practice exercises that match the user's emotions and providing content to promote relaxation. 【0524】 For example, suppose a high school student is studying history and encounters a section they find difficult to understand, and the system detects their frustration. In this case, the server can provide new practice problems with adjusted difficulty levels and dynamically generate explanations to further aid understanding. It can also recommend video content incorporating edutainment elements to help boost their motivation to learn. 【0525】 An example of a prompt message might be: "The user is feeling frustrated. Generate easier practice exercises and provide relaxing content." 【0526】 In this way, the system can improve the quality and efficiency of learning by providing a flexible learning experience while taking user emotions into consideration. 【0527】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0528】 Step 1: 【0529】 The user logs into the online learning system. The user uses their device to enter their account information and begin accessing the system. At this stage, the server receives the input, performs an authentication process, and confirms successful login. The output is the user's learning dashboard. 【0530】 Step 2: 【0531】 Upon successful login, the server collects the user's learning history data and real-time biometric data. Cameras, microphones, and sensors on the device are used for data collection. Input consists of the user's past learning history and current biometric signals. This data is transformed, and integrated information is output. 【0532】 Step 3: 【0533】 The server uses integrated information to run a generative AI model that determines the user's current emotional state. The input here is biosignal data. This data is analyzed and outputted as the user's emotion, such as relaxed, tense, or frustrated. 【0534】 Step 4: 【0535】 After determining the user's emotional state, the server analyzes the user's training data and generates an optimized training plan. The input consists of the user's training history and emotional state. Based on this information, data calculations are performed, and an individual training plan is output. This plan includes training content tailored to the user's emotional state. 【0536】 Step 5: 【0537】 The server creates practice problems and their explanations based on the generated training plan. The input is the training plan. Based on this, a generative AI model is used to automatically generate and output the problem settings and explanation content. 【0538】 Step 6: 【0539】 The server suggests edutainment and relaxation content that matches the user's emotional state. Equal inputs are the emotional state and the user's learning progress. Based on this, the server provides output content that enhances the user's motivation. 【0540】 Step 7: 【0541】 Users progress through their learning based on the provided learning plans, practice problems, and content. They receive system output via their devices and engage in individually optimized learning. Finally, the user's learning progress is fed back as input, and the system continues to operate. 【0542】 (Application Example 2) 【0543】 Next, we will explain application example 2. In the following explanation, 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." 【0544】 Modern online learning systems demand personalized learning experiences. However, traditional systems lack learning adjustments and content recommendations based on user emotional states, making it difficult to maximize user learning efficiency. Therefore, a system is needed that dynamically adjusts learning plans according to user emotions and recommends entertainment content in conjunction with these adjustments. 【0545】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0546】 In this invention, the server includes means for acquiring user input information, means for analyzing learning information, means for generating individualized learning plans based on the analysis, and means for recognizing the user's emotional state and dynamically recommending content based on that emotional state. This makes it possible to maximize the user's learning efficiency while providing an optimal learning experience and content tailored to their emotions. 【0547】 "User input information" refers to all information provided by users in an online learning system, such as text data and selected data. 【0548】 "Learning information" refers to data related to educational materials and learning content provided for educational purposes. 【0549】 An "educational plan" refers to an educational and learning schedule and curriculum that is individually set to help users achieve their learning goals. 【0550】 "Practice exercises" refer to problems and exercises provided to test the knowledge and skills that users have acquired. 【0551】 "Explanation" refers to text or data that provides answers or explanations related to the practice exercises. 【0552】 "Emotional state" refers to the emotional reactions or psychological conditions a user exhibits at a particular point in time. 【0553】 "Dynamic content recommendation" refers to a system that selects and presents appropriate entertainment and educational content in real time based on the user's current emotional state. 【0554】 The system for realizing this invention includes a mechanism in which the user's terminal is equipped with a camera, microphone, and various sensors, and acquires user input information and emotional state through these. The server receives the data transmitted from these terminals and executes a program to analyze the learned information. Specifically, it estimates the emotional state from the user's facial expressions and voice using an image processing library such as OpenCV and software components specialized for emotion recognition. 