system

Abstract

We provide the system. [Solution] A means of receiving answer data and identifying incorrect answers, A means to analyze the cause of incorrect answers and collect corresponding information, A means of presenting analysis results and collected information to the user, A means of accumulating analysis results and making suggestions for future learning, 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 a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional learning support system, incorrect answer analysis in qualification exams and exam preparation is not systematically carried out, and it takes a great deal of time and effort for users to identify the causes of incorrect answers and take appropriate learning measures. This problem is a major obstacle, especially for working people with limited time and students who desire efficient learning.

Means for Solving the Problems

[0005] This invention provides a means for receiving user test answer data and identifying incorrect answers. Furthermore, it includes a means for analyzing the causes of incorrect answers using a generating AI and automatically collecting related information, thereby presenting the analysis results and collected information to the user. This enables efficient learning strategies and provides a means for accumulating user error data and making suggestions for future learning.

[0006] "Answer data" refers to information about the answers that users have entered or selected in exams or practice problems.

[0007] An "incorrect answer" refers to a user's response that differs from the correct answer.

[0008] "Analyzing the cause" refers to the process of analyzing and identifying the background that led to the incorrect answer, as well as any lack of understanding or misunderstandings the user may have had.

[0009] "Collecting information" refers to the act of gathering relevant information from databases or the internet that is useful for solving a problem, based on the results of analysis.

[0010] "Presenting" refers to the system displaying analysis results and collected data / information in a user-friendly and easy-to-understand format on screens and reports.

[0011] "Accumulating analysis results" refers to recording the data and conclusions obtained through processing in a database and using them for future learning support and personalized learning experiences.

[0012] "Providing learning suggestions" means offering plans that recommend the most suitable learning methods and supplementary materials for each individual user, based on accumulated data. [Brief explanation of the drawing]

[0013] [Figure 1] This 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of 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.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a 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.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a 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, and the like.

[0019] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This learning support system uses generative AI to analyze the causes of incorrect answers in exams and supports efficient learning strategies. Specifically, three entities—the server, the terminal, and the user—work together to perform the following processes.

[0035] The server receives answer data submitted by users and identifies incorrect answers by comparing them with correct answer data. The server uses a generative AI to analyze the identified incorrect answers and identify their causes. This cause analysis includes misunderstandings of terminology, calculation errors, and lack of knowledge. Based on the analysis results, the server collects relevant supplementary information from databases and the internet.

[0036] Next, the terminal presents the user with the analysis results and collected information received from the server. This presentation is designed to allow the user to easily understand the cause of incorrect answers and includes specific supplementary explanations and additional learning materials to deepen understanding.

[0037] Users utilize the information provided through their devices to understand the causes of incorrect answers and identify areas for improvement in their next study session. This enables efficient learning even within limited timeframes, optimizing exam preparation.

[0038] For example, if a user answers a network question on an IT certification exam incorrectly, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model." Based on this, the terminal provides the user with a detailed explanation of the OSI reference model and related video links to help the user deepen their understanding.

[0039] In this way, the learning support system efficiently carries out a series of processes, from identifying the cause of incorrect answers to providing information for resolution, thereby maximizing the user's learning effectiveness.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] After the user takes the test, they enter their answer data into the input form on their device and press the submit button to send it to the server.

[0043] Step 2:

[0044] The server stores the answer data received from the user in a database and compares it with the correct answer data to identify incorrect answers.

[0045] Step 3:

[0046] The server sends the identified incorrect answers to the generating AI, which then analyzes the cause of the errors. The analysis results include factors such as insufficient understanding, lack of attention, and misreading.

[0047] Step 4:

[0048] Based on the analysis results, the server collects relevant supplementary materials and explanations from databases and the internet.

[0049] Step 5:

[0050] The terminal displays the analysis results and supplementary materials received from the server to the user. It includes explanatory text and reference links to facilitate user understanding.

[0051] Step 6:

[0052] The user uses the displayed materials to identify the cause of their incorrect answers and to study additional material as needed.

[0053] Step 7:

[0054] The server stores the analysis results and the user's learning responses in a database, which will then be used as data to support future learning.

[0055] (Example 1)

[0056] 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."

[0057] In today's educational environment, a challenge is to analyze the causes of learners' incorrect answers on exams and provide effective learning support based on those analyses. Because the causes of errors are often difficult to identify, and learners risk repeating similar mistakes, efficient instruction is essential.

[0058] 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.

[0059] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the incorrect answers using a generation AI model and identifying the causes, and means for collecting relevant information resources based on the analysis results. This makes it possible to quickly and accurately identify the causes of incorrect answers and provide learners with appropriate feedback and learning resources.

[0060] "Answer information" refers to data that describes the content of the answers that users have entered for the exam questions.

[0061] An "incorrect answer" refers to a user's answer that does not match the correct answer data when compared.

[0062] A "generative AI model" is an artificial intelligence model used to analyze data and identify the causes of incorrect answers.

[0063] "Analysis results" refer to data obtained after error analysis using a generative AI model, indicating the causes and identified problems.

[0064] "Information resources" refer to a collection of knowledge-enhancing tools, such as explanatory materials and supplementary learning materials, that are collected as needed.

[0065] "Feedback" refers to guidance information, including analysis results and additional information, provided to the user.

[0066] "Learning history" refers to the history of learning activities and answers that a user has performed in the past.

[0067] An "external database" refers to a system or location that stores information that exists on the internet or within an organization.

[0068] This learning support system utilizes three components—a server, a terminal, and a user—to improve learning efficiency. Specifically, the server receives answer information submitted by the user and compares it with its internally maintained database of correct answers. When an incorrect answer is identified, the server uses a generative AI model to analyze the cause of the error. This generative AI model utilizes artificial intelligence technology to accurately identify the cause of the error through pattern recognition of the data. After the analysis is complete, the server collects relevant information resources from an external database.

[0069] Next, the terminal presents the user with the analysis results and information resources sent from the server. This display is designed with user-friendly UI / UX to ensure easy comprehension, and the information is provided in various formats, including text, diagrams, and videos. This allows the user to understand the specific reasons for incorrect answers and to refer to supplementary materials for further learning.

[0070] As a concrete example, consider a case where a user answers a network-related question incorrectly on an information technology certification exam. In this case, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model" and collects relevant detailed explanations and video links from the internet, sending them to the user's terminal. As a result, the user can deepen their understanding of this area and achieve better results on the next exam.

[0071] An example of a prompt message might be, "Generate materials and test questions to help students who want to learn the fundamentals of information technology deepen their understanding of the OSI model." Upon receiving such a prompt message, the system provides optimal learning support.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user enters their answers to the test questions into a terminal and sends them to the server. The entered data includes the question ID and the answer. The terminal packages this answer information into packets and forwards them to the server. The server decodes the received packets and stores the answer information in its internal database.

[0075] Step 2:

[0076] The server compares the stored answer information with the correct answer database to identify incorrect answers. In the comparison process, the question ID is used as a key to compare the correct answer with the user's answer; if they do not match, the answer is flagged as incorrect. The incorrect answer data includes the question ID and the content of the incorrect answer. This comparison result is then entered into the next processing step.

[0077] Step 3:

[0078] The server passes the incorrect answers as input to the AI ​​model that generates them, and the AI ​​model begins its root cause analysis. The AI ​​model uses prompts to analyze patterns in the incorrect answers and identifies the causes of the errors. The output generated here is detailed attribute information indicating the cause of the incorrect answers. For example, "misunderstanding of concepts" or "lack of terminology" may be identified.

[0079] Step 4:

[0080] Based on the outputted reasons for incorrect answers, the server collects relevant information resources from external databases and the internet. This collection process uses keywords to search for appropriate materials and video links. The collected output data is diverse, including explanatory text, related links, and visual materials.

[0081] Step 5:

[0082] The terminal presents the user with analysis results and information resources received from the server. The terminal's UI is designed to display the information in a user-friendly format. The user can review this display and, if necessary, access supplementary materials to deepen their understanding. This output includes points for improving the user's learning process.

[0083] Step 6:

[0084] Based on the information provided through the device, users understand the detailed reasons for incorrect answers and adjust their learning accordingly. When users provide feedback, that data is returned to the server and saved for future system improvements and as part of the user's learning history. The feedback information, as output, enriches the next cycle and plays a role in improving learning outcomes.

[0085] (Application Example 1)

[0086] 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."

[0087] In recent years, users have sometimes made incorrect transaction behaviors in electronic payment settings, creating a need for means to identify the causes and provide corrective measures. Current systems lack sufficient feedback based on users' past behavioral history, making it difficult to prevent the recurrence of incorrect behavior.

[0088] 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.