【0555】 The server dynamically generates educational plans and practice tasks based on the user's emotional state. This generation utilizes a generative AI model, adjusting explanations and tasks as needed, taking into account the user's learning history and current progress. Furthermore, it enriches the learning experience by selecting and recommending optimal entertainment content based on the user's emotional state. 【0556】 This system, for example, detects when a user feels stressed while tackling a difficult task, and temporarily adjusts the learning plan. It also recommends relaxing music or videos to alleviate the stress. A specific example of a prompt might be, "The user is feeling relaxed. Please provide a list of movies or music that best suit this feeling," and the server will select appropriate content based on this. 【0557】 In this way, the primary objective of this system is to improve user learning efficiency and satisfaction. 【0558】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0559】 Step 1: 【0560】 The device uses a camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server as input data to evaluate the user's emotional state. 【0561】 Step 2: 【0562】 The server analyzes image data received from the terminal using OpenCV and estimates the user's emotions from their facial expressions. In this process, facial expression patterns exhibiting specific psychological characteristics are compared with a database, and the emotional state is output. 【0563】 Step 3: 【0564】 The server uses emotion recognition software to analyze voice data, associating emotions with the user's speech and intonation. It extracts features from the voice data and determines the emotional nuances expressed in the speech. This result is also output as an emotional state and integrated with the results of facial expression analysis. 【0565】 Step 4: 【0566】 Based on the user's emotional state, the server re-evaluates the user's learning information and adjusts the educational plan. Using a generative AI model, it generates individually optimized educational procedures that take into account the user's learning history and current progress, and outputs them as an educational plan. 【0567】 Step 5: 【0568】 The server dynamically selects entertainment content based on prompts using an AI model that considers the user's emotional state. It determines the most suitable content based on emotional data and outputs a list of content to present to the user. For example, a prompt might be: "The user wants to relax. Please provide a list of movies and music that best suit this emotion." 【0569】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0570】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0571】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0572】 [Fourth Embodiment] 【0573】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0574】 As shown in Figure 7, the 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. 【0575】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0576】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0577】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0578】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0579】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0580】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0581】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0582】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0583】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0584】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0585】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0586】 The present invention is implemented as an online learning system accessed via a user's terminal. This system, centered around a server, is capable of comprehensively analyzing user learning data and generating individually optimized learning plans and practice problems. Specific embodiments are described below. 【0587】 When a user logs into the system via their device, the server retrieves new data from the user, previously collected learning history data, test results, and other information. The server then feeds this information into an analysis algorithm to perform a detailed analysis of the user's current learning status and academic level. 【0588】 The analysis results identify specific academic areas and areas of weakness, and the server uses this information to generate an optimal learning plan for the user. This learning plan is scheduled to match the user's lifestyle and study time, and includes a variety of learning materials (video materials, text materials, etc.). 【0589】 Furthermore, the server generates practice problems that focus on the user's weak subjects and areas. These practice problems are of appropriate difficulty and are designed to effectively check the user's learning. In the explanation section, the server provides detailed solutions and related knowledge to help deepen the user's understanding. 【0590】 As a concrete example, consider a middle school student who struggles with a specific area of ​​mathematics (e.g., functions). When this student accesses the system, the server automatically identifies their weak area based on their past grades and test results. The server then proposes a learning schedule tailored to the user and provides online lessons and practice problems on functions at a consistent pace each week. The problem explanations include visual aids such as diagrams and videos at key points to support the user's understanding. 【0591】 Thus, the present invention enables flexible learning support tailored to the user's individuality and learning situation, and makes it possible to provide advanced educational services at a low cost. 【0592】 The following describes the processing flow. 【0593】 Step 1: 【0594】 The user logs into the system using a terminal. The terminal sends the user's authentication information to the server. The server verifies the authentication information and allows access to the user's profile data. 