[0089] In this invention, the server includes means for receiving answer data and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for analyzing the user's behavior history and identifying the cause of erroneous transaction behavior. This makes it possible to identify the cause when a user engages in erroneous transaction behavior and provide appropriate feedback.

[0090] "Answer data" refers to the answers provided by users, and is the basis for identifying incorrect answers.

[0091] An "incorrect answer" is a response that does not match the correct answer data and is therefore identified as an error.

[0092] "Cause analysis" is the process of analyzing the background and reasons for incorrect answers using generative AI.

[0093] "Response information" refers to supplementary materials and advice collected based on identified causes, which contribute to improving erroneous trading behavior.

[0094] "User activity history" refers to records of transactions and activities that users have performed in the past, and is data used to analyze the causes of incorrect answers.

[0095] "Feedback" refers to information provided to users regarding analysis results and improvement measures, intended to encourage them to reconsider their actions.

[0096] The system that realizes this invention mainly consists of three elements: a server, a terminal, and a user. The server receives answer data transmitted from the user and compares it with correct answer data stored in a database to identify incorrect answers. In this process, a generative AI model is used to analyze the incorrect answers and identify the causes related to the incorrect answers. Based on the identified causes, relevant corresponding information is collected from the database and external information sources.

[0097] The terminal displays analysis results and related information sent from the server in a way that is easy for the user to understand. Specifically, it provides intuitive feedback to the user using a user-friendly interface. It also includes a function to provide related explanatory materials and supplementary materials to further promote understanding.

[0098] Through this system, users can receive feedback on their incorrect transaction behavior. For example, if they have made purchases that exceeded their budget in the past, the system may analyze the cause as "insufficient planning" and send a prompt advising them to use a budget management tool. This prompt might say something like, "Your current spending exceeds your budget. Use a budget management tool to plan for future purchases."

[0099] This system utilizes Google Cloud's AI platform to run its generative AI models, and programming is implemented using Python. Furthermore, frameworks such as Django are used for the user interface design. This configuration aims to help users correct their incorrect behaviors and make appropriate payment decisions.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server receives answer data from users. It identifies incorrect answers by comparing the received data with a database. In this process, it compares the input answer data with the correct answer data and generates a list of incorrect answers as output.

[0103] Step 2:

[0104] The server uses a generative AI model to analyze the identified incorrect answers. The AI ​​is fed the specific content of the incorrect answers as input, and through data processing, it identifies the cause of the error and generates an analysis of the cause as output. Specific examples, such as calculation errors or lack of knowledge, are also presented.

[0105] Step 3:

[0106] The server collects relevant correspondence information from a database or external sources based on the analysis results. This process searches the internet for relevant information regarding the causes of incorrect answers and organizes the collected information as output.

[0107] Step 4:

[0108] The terminal displays analysis results and corresponding information sent from the server to the user. The input is the analysis data received from the server, which is displayed visually through the user interface. Specifically, links to additional learning materials and explanatory videos are provided as needed.

[0109] Step 5:

[0110] Based on the information displayed on the terminal, users can understand the cause of their incorrect answers and identify areas for improvement in their future payment behavior. The output may include specific points for improvement in their next transaction. This allows users to review their actions and prepare themselves for making appropriate payments.

[0111] Step 6:

[0112] The server stores analysis results and feedback provided, which are then used to analyze and suggest future user behavior. The database records past incorrect answers and feedback, enabling the system to produce more accurate output for new inputs.

[0113] 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.

[0114] This invention is a learning support system that utilizes an emotion engine, achieving efficient and effective learning through error analysis by generating AI and recognition of the user's emotions. The system mainly consists of a server, terminals, and users.

[0115] The server identifies incorrect answers based on the answer data received from the user and analyzes the cause using a generation AI. Furthermore, it uses an emotion engine to grasp the user's emotional state in real time and analyzes the learning characteristics of each individual user by comparing it with the accumulated learning history.

[0116] The terminal not only presents the user with analysis results from the server and collected related materials, but also provides learning suggestions and environmental adjustments based on the user's emotional state detected by the emotion engine. For example, if the user is experiencing high stress levels, it can suggest taking a break.

[0117] This system allows users to not only clearly understand the causes of their incorrect answers, but also to adjust their learning strategy and pace according to their emotional state. For example, if a user frequently makes incorrect answers about networks during a mock IT certification exam, the system, upon detecting feelings of "anxiety," will recommend setting up a relaxing learning environment and provide time to watch relevant explanatory videos to help deepen their understanding.

[0118] This enables a system that provides effective learning support through collaboration between the server, terminal, and user, maximizing the user's learning effectiveness.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] Users take a practice test on their device, input their answers, and send them to the server.

[0122] Step 2:

[0123] The server compares the received answer data with the model answer to identify incorrect answers.

[0124] Step 3:

[0125] The server uses a generation AI to analyze the cause of the identified incorrect answers. The analysis includes factors such as lack of knowledge, misunderstanding of the problem, and calculation errors.

[0126] Step 4:

[0127] Based on the analysis results, the server automatically collects relevant explanatory materials and supplementary information from databases and the internet.

[0128] Step 5:

[0129] The emotion engine acquires emotional data from the user's device and analyzes the user's emotional state in real time. The analysis utilizes the user's facial expressions, voice tone, input speed, and other factors.

[0130] Step 6:

[0131] The terminal displays analysis results and collected data from the server and presents the user with optimal learning suggestions based on the results of the emotion engine. For example, if a stressful state is detected, it will suggest relaxation techniques.

[0132] Step 7:

[0133] Based on the displayed suggestions, users adjust their learning pace and, if necessary, engage in activities to improve their emotional state.

[0134] Step 8:

[0135] The server stores the analysis results and changes in the user's emotional state in a database, which will be used as data to support future learning.

[0136] (Example 2)

[0137] 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 will be referred to as the "terminal."

[0138] Modern learning support systems face challenges in accurately identifying the causes of user errors and suggesting appropriate learning strategies. Furthermore, a lack of means to adjust the learning environment to optimize performance based on the user's emotional state prevents the learning effect from being maximized. This can lead to decreased user motivation and difficulty in sustained learning.

[0139] 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.

[0140] In this invention, the server includes means for acquiring answer data and identifying incorrect answers, means for analyzing the causes of incorrect answers and aggregating related information, and means for detecting the user's emotional state in real time and proposing adjustments to the learning environment based on that information. This allows the user to clearly understand the causes of their errors and implement effective learning strategies that match their emotional state.

[0141] "Answer data" refers to information about the questions that users have answered and the content of those answers.

[0142] "Means for identifying incorrect answers" refers to methods or devices that analyze user response data and identify incorrect answers by comparing them with correct answers.

[0143] "Means for analyzing causes and aggregating related information" refers to methods and techniques for identifying the causes of incorrect answers and for comprehensively collecting and organizing knowledge and information related to those causes.

[0144] "Means of providing information to the user" refers to methods or devices for presenting analysis results and aggregated information to the user visually or audibly.

[0145] "Means of real-time detection" refers to methods and technologies for monitoring and detecting a user's emotional state in real time.

[0146] "Means of suggesting adjustments to the learning environment" refers to methods and technologies that suggest adjusting the environment and methods to improve learning efficiency based on the detected emotional state of the user.

[0147] A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and perform specific tasks.

[0148] A "prompt statement" refers to a sentence that serves as a command or question input to a generative AI model, and is used to guide the model's output.

[0149] This invention is a system for supporting user learning, consisting of a server, a terminal, and user participation. The server receives answer data and processes it to identify incorrect answers. This involves database and statistical analysis techniques, and the specific software used is a general database management system and data analysis tools. The server also uses a generative AI model to analyze the causes of incorrect answers and aggregate relevant information. In this process, a generative AI model utilizing natural language processing technology is used, and the AI ​​model is envisioned as a generalized "natural language generation engine."

[0150] The server utilizes sentiment analysis technology to detect the user's real-time emotional state. This sentiment analysis includes technologies such as voice analysis and facial recognition, and is implemented via an API-based general-purpose sentiment analysis engine. Based on this information, it is possible to provide more personalized learning suggestions.

[0151] The terminal presents the analysis results from the server to the user, providing information in a format that is easy for the user to understand. It also has a function to make learning suggestions tailored to the emotional environment and adjust the environment to enhance learning effectiveness. For example, if the terminal detects that the user is feeling stressed, it will display a message such as, "If you are losing focus, take a short break to refresh yourself."

[0152] By using the system, users can comprehensively understand their learning progress and adjust their learning strategy and pace as needed. For example, a user can input a prompt into the system such as, "Please recommend video materials to help me understand network-related questions that I got wrong frequently in recent practice tests. I'm feeling nervous right now," and receive appropriate information to proceed with their studies.

[0153] In this way, the server, terminal, and user work together as a unified team to achieve efficient and effective learning support.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The server receives answer data sent from the user via the terminal. It receives the problem identification information and the user's answer as input and stores this in the database. Next, it compares the incorrect answers with the correct answer data to identify them. Here, an algorithm is used to calculate the accuracy rate and output the locations of the user's incorrect answers. Specifically, the server executes database queries and analyzes the obtained data.

[0157] Step 2:

[0158] The server uses a generative AI model to analyze the causes of incorrect answers. The input consists of identified incorrect answer data and information about the problems associated with those incorrect answers. The generative AI model uses natural language processing to analyze the knowledge errors and misunderstandings underlying the incorrect answers. This process outputs the causes of the incorrect answers as analysis results. Specifically, the server creates prompts for the generative AI model and records the model's responses as analysis results.

[0159] Step 3:

[0160] The server activates an emotion engine to detect the user's emotional state in real time. Inputs include user voice data and webcam images. Based on this data, the server analyzes the emotional state and outputs emotional evaluations such as stress levels and concentration levels. Specifically, the server uses voice analysis APIs and facial recognition software to analyze the data and estimate the emotional state.

[0161] Step 4:

[0162] The terminal provides the user with analysis results sent from the server. Input data includes the causes of incorrect answers, related information, and emotional state assessments. Based on this, the terminal visually displays information to the user and outputs suggestions for learning strategies and environment adjustments. Specifically, the terminal displays information in graph and text formats and uses an interactive user interface as needed.

[0163] Step 5:

[0164] Users adjust their learning methods based on the information displayed on their device. They receive suggested information from the server as input and revise their learning plan. Specifically, users can refer to recommended learning materials and follow the provided break advice. As a result, improved learning efficiency and deeper understanding can be expected.

[0165] (Application Example 2)

[0166] 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 device 14 will be referred to as the "terminal."

[0167] In today's learning environment, there is a need for systems that not only identify incorrect answers but also analyze their causes and provide learning suggestions that take into account the user's emotional state, enabling learners to learn effectively while reducing stress. However, conventional learning support systems have been unable to provide real-time feedback or adjust the learning environment while considering the user's emotional state.

[0168] 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.

[0169] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for understanding the user's emotional state using an emotion engine and adjusting the learning environment. This enables learning suggestions and environment adjustments based on the user's emotions.

[0170] "Answer information" refers to the answer data submitted by users to learning problems.

[0171] "Incorrect answer" refers to answer information that has been identified as not being the correct answer.

[0172] "Analysis results" refers to the results of the analysis of the causes of incorrect answers by the generating AI.

[0173] An "emotion engine" refers to software that identifies and evaluates a user's emotional state in real time.

[0174] "Adjusting the learning environment" refers to making suggestions or changes to the learning process based on the user's emotional state and learning history.

[0175] A "communication network" refers to a network that enables the exchange of electronic information, such as the Internet.

[0176] The system for implementing this invention mainly consists of a server, a terminal, and a user. The server first receives answer information. At this time, it performs data analysis processing to identify incorrect answers using a generative AI model. As a result, the cause of the incorrect answers is clearly analyzed.

[0177] The server also uses an emotion engine to understand the user's emotional state in real time. This allows it to assess the user's current stress level and agitation level, and adjust the learning environment accordingly.

[0178] The device receives analysis results from the server and presents them to the user. The user can use this information to clearly understand their own error patterns and learning challenges. Furthermore, the device can consider the user's emotional state, detected by the emotion engine, and propose an appropriate learning strategy.

[0179] For example, if a user is solving a math problem and makes frequent mistakes, the server's emotion engine will detect feelings of frustration. In such situations, the device may suggest a break to encourage relaxation or display a link to an explanatory video to help with understanding.

[0180] The following are examples of prompts for a generative AI model.

[0181] "How would you support a user who is struggling with an elementary math problem and can't solve it?"

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] The server receives answer information submitted by the user. This answer information is the answer data to the question that the user answered. From the answer information received as input, the server performs data processing by comparing it with the correct answer in order to identify incorrect answers, and obtains an output that determines whether the answer is correct or incorrect.

[0185] Step 2:

[0186] The server analyzes the causes of incorrect answers identified using a generative AI model. This process analyzes patterns and trends in incorrect answers and outputs the reasons for the mistakes. The generative AI analyzes the incorrect answer information as input and generates analysis results that can explain the causes in natural language.

[0187] Step 3:

[0188] The server uses an emotion engine to analyze the user's emotional state in real time. It uses the user's facial expressions and behavioral data as input to identify emotional states such as stress and anxiety. The output is the user's current emotional state. This data is stored along with the analysis results.

[0189] Step 4:

[0190] The terminal presents the user with analysis results and emotional state data received from the server. This process receives analysis results and emotional state data as input and notifies the user visually or audibly. The output is to display the information in a format easily understood by the user.

[0191] Step 5:

[0192] The device suggests adjustments to the learning environment and methods based on the user's emotional state. It considers emotional data and past learning history as input, suggesting things like breaks or activities to relax. The output is effective learning suggestions for the user.

[0193] Step 6:

[0194] The user accepts suggestions from the device and adjusts the learning environment as needed. This allows the user to learn at their own pace and in a way that suits their emotional state. The device provides feedback as input, and the learning environment and strategy are adjusted as output.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] [Second Embodiment]

[0199] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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".

[0211] This learning support system uses generative AI to analyze the causes of incorrect answers in exams and supports efficient learning strategies. Specifically, three entities—the server, the terminal, and the user—work together to perform the following processes.

[0212] The server receives answer data submitted by users and identifies incorrect answers by comparing them with correct answer data. The server uses a generative AI to analyze the identified incorrect answers and identify their causes. This cause analysis includes misunderstandings of terminology, calculation errors, and lack of knowledge. Based on the analysis results, the server collects relevant supplementary information from databases and the internet.

[0213] Next, the terminal presents the user with the analysis results and collected information received from the server. This presentation is designed to allow the user to easily understand the cause of incorrect answers and includes specific supplementary explanations and additional learning materials to deepen understanding.

[0214] Users utilize the information provided through their devices to understand the causes of incorrect answers and identify areas for improvement in their next study session. This enables efficient learning even within limited timeframes, optimizing exam preparation.

[0215] For example, if a user answers a network question on an IT certification exam incorrectly, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model." Based on this, the terminal provides the user with a detailed explanation of the OSI reference model and related video links to help the user deepen their understanding.

[0216] In this way, the learning support system efficiently carries out a series of processes, from identifying the cause of incorrect answers to providing information for resolution, thereby maximizing the user's learning effectiveness.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] After the user takes the test, they enter their answer data into the input form on their device and press the submit button to send it to the server.

[0220] Step 2:

[0221] The server stores the answer data received from the user in a database and compares it with the correct answer data to identify incorrect answers.

[0222] Step 3:

[0223] The server sends the identified incorrect answers to the generating AI, which then analyzes the cause of the errors. The analysis results include factors such as insufficient understanding, lack of attention, and misreading.

[0224] Step 4:

[0225] Based on the analysis results, the server collects relevant supplementary materials and explanations from databases and the internet.

[0226] Step 5:

[0227] The terminal displays the analysis results and supplementary materials received from the server to the user. It includes explanatory text and reference links to facilitate user understanding.

[0228] Step 6:

[0229] The user uses the displayed materials to identify the cause of their incorrect answers and to study additional material as needed.

[0230] Step 7:

[0231] The server stores the analysis results and the user's learning responses in a database, which will then be used as data to support future learning.

[0232] (Example 1)

[0233] 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."

[0234] In today's educational environment, a challenge is to analyze the causes of learners' incorrect answers on exams and provide effective learning support based on those analyses. Because the causes of errors are often difficult to identify, and learners risk repeating similar mistakes, efficient instruction is essential.

[0235] 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.

[0236] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the incorrect answers using a generation AI model and identifying the causes, and means for collecting relevant information resources based on the analysis results. This makes it possible to quickly and accurately identify the causes of incorrect answers and provide learners with appropriate feedback and learning resources.

[0237] "Answer information" refers to data that describes the content of the answers that users have entered for the exam questions.

[0238] An "incorrect answer" refers to a user's answer that does not match the correct answer data when compared.

[0239] A "generative AI model" is an artificial intelligence model used to analyze data and identify the causes of incorrect answers.

[0240] "Analysis results" refer to data obtained after error analysis using a generative AI model, indicating the causes and identified problems.

[0241] "Information resources" refer to a collection of knowledge-enhancing tools, such as explanatory materials and supplementary learning materials, that are collected as needed.