【0595】 Step 2: 【0596】 The server receives user input and past learning history data. This includes the user's most recently completed test results and learning time. The server stores this data in a database and updates it to the latest state. 【0597】 Step 3: 【0598】 The server executes machine learning algorithms and analyzes the collected training data. The server identifies the user's learning patterns, weaknesses, and strengths, and evaluates the user's academic ability. 【0599】 Step 4: 【0600】 Based on these analyses, the server generates an optimal learning plan. This plan includes recommended learning materials, schedules, and study methods. The server then sends this information to the terminal. 【0601】 Step 5: 【0602】 The server generates practice problems that focus on the user's weak areas. The difficulty and format of the problems are customized to the user's skill level. The server also creates detailed explanations for each problem. 【0603】 Step 6: 【0604】 The user works through the learning plan and practice problems provided via the device. The device records the user's progress and sends feedback to the server. 【0605】 Step 7: 【0606】 The server analyzes user feedback and progress data, updating or adjusting the learning plan as needed. This information is then reflected in the next learning cycle. 【0607】 (Example 1) 【0608】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0609】 In today's educational environment, providing learning plans and materials tailored to individual learners is crucial for efficient learning. However, general learning systems often lack the flexibility to accommodate individual learning needs and progress, and frequently fail to provide adequate support, particularly for areas of weakness. As a result, learners often do not receive learning experiences that are suitable for improving their academic abilities. 【0610】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0611】 In this invention, the server includes means for acquiring information input by the user, means for analyzing learning data, means for generating an individualized learning plan, means for generating practice problems that focus on the user's weak areas, means for generating detailed explanations, means for performing data analysis and content generation using generational AI technology, and means for visualizing the analysis results. As a result, the user can receive a learning plan and learning materials optimized for their learning situation and needs, enabling them to efficiently improve their academic ability. 【0612】 "Means of obtaining user input" refers to methods of collecting personal information and data related to learning content that users provide to the system, via communication technology. 【0613】 "Means of analyzing learning data" refers to computational processing that analyzes a user's learning history, test results, etc., to evaluate their learning tendencies and level of understanding. 【0614】 "Means for generating personalized learning plans" refers to a method of creating a dedicated learning program tailored to each user's learning goals and progress, based on analyzed learning data. 【0615】 "A means of generating practice problems that focus on the user's weak areas" refers to the ability to identify areas where the user lacks understanding and automatically create problems specifically tailored to those areas. 【0616】 "Means for generating detailed explanations" refers to document creation techniques for clearly explaining the solutions and related knowledge for the generated practice problems. 【0617】 "Methods for performing data analysis and content generation using generative AI technology" refers to methods that utilize artificial intelligence technology to rapidly analyze large amounts of data and generate useful information. 【0618】 "Methods for visualizing analysis results" refer to techniques for displaying the results obtained from data analysis in visual formats such as diagrams and graphs. 【0619】 This invention is a system for providing user-optimized learning plans and individualized instruction in an online learning environment. It consists of a multi-functional program that supports learning activities by accessing a server through the user's terminal. 【0620】 When a user accesses the system from their device, the server retrieves the user's input information using a secure communication protocol. Specifically, the user's learning history and new information are collected and stored in a database. The server performs data analysis using Python or R, formats the data using the Pandas library, and generates statistical information using NumPy. This analysis makes it possible to evaluate the user's academic ability and learning tendencies. 【0621】 Based on the analyzed data, the server uses the SciKit-learn machine learning library to generate a personalized learning plan. This plan includes online learning materials tailored to the user's needs and is scheduled to allow the user to learn efficiently. It also designs a dynamically adjusting learning program using Python and generates practice problems using generative AI technology. The generated practice problems focus on the user's weak areas and provide interactive explanations using the Nomjs library. 【0622】 As a concrete example, if a middle school student struggles with the topic of functions in mathematics, the server analyzes past performance data and creates a personalized learning schedule and supplementary problems for that student. An example of a prompt in this case would be, "Generate practice problems including visual explanations on functions, which is a difficult topic for middle school students in mathematics." The generated content is delivered to the user's terminal and supports interactive, visual learning. 【0623】 This system aims to help improve academic performance by providing personalized education that is tailored to each user's different learning needs. 