[0242] "Feedback" refers to guidance information, including analysis results and additional information, provided to the user.

[0243] "Learning history" refers to the history of learning activities and answers that a user has performed in the past.

[0244] An "external database" refers to a system or location that stores information that exists on the internet or within an organization.

[0245] This learning support system utilizes three components—a server, a terminal, and a user—to improve learning efficiency. Specifically, the server receives answer information submitted by the user and compares it with its internally maintained database of correct answers. When an incorrect answer is identified, the server uses a generative AI model to analyze the cause of the error. This generative AI model utilizes artificial intelligence technology to accurately identify the cause of the error through pattern recognition of the data. After the analysis is complete, the server collects relevant information resources from an external database.

[0246] Next, the terminal presents the user with the analysis results and information resources sent from the server. This display is designed with user-friendly UI / UX to ensure easy comprehension, and the information is provided in various formats, including text, diagrams, and videos. This allows the user to understand the specific reasons for incorrect answers and to refer to supplementary materials for further learning.

[0247] As a concrete example, consider a case where a user answers a network-related question incorrectly on an information technology certification exam. In this case, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model" and collects relevant detailed explanations and video links from the internet, sending them to the user's terminal. As a result, the user can deepen their understanding of this area and achieve better results on the next exam.

[0248] An example of a prompt message might be, "Generate materials and test questions to help students who want to learn the fundamentals of information technology deepen their understanding of the OSI model." Upon receiving such a prompt message, the system provides optimal learning support.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The user enters their answers to the test questions into a terminal and sends them to the server. The entered data includes the question ID and the answer. The terminal packages this answer information into packets and forwards them to the server. The server decodes the received packets and stores the answer information in its internal database.

[0252] Step 2:

[0253] The server compares the stored answer information with the correct answer database to identify incorrect answers. In the comparison process, the question ID is used as a key to compare the correct answer with the user's answer; if they do not match, the answer is flagged as incorrect. The incorrect answer data includes the question ID and the content of the incorrect answer. This comparison result is then entered into the next processing step.

[0254] Step 3:

[0255] The server passes the incorrect answers as input to the AI ​​model that generates them, and the AI ​​model begins its root cause analysis. The AI ​​model uses prompts to analyze patterns in the incorrect answers and identifies the causes of the errors. The output generated here is detailed attribute information indicating the cause of the incorrect answers. For example, "misunderstanding of concepts" or "lack of terminology" may be identified.

[0256] Step 4:

[0257] Based on the outputted reasons for incorrect answers, the server collects relevant information resources from external databases and the internet. This collection process uses keywords to search for appropriate materials and video links. The collected output data is diverse, including explanatory text, related links, and visual materials.

[0258] Step 5:

[0259] The terminal presents the user with analysis results and information resources received from the server. The terminal's UI is designed to display the information in a user-friendly format. The user can review this display and, if necessary, access supplementary materials to deepen their understanding. This output includes points for improving the user's learning process.

[0260] Step 6:

[0261] Based on the information provided through the device, users understand the detailed reasons for incorrect answers and adjust their learning accordingly. When users provide feedback, that data is returned to the server and saved for future system improvements and as part of the user's learning history. The feedback information, as output, enriches the next cycle and plays a role in improving learning outcomes.

[0262] (Application Example 1)

[0263] 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."

[0264] In recent years, users have sometimes made incorrect transaction behaviors in electronic payment settings, creating a need for means to identify the causes and provide corrective measures. Current systems lack sufficient feedback based on users' past behavioral history, making it difficult to prevent the recurrence of incorrect behavior.

[0265] 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.

[0266] In this invention, the server includes means for receiving answer data and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for analyzing the user's behavior history and identifying the cause of erroneous transaction behavior. This makes it possible to identify the cause when a user engages in erroneous transaction behavior and provide appropriate feedback.

[0267] "Answer data" refers to the answers provided by users, and is the basis for identifying incorrect answers.

[0268] An "incorrect answer" is a response that does not match the correct answer data and is therefore identified as an error.

[0269] "Cause analysis" is the process of analyzing the background and reasons for incorrect answers using generative AI.

[0270] "Response information" refers to supplementary materials and advice collected based on identified causes, which contribute to improving erroneous trading behavior.

[0271] "User activity history" refers to records of transactions and activities that users have performed in the past, and is data used to analyze the causes of incorrect answers.

[0272] "Feedback" refers to information provided to users regarding analysis results and improvement measures, intended to encourage them to reconsider their actions.

[0273] The system that realizes this invention mainly consists of three elements: a server, a terminal, and a user. The server receives answer data transmitted from the user and compares it with correct answer data stored in a database to identify incorrect answers. In this process, a generative AI model is used to analyze the incorrect answers and identify the causes related to the incorrect answers. Based on the identified causes, relevant corresponding information is collected from the database and external information sources.

[0274] The terminal displays analysis results and related information sent from the server in a way that is easy for the user to understand. Specifically, it provides intuitive feedback to the user using a user-friendly interface. It also includes a function to provide related explanatory materials and supplementary materials to further promote understanding.

[0275] Through this system, users can receive feedback on their incorrect transaction behavior. For example, if they have made purchases that exceeded their budget in the past, the system may analyze the cause as "insufficient planning" and send a prompt advising them to use a budget management tool. This prompt might say something like, "Your current spending exceeds your budget. Use a budget management tool to plan for future purchases."

[0276] This system utilizes Google Cloud's AI platform to run generative AI models, and programming is implemented using Python. Furthermore, frameworks such as Django are used for the user interface design. The goal of this configuration is to help users correct their incorrect behaviors and make appropriate payment decisions.

[0277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0278] Step 1:

[0279] The server receives answer data from users. It identifies incorrect answers by comparing the received data with a database. In this process, it compares the input answer data with the correct answer data and generates a list of incorrect answers as output.

[0280] Step 2:

[0281] The server uses a generative AI model to analyze the identified incorrect answers. The AI ​​is fed the specific content of the incorrect answers as input, and through data processing, it identifies the cause of the error and generates an analysis of the cause as output. Specific examples, such as calculation errors or lack of knowledge, are also presented.

[0282] Step 3:

[0283] The server collects relevant response information from a database or an external source based on the analysis results. In this process, relevant information regarding the cause of incorrect answers is retrieved from the Internet, and the information collected as output is refined.

[0284] Step 4:

[0285] The terminal presents the analysis results and response information sent from the server to the user. The input is the analysis data received from the server, which is visually displayed through the user interface. As a specific operation, links to additional teaching materials and explanatory videos are also provided as needed.

[0286] Step 5:

[0287] Based on the information displayed on the terminal, the user understands the cause of the incorrect answer and confirms improvement measures for future payment actions. As output, specific improvement points for the next transaction can be considered. This enables the user to review their actions and prepare for appropriate payment.

[0288] Step 6:

[0289] The server accumulates the analysis results and the provided feedback, and further uses them for the analysis and proposal of future user actions. The database records past incorrect answers and feedback, enabling the system to output improved accuracy for new inputs.

[0290] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0291] The present invention is a learning support system that uses an emotion engine in combination, and realizes efficient and effective learning by analyzing incorrect answers by generative AI and recognizing the user's emotion. The system mainly consists of a server, a terminal, and a user.

[0292] The server identifies incorrect answers based on the answer data received from the user and analyzes the cause using a generation AI. Furthermore, it uses an emotion engine to grasp the user's emotional state in real time and analyzes the learning characteristics of each individual user by comparing it with the accumulated learning history.

[0293] The terminal not only presents the user with analysis results from the server and collected related materials, but also provides learning suggestions and environmental adjustments based on the user's emotional state detected by the emotion engine. For example, if the user is experiencing high stress levels, it can suggest taking a break.

[0294] This system allows users to not only clearly understand the causes of their incorrect answers, but also to adjust their learning strategy and pace according to their emotional state. For example, if a user frequently makes incorrect answers about networks during a mock IT certification exam, the system, upon detecting feelings of "anxiety," will recommend setting up a relaxing learning environment and provide time to watch relevant explanatory videos to help deepen their understanding.

[0295] This enables a system that provides effective learning support through collaboration between the server, terminal, and user, maximizing the user's learning effectiveness.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] Users take a practice test on their device, input their answers, and send them to the server.

[0299] Step 2:

[0300] The server compares the received answer data with the model answer to identify incorrect answers.

[0301] Step 3:

[0302] The server analyzes the cause of the identified incorrect answer using the generative AI. The analysis content includes lack of knowledge, misunderstanding of the problem, calculation errors, etc.

[0303] Step 4:

[0304] Based on the analysis results, the server automatically collects relevant explanatory materials and supplementary information from the database and the Internet.