【0624】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0625】 Step 1: 【0626】 Users log in to the system via their terminal. During this process, authentication information and the user's most recent learning activity data are sent to the server as input. The server securely stores the received user information in a database using encryption technology. This allows the user's account to be identified and access to their past learning records. 【0627】 Step 2: 【0628】 The server retrieves user learning history data stored in the database and newly entered learning activity data. Using this as input, it converts it into a DataFrame using the Python Pandas library and performs data preprocessing. Specifically, this includes data cleaning and missing value imputation. The output of this process is an analyzable dataset. 【0629】 Step 3: 【0630】 The server analyzes the dataset obtained in the previous step. Here, NumPy is used to analyze the data using statistical methods. As a result, the user's academic level and learning tendencies are output. Based on these analysis results, the user's strengths and weaknesses are visualized. 【0631】 Step 4: 【0632】 The server uses SciKit-learn to build a machine learning model and generates a user-optimized learning plan based on the analysis results. The input consists of the user's current learning progress data and past learning history, which is used to predict learning patterns. The output is a user-specific learning schedule, including the format of learning materials and exercises. 【0633】 Step 5: 【0634】 The server uses a generative AI model to generate practice problems tailored to the user's weak areas. Past test results and progress are used as input, and the generated problems are adjusted to an optimal difficulty level. The output consists of practice problems and accompanying detailed explanations. 【0635】 Step 6: 【0636】 The server delivers practice problems and explanations to the terminal. When the user solves a problem, the result is sent back to the server as input. The server evaluates the result and updates the user's current level of understanding. Specifically, this includes visualizing the user's progress on an interactive dashboard. This result is used to dynamically adjust the next learning plan. 【0637】 (Application Example 1) 【0638】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0639】 In online learning systems, a challenge is providing a dynamically optimized learning experience tailored to each user's individual learning needs. In particular, the lack of functionality to adjust learning content in real time using the user's visual information is a problem that hinders user learning efficiency. 【0640】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0641】 In this invention, the server includes means for acquiring data input by the user, means for analyzing learning information, and means for generating individualized learning plans based on the analysis. This makes it possible to optimize learning content in real time based on the user's visual information. 【0642】 A "user" is an individual who uses the system to access educational content and practice problems. 【0643】 "Data" refers to information entered by the user and learning-related information used by the server for analysis. 【0644】 "Learning information" refers to data related to a user's learning history and current learning status. 【0645】 "Analysis" is the process by which a server analyzes a user's learning information and evaluates their academic ability and learning tendencies. 【0646】 An "educational plan" is a plan that provides a learning schedule and materials optimized for the user. 【0647】 "Practice problems" are assignments generated to deepen the user's understanding of the learning material. 【0648】 "Visual information" refers to data related to facial expressions and eye movements acquired by users using smart glasses or similar devices. 【0649】 "Dynamic optimization" means adaptively adjusting educational content based on the user's real-time learning progress. 【0650】 The system for implementing this invention aims to provide users with a personalized learning experience using smart glasses or other devices. A server acquires input data from the user and analyzes the learning information in detail. This analysis generates an individualized learning plan, and based on that plan, practice problems optimized for the user are created. 【0651】 The server monitors the user's learning progress in real time by detecting visual information. This includes facial expression and gaze data obtained from cameras built into smart glasses. This data is analyzed using image processing libraries such as OpenCV, along with Emotion Detection and Eye Tracking modules. This allows the server to measure the user's concentration and comprehension levels and dynamically optimize the learning content. 【0652】 As a concrete example, imagine a student wearing smart glasses during a math class. If the student's facial expression shows signs of confusion during the class, the server immediately detects this and adjusts the learning content accordingly, displaying corresponding support videos and diagrams on the HUD. This allows the user to receive real-time support for problem-solving. 【0653】 An example of a prompt message could be: "Instantly optimize the learning content based on the user's facial expressions and gaze information. For example, if the user shows a confused expression during learning, insert a short explanatory video." By inputting this prompt message into the AI ​​generation model, appropriate learning content will be suggested. 【0654】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0655】 Step 1: 【0656】 When a user logs into a device, the device sends the user's authentication information to the server. Based on this input, the server retrieves the user's learning history and past learning data from the database and outputs it as learning information. 