[0305] Step 5:

[0306] The emotion engine obtains emotion data from the user's terminal and analyzes the user's emotional state in real time. The analysis uses the user's expression, voice tone, input speed, etc.

[0307] Step 6:

[0308] The terminal displays the analysis results and the collected materials from the server, and presents the optimal learning suggestions to the user based on the results of the emotion engine. For example, when a stressed state is recognized, suggestions on relaxation methods are provided.

[0309] Step 7:

[0310] The user adjusts the learning pace based on the displayed suggestions and conducts activities to improve the emotional state if necessary.

[0311] Step 8:

[0312] The server accumulates the analysis results and the changes in the user's emotional state in the database and uses them as data for future learning support.

[0313] (Example 2)

[0314] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] Modern learning support systems face challenges in accurately identifying the causes of user errors and suggesting appropriate learning strategies. Furthermore, a lack of means to adjust the learning environment to optimize performance based on the user's emotional state prevents the learning effect from being maximized. This can lead to decreased user motivation and difficulty in sustained learning.

[0316] 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.

[0317] In this invention, the server includes means for acquiring answer data and identifying incorrect answers, means for analyzing the causes of incorrect answers and aggregating related information, and means for detecting the user's emotional state in real time and proposing adjustments to the learning environment based on that information. This allows the user to clearly understand the causes of their errors and implement effective learning strategies that match their emotional state.

[0318] "Answer data" refers to information about the questions that users have answered and the content of those answers.

[0319] "Means for identifying incorrect answers" refers to methods or devices that analyze user response data and identify incorrect answers by comparing them with correct answers.

[0320] "Means for analyzing causes and aggregating related information" refers to methods and techniques for identifying the causes of incorrect answers and for comprehensively collecting and organizing knowledge and information related to those causes.

[0321] "Means of providing information to the user" refers to methods or devices for presenting analysis results and aggregated information to the user visually or audibly.

[0322] "Means of real-time detection" refers to methods and technologies for monitoring and detecting a user's emotional state in real time.

[0323] "Means of suggesting adjustments to the learning environment" refers to methods and technologies that suggest adjusting the environment and methods to improve learning efficiency based on the detected emotional state of the user.

[0324] A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and perform specific tasks.

[0325] A "prompt statement" refers to a sentence that serves as a command or question input to a generative AI model, and is used to guide the model's output.

[0326] This invention is a system for supporting user learning, consisting of a server, a terminal, and user participation. The server receives answer data and processes it to identify incorrect answers. This involves database and statistical analysis techniques, and the specific software used is a general database management system and data analysis tools. The server also uses a generative AI model to analyze the causes of incorrect answers and aggregate relevant information. In this process, a generative AI model utilizing natural language processing technology is used, and the AI ​​model is envisioned as a generalized "natural language generation engine."

[0327] The server utilizes sentiment analysis technology to detect the user's real-time emotional state. This sentiment analysis includes technologies such as voice analysis and facial recognition, and is implemented via an API-based general-purpose sentiment analysis engine. Based on this information, it is possible to provide more personalized learning suggestions.

[0328] The terminal presents the analysis results from the server to the user, providing information in a format that is easy for the user to understand. It also has a function to make learning suggestions tailored to the emotional environment and adjust the environment to enhance learning effectiveness. For example, if the terminal detects that the user is feeling stressed, it will display a message such as, "If you are losing focus, take a short break to refresh yourself."

[0329] By using the system, users can comprehensively understand their learning progress and adjust their learning strategy and pace as needed. For example, a user can input a prompt into the system such as, "Please recommend video materials to help me understand network-related questions that I got wrong frequently in recent practice tests. I'm feeling nervous right now," and receive appropriate information to proceed with their studies.

[0330] In this way, the server, terminal, and user work together as a unified team to achieve efficient and effective learning support.

[0331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0332] Step 1:

[0333] The server receives answer data sent from the user via the terminal. It receives the problem identification information and the user's answer as input and stores this in the database. Next, it compares the incorrect answers with the correct answer data to identify them. Here, an algorithm is used to calculate the accuracy rate and output the locations of the user's incorrect answers. Specifically, the server executes database queries and analyzes the obtained data.

[0334] Step 2:

[0335] The server uses a generative AI model to analyze the causes of incorrect answers. The input consists of identified incorrect answer data and information about the problems associated with those incorrect answers. The generative AI model uses natural language processing to analyze the knowledge errors and misunderstandings underlying the incorrect answers. This process outputs the causes of the incorrect answers as analysis results. Specifically, the server creates prompts for the generative AI model and records the model's responses as analysis results.

[0336] Step 3:

[0337] The server activates an emotion engine to detect the user's emotional state in real time. Inputs include user voice data and webcam images. Based on this data, the server analyzes the emotional state and outputs emotional evaluations such as stress levels and concentration levels. Specifically, the server uses voice analysis APIs and facial recognition software to analyze the data and estimate the emotional state.

[0338] Step 4:

[0339] The terminal provides the user with analysis results sent from the server. Input data includes the causes of incorrect answers, related information, and emotional state assessments. Based on this, the terminal visually displays information to the user and outputs suggestions for learning strategies and environment adjustments. Specifically, the terminal displays information in graph and text formats and uses an interactive user interface as needed.

[0340] Step 5:

[0341] Users adjust their learning methods based on the information displayed on their device. They receive suggested information from the server as input and revise their learning plan. Specifically, users can refer to recommended learning materials and follow the provided break advice. As a result, improved learning efficiency and deeper understanding can be expected.

[0342] (Application Example 2)

[0343] 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."

[0344] In today's learning environment, there is a need for systems that not only identify incorrect answers but also analyze their causes and provide learning suggestions that take into account the user's emotional state, enabling learners to learn effectively while reducing stress. However, conventional learning support systems have been unable to provide real-time feedback or adjust the learning environment while considering the user's emotional state.

[0345] 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.

[0346] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for understanding the user's emotional state using an emotion engine and adjusting the learning environment. This enables learning suggestions and environment adjustments based on the user's emotions.

[0347] "Answer information" refers to the answer data submitted by users to learning problems.

[0348] "Incorrect answer" refers to answer information that has been identified as not being the correct answer.

[0349] "Analysis results" refers to the results of the analysis of the causes of incorrect answers by the generating AI.

[0350] An "emotion engine" refers to software that identifies and evaluates a user's emotional state in real time.

[0351] "Adjusting the learning environment" refers to making suggestions or changes to the learning process based on the user's emotional state and learning history.

[0352] A "communication network" refers to a network that enables the exchange of electronic information, such as the Internet.

[0353] The system for implementing this invention mainly consists of a server, a terminal, and a user. The server first receives answer information. At this time, it performs data analysis processing to identify incorrect answers using a generative AI model. As a result, the cause of the incorrect answers is clearly analyzed.

[0354] The server also uses an emotion engine to understand the user's emotional state in real time. This allows it to assess the user's current stress level and agitation level, and adjust the learning environment accordingly.

[0355] The device receives analysis results from the server and presents them to the user. The user can use this information to clearly understand their own error patterns and learning challenges. Furthermore, the device can consider the user's emotional state, detected by the emotion engine, and propose an appropriate learning strategy.

[0356] For example, if a user is solving a math problem and makes frequent mistakes, the server's emotion engine will detect feelings of frustration. In such situations, the device may suggest a break to encourage relaxation or display a link to an explanatory video to help with understanding.

[0357] The following are examples of prompts for a generative AI model.

[0358] "How would you support a user who is struggling with an elementary math problem and can't solve it?"

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The server receives answer information submitted by the user. This answer information is the answer data to the question that the user answered. From the answer information received as input, the server performs data processing by comparing it with the correct answer in order to identify incorrect answers, and obtains an output that determines whether the answer is correct or incorrect.

[0362] Step 2:

[0363] The server analyzes the causes of incorrect answers identified using a generative AI model. This process analyzes patterns and trends in incorrect answers and outputs the reasons for the mistakes. The generative AI analyzes the incorrect answer information as input and generates analysis results that can explain the causes in natural language.

[0364] Step 3:

[0365] The server uses an emotion engine to analyze the user's emotional state in real time. It uses the user's facial expressions and behavioral data as input to identify emotional states such as stress and anxiety. The output is the user's current emotional state. This data is stored along with the analysis results.

[0366] Step 4:

[0367] The terminal presents the user with analysis results and emotional state data received from the server. This process receives analysis results and emotional state data as input and notifies the user visually or audibly. The output is to display the information in a format easily understood by the user.

[0368] Step 5:

[0369] The device suggests adjustments to the learning environment and methods based on the user's emotional state. It considers emotional data and past learning history as input, suggesting things like breaks or activities to relax. The output is effective learning suggestions for the user.

[0370] Step 6:

[0371] The user accepts suggestions from the device and adjusts the learning environment as needed. This allows the user to learn at their own pace and in a way that suits their emotional state. The device provides feedback as input, and the learning environment and strategy are adjusted as output.

[0372] 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.

[0373] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0374] 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.

[0375] [Third Embodiment]

[0376] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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).

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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".

[0388] This learning support system uses generative AI to analyze the causes of incorrect answers in exams and supports efficient learning strategies. Specifically, three entities—the server, the terminal, and the user—work together to perform the following processes.

[0389] The server receives answer data submitted by users and identifies incorrect answers by comparing them with correct answer data. The server uses a generative AI to analyze the identified incorrect answers and identify their causes. This cause analysis includes misunderstandings of terminology, calculation errors, and lack of knowledge. Based on the analysis results, the server collects relevant supplementary information from databases and the internet.

[0390] Next, the terminal presents the user with the analysis results and collected information received from the server. This presentation is designed to allow the user to easily understand the cause of incorrect answers and includes specific supplementary explanations and additional learning materials to deepen understanding.

[0391] Users utilize the information provided through their devices to understand the causes of incorrect answers and identify areas for improvement in their next study session. This enables efficient learning even within limited timeframes, optimizing exam preparation.

[0392] For example, if a user answers a network question on an IT certification exam incorrectly, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model." Based on this, the terminal provides the user with a detailed explanation of the OSI reference model and related video links to help the user deepen their understanding.

[0393] In this way, the learning support system efficiently carries out a series of processes, from identifying the cause of incorrect answers to providing information for resolution, thereby maximizing the user's learning effectiveness.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] After the user takes the test, they enter their answer data into the input form on their device and press the submit button to send it to the server.

[0397] Step 2:

[0398] The server stores the answer data received from the user in a database and compares it with the correct answer data to identify incorrect answers.

[0399] Step 3:

[0400] The server sends the identified incorrect answers to the generating AI, which then analyzes the cause of the errors. The analysis results include factors such as insufficient understanding, lack of attention, and misreading.

[0401] Step 4:

[0402] Based on the analysis results, the server collects relevant supplementary materials and explanations from databases and the internet.

[0403] Step 5:

[0404] The terminal displays the analysis results and supplementary materials received from the server to the user. It includes explanatory text and reference links to facilitate user understanding.

[0405] Step 6:

[0406] The user uses the displayed materials to identify the cause of their incorrect answers and to study additional material as needed.

[0407] Step 7:

[0408] The server stores the analysis results and the user's learning responses in a database, which will then be used as data to support future learning.

[0409] (Example 1)

[0410] 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."

[0411] In today's educational environment, a challenge is to analyze the causes of learners' incorrect answers on exams and provide effective learning support based on those analyses. Because the causes of errors are often difficult to identify, and learners risk repeating similar mistakes, efficient instruction is essential.

[0412] 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.

[0413] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the incorrect answers using a generation AI model and identifying the causes, and means for collecting relevant information resources based on the analysis results. This makes it possible to quickly and accurately identify the causes of incorrect answers and provide learners with appropriate feedback and learning resources.

[0414] "Answer information" refers to data that describes the content of the answers that users have entered for the exam questions.

[0415] An "incorrect answer" refers to a user's answer that does not match the correct answer data when compared.

[0416] A "generative AI model" is an artificial intelligence model used to analyze data and identify the causes of incorrect answers.

[0417] "Analysis results" refer to data obtained after error analysis using a generative AI model, indicating the causes and identified problems.

[0418] "Information resources" refer to a collection of knowledge-enhancing tools, such as explanatory materials and supplementary learning materials, that are collected as needed.

[0419] "Feedback" refers to guidance information, including analysis results and additional information, provided to the user.

[0420] "Learning history" refers to the history of learning activities and answers that a user has performed in the past.

[0421] An "external database" refers to a system or location that stores information that exists on the internet or within an organization.

[0422] This learning support system utilizes three components—a server, a terminal, and a user—to improve learning efficiency. Specifically, the server receives answer information submitted by the user and compares it with its internally maintained database of correct answers. When an incorrect answer is identified, the server uses a generative AI model to analyze the cause of the error. This generative AI model utilizes artificial intelligence technology to accurately identify the cause of the error through pattern recognition of the data. After the analysis is complete, the server collects relevant information resources from an external database.

[0423] Next, the terminal presents the user with the analysis results and information resources sent from the server. This display is designed with user-friendly UI / UX to ensure easy comprehension, and the information is provided in various formats, including text, diagrams, and videos. This allows the user to understand the specific reasons for incorrect answers and to refer to supplementary materials for further learning.

[0424] As a concrete example, consider a case where a user answers a network-related question incorrectly on an information technology certification exam. In this case, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model" and collects relevant detailed explanations and video links from the internet, sending them to the user's terminal. As a result, the user can deepen their understanding of this area and achieve better results on the next exam.

[0425] An example of a prompt message might be, "Generate materials and test questions to help students who want to learn the fundamentals of information technology deepen their understanding of the OSI model." Upon receiving such a prompt message, the system provides optimal learning support.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The user enters their answers to the test questions into a terminal and sends them to the server. The entered data includes the question ID and the answer. The terminal packages this answer information into packets and forwards them to the server. The server decodes the received packets and stores the answer information in its internal database.

[0429] Step 2:

[0430] The server compares the stored answer information with the correct answer database to identify incorrect answers. In the comparison process, the question ID is used as a key to compare the correct answer with the user's answer; if they do not match, the answer is flagged as incorrect. The incorrect answer data includes the question ID and the content of the incorrect answer. This comparison result is then entered into the next processing step.

[0431] Step 3:

[0432] The server passes the incorrect answers as input to the AI ​​model that generates them, and the AI ​​model begins its root cause analysis. The AI ​​model uses prompts to analyze patterns in the incorrect answers and identifies the causes of the errors. The output generated here is detailed attribute information indicating the cause of the incorrect answers. For example, "misunderstanding of concepts" or "lack of terminology" may be identified.

[0433] Step 4:

[0434] Based on the outputted reasons for incorrect answers, the server collects relevant information resources from external databases and the internet. This collection process uses keywords to search for appropriate materials and video links. The collected output data is diverse, including explanatory text, related links, and visual materials.

[0435] Step 5:

[0436] The terminal presents the user with analysis results and information resources received from the server. The terminal's UI is designed to display the information in a user-friendly format. The user can review this display and, if necessary, access supplementary materials to deepen their understanding. This output includes points for improving the user's learning process.

[0437] Step 6:

[0438] Based on the information provided through the device, users understand the detailed reasons for incorrect answers and adjust their learning accordingly. When users provide feedback, that data is returned to the server and saved for future system improvements and as part of the user's learning history. The feedback information, as output, enriches the next cycle and plays a role in improving learning outcomes.

[0439] (Application Example 1)

[0440] 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."

[0441] In recent years, users have sometimes made incorrect transaction behaviors in electronic payment settings, creating a need for means to identify the causes and provide corrective measures. Current systems lack sufficient feedback based on users' past behavioral history, making it difficult to prevent the recurrence of incorrect behavior.

[0442] 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.

[0443] In this invention, the server includes means for receiving answer data and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for analyzing the user's behavior history and identifying the cause of erroneous transaction behavior. This makes it possible to identify the cause when a user engages in erroneous transaction behavior and provide appropriate feedback.

[0444] "Answer data" refers to the answers provided by users, and is the basis for identifying incorrect answers.

[0445] An "incorrect answer" is a response that does not match the correct answer data and is therefore identified as an error.

[0446] "Cause analysis" is the process of analyzing the background and reasons for incorrect answers using generative AI.

[0447] "Response information" refers to supplementary materials and advice collected based on identified causes, which contribute to improving erroneous trading behavior.

[0448] "User activity history" refers to records of transactions and activities that users have performed in the past, and is data used to analyze the causes of incorrect answers.

[0449] "Feedback" refers to information provided to users regarding analysis results and improvement measures, intended to encourage them to reconsider their actions.

[0450] The system that realizes this invention mainly consists of three elements: a server, a terminal, and a user. The server receives answer data transmitted from the user and compares it with correct answer data stored in a database to identify incorrect answers. In this process, a generative AI model is used to analyze the incorrect answers and identify the causes related to the incorrect answers. Based on the identified causes, relevant corresponding information is collected from the database and external information sources.

[0451] The terminal displays analysis results and related information sent from the server in a way that is easy for the user to understand. Specifically, it provides intuitive feedback to the user using a user-friendly interface. It also includes a function to provide related explanatory materials and supplementary materials to further promote understanding.