【0657】 Step 2: 【0658】 The server executes an analysis algorithm based on the acquired learning information. It analyzes the input learning information in detail to evaluate the user's current academic level and learning tendencies. This analysis generates an individualized educational plan. As a result, it outputs an educational plan optimized for the user. 【0659】 Step 3: 【0660】 The terminal sends a request to the server to generate practice problems based on the educational plan. The server receives this request, selects appropriate practice problems based on the educational plan, and outputs that set of problems to the user's terminal. 【0661】 Step 4: 【0662】 When a user uses smart glasses to work on practice problems, the device detects visual information using the camera built into the smart glasses. It inputs gaze and facial expression data acquired from the camera and analyzes the user's concentration level and emotions in real time. This analysis result is then sent to a server. 【0663】 Step 5: 【0664】 The server receives the results of visual information analysis and uses a generative AI model to optimize the learning content. For example, if the user is confused, it automatically suggests supplementary explanatory videos or additional learning materials based on the prompt text. This modified learning content is then output to the user's device. 【0665】 Step 6: 【0666】 The device displays optimized learning content sent from the server on the HUD. This allows users to progress through the learning process while receiving visual aids to deepen their understanding of the material in real time. 【0667】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0668】 The present invention is implemented as an online learning system accessed through a user's terminal. This system is server-centric and incorporates an emotion engine that recognizes the user's emotions, enabling individually optimized learning support. A specific embodiment of this system is described below. 【0669】 When a user logs into the system using a device, the server collects the user's learning data and emotional information. Emotional information is acquired in real time through the device's camera, microphone, sensors, etc. The server inputs this emotional data into the emotional engine to determine the user's current emotional state. 【0670】 Based on the determined emotional state, the server further analyzes the user's learning data. In particular, it identifies the emotional patterns the user exhibits during learning and provides a corresponding learning plan. For example, if the server determines that the user is feeling frustrated while working on a difficult problem, it adjusts the learning plan, temporarily lowering the difficulty level or providing content that helps with relaxation. 【0671】 Furthermore, the server dynamically generates practice problems based on the user's emotions, and adjusts the explanations to match those emotions. By combining these emotion engines, it becomes possible to provide a learning experience that aligns with the user's emotional state. 【0672】 As a concrete example, imagine a high school student intensely studying a specific section of history before a test. If the system detects signs of frustration, the server will modify the study schedule and provide edutainment content to boost motivation. It will also add explanations for difficult sections to help the user calmly return to their studies. 【0673】 This invention aims to create an advanced learning environment that not only supports the user's academic performance but also takes into account emotional support. 【0674】 The following describes the processing flow. 【0675】 Step 1: 【0676】 The user logs into the system via their device. The device sends the user's authentication information to the server. The server verifies the authentication information and makes it possible to access the user's profile data. 【0677】 Step 2: 【0678】 The server retrieves user learning data and emotional information from the terminal. Emotional information is collected in real time via the camera and microphone. This includes facial recognition and voice tone analysis. 【0679】 Step 3: 【0680】 The server analyzes the acquired training data and emotional data. The emotional engine determines the user's current emotional state and evaluates factors such as stress levels and concentration. 【0681】 Step 4: 【0682】 The server adjusts the learning plan based on the user's emotional state. If the user's emotional state is negative, the server will either change the difficulty level of the learning material or suggest relaxation content. 【0683】 Step 5: 【0684】 The server generates practice problems based on the user's emotions and learning history. The difficulty and format of the problems are adjusted to match the user's emotional state. Furthermore, the explanations for the problems are customized to be easily understood by the user. 【0685】 Step 6: 【0686】 Users work on practice problems and study plans through their devices. The devices feed back the user's progress and new sentiment data to the server. 【0687】 Step 7: 【0688】 The server analyzes feedback and dynamically updates the learning plan as needed. Real-time adjustments are made to optimize the user's learning experience. 【0689】 (Example 2) 【0690】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0691】 Traditional online learning systems require personalized learning support to maximize user learning efficiency, but they lack systems that take into account users' emotional states, resulting in challenges in improving learning motivation and continuity. In particular, it has been difficult to adequately address frustration and decreased motivation that occur during learning. 