[0452] Through this system, users can receive feedback on their incorrect transaction behavior. For example, if they have made purchases that exceeded their budget in the past, the system may analyze the cause as "insufficient planning" and send a prompt advising them to use a budget management tool. This prompt might say something like, "Your current spending exceeds your budget. Use a budget management tool to plan for future purchases."

[0453] This system utilizes Google Cloud's AI platform to run generative AI models, and programming is implemented using Python. Furthermore, frameworks such as Django are used for the user interface design. The goal of this configuration is to help users correct their incorrect behaviors and make appropriate payment decisions.

[0454] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0455] Step 1:

[0456] The server receives answer data from users. It identifies incorrect answers by comparing the received data with a database. In this process, it compares the input answer data with the correct answer data and generates a list of incorrect answers as output.

[0457] Step 2:

[0458] The server uses a generative AI model to analyze the identified incorrect answers. The AI ​​is fed the specific content of the incorrect answers as input, and through data processing, it identifies the cause of the error and generates an analysis of the cause as output. Specific examples, such as calculation errors or lack of knowledge, are also presented.

[0459] Step 3:

[0460] The server collects relevant correspondence information from a database or external sources based on the analysis results. This process searches the internet for relevant information regarding the causes of incorrect answers and organizes the collected information as output.

[0461] Step 4:

[0462] The terminal displays analysis results and corresponding information sent from the server to the user. The input is the analysis data received from the server, which is displayed visually through the user interface. Specifically, links to additional learning materials and explanatory videos are provided as needed.

[0463] Step 5:

[0464] Based on the information displayed on the terminal, users can understand the cause of their incorrect answers and identify areas for improvement in their future payment behavior. The output may include specific points for improvement in their next transaction. This allows users to review their actions and prepare themselves for making appropriate payments.

[0465] Step 6:

[0466] The server stores analysis results and feedback provided, which are then used to analyze and suggest future user behavior. The database records past incorrect answers and feedback, enabling the system to produce more accurate output for new inputs.

[0467] 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.

[0468] This invention is a learning support system that utilizes an emotion engine, achieving efficient and effective learning through error analysis by generating AI and recognition of the user's emotions. The system mainly consists of a server, terminals, and users.

[0469] The server identifies incorrect answers based on the answer data received from the user and analyzes the cause using a generation AI. Furthermore, it uses an emotion engine to grasp the user's emotional state in real time and analyzes the learning characteristics of each individual user by comparing it with the accumulated learning history.

[0470] The terminal not only presents the user with analysis results from the server and collected related materials, but also provides learning suggestions and environmental adjustments based on the user's emotional state detected by the emotion engine. For example, if the user is experiencing high stress levels, it can suggest taking a break.

[0471] This system allows users to not only clearly understand the causes of their incorrect answers, but also to adjust their learning strategy and pace according to their emotional state. For example, if a user frequently makes incorrect answers about networks during a mock IT certification exam, the system, upon detecting feelings of "anxiety," will recommend setting up a relaxing learning environment and provide time to watch relevant explanatory videos to help deepen their understanding.

[0472] This enables a system that provides effective learning support through collaboration between the server, terminal, and user, maximizing the user's learning effectiveness.

[0473] The following describes the processing flow.

[0474] Step 1:

[0475] Users take a practice test on their device, input their answers, and send them to the server.

[0476] Step 2:

[0477] The server compares the received answer data with the model answer to identify incorrect answers.

[0478] Step 3:

[0479] The server uses a generation AI to analyze the cause of the identified incorrect answers. The analysis includes factors such as lack of knowledge, misunderstanding of the problem, and calculation errors.

[0480] Step 4:

[0481] Based on the analysis results, the server automatically collects relevant explanatory materials and supplementary information from databases and the internet.

[0482] Step 5:

[0483] The emotion engine acquires emotional data from the user's device and analyzes the user's emotional state in real time. The analysis utilizes the user's facial expressions, voice tone, input speed, and other factors.

[0484] Step 6:

[0485] The terminal displays analysis results and collected data from the server and presents the user with optimal learning suggestions based on the results of the emotion engine. For example, if a stressful state is detected, it will suggest relaxation techniques.

[0486] Step 7:

[0487] Based on the displayed suggestions, users adjust their learning pace and, if necessary, engage in activities to improve their emotional state.

[0488] Step 8:

[0489] The server stores the analysis results and changes in the user's emotional state in a database, which will be used as data to support future learning.

[0490] (Example 2)

[0491] 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."

[0492] Modern learning support systems face challenges in accurately identifying the causes of user errors and suggesting appropriate learning strategies. Furthermore, a lack of means to adjust the learning environment to optimize performance based on the user's emotional state prevents the learning effect from being maximized. This can lead to decreased user motivation and difficulty in sustained learning.

[0493] 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.

[0494] In this invention, the server includes means for acquiring answer data and identifying incorrect answers, means for analyzing the causes of incorrect answers and aggregating related information, and means for detecting the user's emotional state in real time and proposing adjustments to the learning environment based on that information. This allows the user to clearly understand the causes of their errors and implement effective learning strategies that match their emotional state.

[0495] "Answer data" refers to information about the questions that users have answered and the content of those answers.

[0496] "Means for identifying incorrect answers" refers to methods or devices that analyze user response data and identify incorrect answers by comparing them with correct answers.

[0497] "Means for analyzing causes and aggregating related information" refers to methods and techniques for identifying the causes of incorrect answers and for comprehensively collecting and organizing knowledge and information related to those causes.

[0498] "Means of providing information to the user" refers to methods or devices for presenting analysis results and aggregated information to the user visually or audibly.

[0499] "Means of real-time detection" refers to methods and technologies for monitoring and detecting a user's emotional state in real time.

[0500] "Means of suggesting adjustments to the learning environment" refers to methods and technologies that suggest adjusting the environment and methods to improve learning efficiency based on the detected emotional state of the user.

[0501] A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and perform specific tasks.

[0502] A "prompt statement" refers to a sentence that serves as a command or question input to a generative AI model, and is used to guide the model's output.

[0503] This invention is a system for supporting user learning, consisting of a server, a terminal, and user participation. The server receives answer data and processes it to identify incorrect answers. This involves database and statistical analysis techniques, and the specific software used is a general database management system and data analysis tools. The server also uses a generative AI model to analyze the causes of incorrect answers and aggregate relevant information. In this process, a generative AI model utilizing natural language processing technology is used, and the AI ​​model is envisioned as a generalized "natural language generation engine."

[0504] The server utilizes sentiment analysis technology to detect the user's real-time emotional state. This sentiment analysis includes technologies such as voice analysis and facial recognition, and is implemented via an API-based general-purpose sentiment analysis engine. Based on this information, it is possible to provide more personalized learning suggestions.

[0505] The terminal presents the analysis results from the server to the user, providing information in a format that is easy for the user to understand. It also has a function to make learning suggestions tailored to the emotional environment and adjust the environment to enhance learning effectiveness. For example, if the terminal detects that the user is feeling stressed, it will display a message such as, "If you are losing focus, take a short break to refresh yourself."

[0506] By using the system, users can comprehensively understand their learning progress and adjust their learning strategy and pace as needed. For example, a user can input a prompt into the system such as, "Please recommend video materials to help me understand network-related questions that I got wrong frequently in recent practice tests. I'm feeling nervous right now," and receive appropriate information to proceed with their studies.

[0507] In this way, the server, terminal, and user work together as a unified team to achieve efficient and effective learning support.

[0508] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0509] Step 1:

[0510] The server receives answer data sent from the user via the terminal. It receives the problem identification information and the user's answer as input and stores this in the database. Next, it compares the incorrect answers with the correct answer data to identify them. Here, an algorithm is used to calculate the accuracy rate and output the locations of the user's incorrect answers. Specifically, the server executes database queries and analyzes the obtained data.

[0511] Step 2:

[0512] The server uses a generative AI model to analyze the causes of incorrect answers. The input consists of identified incorrect answer data and information about the problems associated with those incorrect answers. The generative AI model uses natural language processing to analyze the knowledge errors and misunderstandings underlying the incorrect answers. This process outputs the causes of the incorrect answers as analysis results. Specifically, the server creates prompts for the generative AI model and records the model's responses as analysis results.

[0513] Step 3:

[0514] The server activates an emotion engine to detect the user's emotional state in real time. Inputs include user voice data and webcam images. Based on this data, the server analyzes the emotional state and outputs emotional evaluations such as stress levels and concentration levels. Specifically, the server uses voice analysis APIs and facial recognition software to analyze the data and estimate the emotional state.