【0692】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0693】 In this invention, the server includes means for collecting known bodily signals using a biometric information acquisition device, means for determining the emotional state based on an AI model that generates the collected bodily signals, and means for analyzing the learning data. This makes it possible to provide a learning experience that is individually optimized according to the user's emotional state. 【0694】 A "user" refers to an individual who uses the system to engage in online learning. 【0695】 "Means of acquiring information" refers to methods of collecting data entered by users and login information. 【0696】 A "biometric information acquisition device" refers to a device that collects a user's physical signals using cameras, microphones, sensors, etc. 【0697】 "Physiological signals" refer to physiological data related to determining an emotional state, such as the user's facial expressions, voice tone, and heart rate. 【0698】 A "generative AI model" refers to an artificial intelligence model that uses machine learning to analyze and predict emotional states. 【0699】 "Emotional state" refers to the state that indicates the user's psychological feelings and emotional tendencies. 【0700】 "Learning data" refers to information such as the user's learning history, grades, and progress. 【0701】 A "learning plan" refers to an individually optimized learning schedule and content created based on analyzed learning data. 【0702】 "Practice problems" refer to questions provided to assist users in their learning and to check their level of understanding. 【0703】 "Means of generating explanations" refers to methods of providing explanations and hints for practice problems to deepen the user's understanding. 【0704】 This invention is an online learning system that provides individually optimized learning support that takes into account the user's emotional state. This system is mainly server-based, and the user and terminal work together in cooperation. 【0705】 When a user logs into the online learning system via their device, the server first collects the user's learning data. This data includes past learning history and current progress. Simultaneously, the device utilizes its built-in camera, microphone, and various sensors to collect biometric information in real time. This allows the server to understand the user's facial expressions, voice tone, heart rate, and other characteristics. 【0706】 Next, the server uses a generative AI model to determine the user's emotional state based on the collected bodily signals. At this stage, the user's emotional tendencies, such as whether they are relaxed or feeling frustrated, are revealed. 【0707】 By integrating this emotional state data with training data, the server performs a comprehensive analysis and automatically generates an individually optimized learning plan. This includes selecting practice exercises that match the user's emotions and providing content to promote relaxation. 【0708】 For example, suppose a high school student is studying history and encounters a section they find difficult to understand, and the system detects their frustration. In this case, the server can provide new practice problems with adjusted difficulty levels and dynamically generate explanations to further aid understanding. It can also recommend video content incorporating edutainment elements to help boost their motivation to learn. 【0709】 An example of a prompt message might be: "The user is feeling frustrated. Generate easier practice exercises and provide relaxing content." 【0710】 In this way, the system can improve the quality and efficiency of learning by providing a flexible learning experience while taking user emotions into consideration. 【0711】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0712】 Step 1: 【0713】 The user logs into the online learning system. The user uses their device to enter their account information and begin accessing the system. At this stage, the server receives the input, performs an authentication process, and confirms successful login. The output is the user's learning dashboard. 【0714】 Step 2: 【0715】 Upon successful login, the server collects the user's learning history data and real-time biometric data. Cameras, microphones, and sensors on the device are used for data collection. Input consists of the user's past learning history and current biometric signals. This data is transformed, and integrated information is output. 【0716】 Step 3: 【0717】 The server uses integrated information to run a generative AI model that determines the user's current emotional state. The input here is biosignal data. This data is analyzed and outputted as the user's emotion, such as relaxed, tense, or frustrated. 【0718】 Step 4: 【0719】 After determining the user's emotional state, the server analyzes the user's training data and generates an optimized training plan. The input consists of the user's training history and emotional state. Based on this information, data calculations are performed, and an individual training plan is output. This plan includes training content tailored to the user's emotional state. 【0720】 Step 5: 【0721】 The server creates practice problems and their explanations based on the generated training plan. The input is the training plan. Based on this, a generative AI model is used to automatically generate and output the problem settings and explanation content. 【0722】 Step 6: 【0723】 The server suggests edutainment and relaxation content that matches the user's emotional state. Equal inputs are the emotional state and the user's learning progress. Based on this, the server provides output content that enhances the user's motivation. 【0724】 Step 7: 【0725】 Users progress through their learning based on the provided learning plans, practice problems, and content. They receive system output via their devices and engage in individually optimized learning. Finally, the user's learning progress is fed back as input, and the system continues to operate. 【0726】 (Application Example 2) 【0727】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0728】 Modern online learning systems demand personalized learning experiences. However, traditional systems lack learning adjustments and content recommendations based on user emotional states, making it difficult to maximize user learning efficiency. Therefore, a system is needed that dynamically adjusts learning plans according to user emotions and recommends entertainment content in conjunction with these adjustments. 【0729】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0730】 In this invention, the server includes means for acquiring user input information, means for analyzing learning information, means for generating individualized learning plans based on the analysis, and means for recognizing the user's emotional state and dynamically recommending content based on that emotional state. This makes it possible to maximize the user's learning efficiency while providing an optimal learning experience and content tailored to their emotions. 【0731】 "User input information" refers to all information provided by users in an online learning system, such as text data and selected data. 【0732】 "Learning information" refers to data related to educational materials and learning content provided for educational purposes. 【0733】 An "educational plan" refers to an educational and learning schedule and curriculum that is individually set to help users achieve their learning goals. 【0734】 "Practice exercises" refer to problems and exercises provided to test the knowledge and skills that users have acquired. 【0735】 "Explanation" refers to text or data that provides answers or explanations related to the practice exercises. 【0736】 "Emotional state" refers to the emotional reactions or psychological conditions a user exhibits at a particular point in time. 【0737】 "Dynamic content recommendation" refers to a system that selects and presents appropriate entertainment and educational content in real time based on the user's current emotional state. 【0738】 The system for realizing this invention includes a mechanism in which the user's terminal is equipped with a camera, microphone, and various sensors, and acquires user input information and emotional state through these. The server receives the data transmitted from these terminals and executes a program to analyze the learned information. Specifically, it estimates the emotional state from the user's facial expressions and voice using an image processing library such as OpenCV and software components specialized for emotion recognition. 【0739】 The server dynamically generates educational plans and practice tasks based on the user's emotional state. This generation utilizes a generative AI model, adjusting explanations and tasks as needed, taking into account the user's learning history and current progress. Furthermore, it enriches the learning experience by selecting and recommending optimal entertainment content based on the user's emotional state. 【0740】 This system, for example, detects when a user feels stressed while tackling a difficult task, and temporarily adjusts the learning plan. It also recommends relaxing music or videos to alleviate the stress. A specific example of a prompt might be, "The user is feeling relaxed. Please provide a list of movies or music that best suit this feeling," and the server will select appropriate content based on this. 【0741】 In this way, the primary objective of this system is to improve user learning efficiency and satisfaction. 【0742】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0743】 Step 1: 【0744】 The device uses a camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server as input data to evaluate the user's emotional state. 【0745】 Step 2: 【0746】 The server analyzes image data received from the terminal using OpenCV and estimates the user's emotions from their facial expressions. In this process, facial expression patterns exhibiting specific psychological characteristics are compared with a database, and the emotional state is output. 【0747】 Step 3: 【0748】 The server uses emotion recognition software to analyze voice data, associating emotions with the user's speech and intonation. It extracts features from the voice data and determines the emotional nuances expressed in the speech. This result is also output as an emotional state and integrated with the results of facial expression analysis. 【0749】 Step 4: 【0750】 Based on the user's emotional state, the server re-evaluates the user's learning information and adjusts the educational plan. Using a generative AI model, it generates individually optimized educational procedures that take into account the user's learning history and current progress, and outputs them as an educational plan. 【0751】 Step 5: 【0752】 The server dynamically selects entertainment content based on prompts using an AI model that considers the user's emotional state. It determines the most suitable content based on emotional data and outputs a list of content to present to the user. For example, a prompt might be: "The user wants to relax. Please provide a list of movies and music that best suit this emotion." 【0753】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0754】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0755】 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0756】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0757】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0758】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0759】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0760】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0761】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0762】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0763】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0764】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0765】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0766】 Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12. 【0767】 Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0768】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0769】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0770】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0771】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0772】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0773】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference. 【0774】 The following is further disclosed regarding the embodiments described above. 【0775】 (Claim 1) 【0776】 Means of obtaining information entered by the user, 【0777】 Methods for analyzing training data, 【0778】 Based on the analysis, means for generating individual learning plans, 【0779】 A means for generating practice problems based on the aforementioned learning plan, 【0780】 A means for generating an explanation for the practice problem, 【0781】 A system that includes this. 【0782】 (Claim 2) 【0783】 The system according to claim 1, further comprising means for recording and updating user learning history data. 【0784】 (Claim 3) 【0785】 The system according to claim 1, further comprising means for dynamically adjusting the learning plan based on the user's learning tendencies. 【0786】 "Example 1" 【0787】 (Claim 1) 【0788】 Means of obtaining information entered by the user, 【0789】 Methods for analyzing training data, 【0790】 A means for generating an individualized learning plan based on the analysis, 【0791】 A means for generating practice problems that focus on the user's weak areas based on the aforementioned learning plan, 【0792】 A means for generating a detailed explanation for the practice problem, 【0793】 A means of performing data analysis and content generation using generative AI technology, 【0794】 Means for visualizing the analysis results, 【0795】 A system that includes this. 【0796】 (Claim 2) 【0797】 The system according to claim 1, further comprising means for recording, updating, and analyzing user learning history data. 【0798】 (Claim 3) 【0799】 The system according to claim 1, further comprising means for dynamically adjusting the learning plan based on the user's learning tendencies and progress. 【0800】 "Application Example 1" 【0801】 (Claim 1) 【0802】 A means of obtaining data entered by the user, 【0803】 A means of analyzing learning information, 【0804】 A means for generating individual educational plans based on the analysis, 【0805】 Based on the aforementioned educational plan, means for creating practice problems, 【0806】 Means for generating an explanation for the practice problem, 【0807】 Means for detecting the user's visual information, 【0808】 A means for dynamically optimizing the learning content based on the visual information, 【0809】 A system that includes this. 【0810】 (Claim 2) 【0811】 The system according to claim 1, further comprising means for recording and updating user learning history information. 【0812】 (Claim 3) 【0813】 The system according to claim 1, further comprising means for dynamically adjusting the educational plan based on the user's learning tendencies and visual analysis results. 【0814】 "Example 2 of combining an emotion engine" 【0815】 (Claim 1) 【0816】 Means of obtaining information entered by the user, 【0817】 A means for collecting known bodily signals using a biometric information acquisition device, 【0818】 A means for determining emotional states based on a generated AI model of collected bodily signals, 【0819】 Methods for analyzing training data, 【0820】 A means for generating individual learning plans based on the analysis, 【0821】 A means for generating practice problems based on the aforementioned learning plan, 【0822】 A means for generating an explanation for the practice problem, 【0823】 A system that includes this. 【0824】 (Claim 2) 【0825】 The system according to claim 1, further comprising means for recording and updating user learning history data. 【0826】 (Claim 3) 【0827】 The system according to claim 1, further comprising means for dynamically adjusting the learning plan based on the user's learning tendencies and emotional state. 【0828】 "Application example 2 when combining with an emotional engine" 【0829】 (Claim 1) 【0830】 The part that acquires user input information, 【0831】 The part of the brain that analyzes learning information, 【0832】 Based on the analysis, a part generates an individualized educational plan, 【0833】 Based on the aforementioned educational plan, the part that generates practice tasks, 【0834】 A part that generates an explanation for the practice task, 【0835】 A part that recognizes the user's emotional state and dynamically recommends content based on that emotional state, 【0836】 A system that includes this. 【0837】 (Claim 2) 【0838】 The system according to claim 1, further comprising a component for recording and updating user learning history information. 【0839】 (Claim 3) 【0840】 The system according to claim 1, further comprising a component in which the educational plan is dynamically adjusted based on the user's learning tendencies and emotional state. [Explanation of symbols] 【0841】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] Means of obtaining information entered by the user, Methods for analyzing training data, Based on the analysis, means for generating individual learning plans, A means for generating practice problems based on the aforementioned learning plan, A means for generating an explanation for the practice problem, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for recording and updating user learning history data. [Claim 3] The system according to claim 1, further comprising means for dynamically adjusting the learning plan based on the user's learning tendencies.

Images