[0515] Step 4:

[0516] The terminal provides the user with analysis results sent from the server. Input data includes the causes of incorrect answers, related information, and emotional state assessments. Based on this, the terminal visually displays information to the user and outputs suggestions for learning strategies and environment adjustments. Specifically, the terminal displays information in graph and text formats and uses an interactive user interface as needed.

[0517] Step 5:

[0518] Users adjust their learning methods based on the information displayed on their device. They receive suggested information from the server as input and revise their learning plan. Specifically, users can refer to recommended learning materials and follow the provided break advice. As a result, improved learning efficiency and deeper understanding can be expected.

[0519] (Application Example 2)

[0520] 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."

[0521] In today's learning environment, there is a need for systems that not only identify incorrect answers but also analyze their causes and provide learning suggestions that take into account the user's emotional state, enabling learners to learn effectively while reducing stress. However, conventional learning support systems have been unable to provide real-time feedback or adjust the learning environment while considering the user's emotional state.

[0522] 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.

[0523] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for understanding the user's emotional state using an emotion engine and adjusting the learning environment. This enables learning suggestions and environment adjustments based on the user's emotions.

[0524] "Answer information" refers to the answer data submitted by users to learning problems.

[0525] "Incorrect answer" refers to answer information that has been identified as not being the correct answer.

[0526] "Analysis results" refers to the results of the analysis of the causes of incorrect answers by the generating AI.

[0527] An "emotion engine" refers to software that identifies and evaluates a user's emotional state in real time.

[0528] "Adjusting the learning environment" refers to making suggestions or changes to the learning process based on the user's emotional state and learning history.

[0529] A "communication network" refers to a network that enables the exchange of electronic information, such as the Internet.

[0530] The system for implementing this invention mainly consists of a server, a terminal, and a user. The server first receives answer information. At this time, it performs data analysis processing to identify incorrect answers using a generative AI model. As a result, the cause of the incorrect answers is clearly analyzed.

[0531] The server also uses an emotion engine to understand the user's emotional state in real time. This allows it to assess the user's current stress level and agitation level, and adjust the learning environment accordingly.

[0532] The device receives analysis results from the server and presents them to the user. The user can use this information to clearly understand their own error patterns and learning challenges. Furthermore, the device can consider the user's emotional state, detected by the emotion engine, and propose an appropriate learning strategy.

[0533] For example, if a user is solving a math problem and makes frequent mistakes, the server's emotion engine will detect feelings of frustration. In such situations, the device may suggest a break to encourage relaxation or display a link to an explanatory video to help with understanding.

[0534] The following are examples of prompts for a generative AI model.

[0535] "How would you support a user who is struggling with an elementary math problem and can't solve it?"

[0536] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0537] Step 1:

[0538] The server receives answer information submitted by the user. This answer information is the answer data to the question that the user answered. From the answer information received as input, the server performs data processing by comparing it with the correct answer in order to identify incorrect answers, and obtains an output that determines whether the answer is correct or incorrect.

[0539] Step 2:

[0540] The server analyzes the causes of incorrect answers identified using a generative AI model. This process analyzes patterns and trends in incorrect answers and outputs the reasons for the mistakes. The generative AI analyzes the incorrect answer information as input and generates analysis results that can explain the causes in natural language.

[0541] Step 3:

[0542] The server uses an emotion engine to analyze the user's emotional state in real time. It uses the user's facial expressions and behavioral data as input to identify emotional states such as stress and anxiety. The output is the user's current emotional state. This data is stored along with the analysis results.

[0543] Step 4:

[0544] The terminal presents the user with analysis results and emotional state data received from the server. This process receives analysis results and emotional state data as input and notifies the user visually or audibly. The output is to display the information in a format easily understood by the user.

[0545] Step 5:

[0546] The device suggests adjustments to the learning environment and methods based on the user's emotional state. It considers emotional data and past learning history as input, suggesting things like breaks or activities to relax. The output is effective learning suggestions for the user.

[0547] Step 6:

[0548] The user accepts suggestions from the device and adjusts the learning environment as needed. This allows the user to learn at their own pace and in a way that suits their emotional state. The device provides feedback as input, and the learning environment and strategy are adjusted as output.

[0549] 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.

[0550] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0551] 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.

[0552] [Fourth Embodiment]

[0553] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0554] 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.

[0555] 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).

[0556] 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.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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".

[0566] This learning support system uses generative AI to analyze the causes of incorrect answers in exams and supports efficient learning strategies. Specifically, three entities—the server, the terminal, and the user—work together to perform the following processes.

[0567] The server receives answer data submitted by users and identifies incorrect answers by comparing them with correct answer data. The server uses a generative AI to analyze the identified incorrect answers and identify their causes. This cause analysis includes misunderstandings of terminology, calculation errors, and lack of knowledge. Based on the analysis results, the server collects relevant supplementary information from databases and the internet.

[0568] Next, the terminal presents the user with the analysis results and collected information received from the server. This presentation is designed to allow the user to easily understand the cause of incorrect answers and includes specific supplementary explanations and additional learning materials to deepen understanding.

[0569] Users utilize the information provided through their devices to understand the causes of incorrect answers and identify areas for improvement in their next study session. This enables efficient learning even within limited timeframes, optimizing exam preparation.

[0570] For example, if a user answers a network question on an IT certification exam incorrectly, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model." Based on this, the terminal provides the user with a detailed explanation of the OSI reference model and related video links to help the user deepen their understanding.

[0571] In this way, the learning support system efficiently carries out a series of processes, from identifying the cause of incorrect answers to providing information for resolution, thereby maximizing the user's learning effectiveness.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] After the user takes the test, they enter their answer data into the input form on their device and press the submit button to send it to the server.

[0575] Step 2:

[0576] The server stores the answer data received from the user in a database and compares it with the correct answer data to identify incorrect answers.

[0577] Step 3:

[0578] The server sends the identified incorrect answers to the generating AI, which then analyzes the cause of the errors. The analysis results include factors such as insufficient understanding, lack of attention, and misreading.

[0579] Step 4:

[0580] Based on the analysis results, the server collects relevant supplementary materials and explanations from databases and the internet.

[0581] Step 5:

[0582] The terminal displays the analysis results and supplementary materials received from the server to the user. It includes explanatory text and reference links to facilitate user understanding.

[0583] Step 6:

[0584] The user uses the displayed materials to identify the cause of their incorrect answers and to study additional material as needed.

[0585] Step 7:

[0586] The server stores the analysis results and the user's learning responses in a database, which will then be used as data to support future learning.

[0587] (Example 1)

[0588] 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".

[0589] In today's educational environment, a challenge is to analyze the causes of learners' incorrect answers on exams and provide effective learning support based on those analyses. Because the causes of errors are often difficult to identify, and learners risk repeating similar mistakes, efficient instruction is essential.

[0590] 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.

[0591] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the incorrect answers using a generation AI model and identifying the causes, and means for collecting relevant information resources based on the analysis results. This makes it possible to quickly and accurately identify the causes of incorrect answers and provide learners with appropriate feedback and learning resources.

[0592] "Answer information" refers to data that describes the content of the answers that users have entered for the exam questions.

[0593] An "incorrect answer" refers to a user's answer that does not match the correct answer data when compared.

[0594] A "generative AI model" is an artificial intelligence model used to analyze data and identify the causes of incorrect answers.

[0595] "Analysis results" refer to data obtained after error analysis using a generative AI model, indicating the causes and identified problems.

[0596] "Information resources" refer to a collection of knowledge-enhancing tools, such as explanatory materials and supplementary learning materials, that are collected as needed.

[0597] "Feedback" refers to guidance information, including analysis results and additional information, provided to the user.

[0598] "Learning history" refers to the history of learning activities and answers that a user has performed in the past.

[0599] An "external database" refers to a system or location that stores information that exists on the internet or within an organization.

[0600] This learning support system utilizes three components—a server, a terminal, and a user—to improve learning efficiency. Specifically, the server receives answer information submitted by the user and compares it with its internally maintained database of correct answers. When an incorrect answer is identified, the server uses a generative AI model to analyze the cause of the error. This generative AI model utilizes artificial intelligence technology to accurately identify the cause of the error through pattern recognition of the data. After the analysis is complete, the server collects relevant information resources from an external database.

[0601] Next, the terminal presents the user with the analysis results and information resources sent from the server. This display is designed with user-friendly UI / UX to ensure easy comprehension, and the information is provided in various formats, including text, diagrams, and videos. This allows the user to understand the specific reasons for incorrect answers and to refer to supplementary materials for further learning.

[0602] As a concrete example, consider a case where a user answers a network-related question incorrectly on an information technology certification exam. In this case, the server analyzes the incorrect answer as "insufficient knowledge of the OSI reference model" and collects relevant detailed explanations and video links from the internet, sending them to the user's terminal. As a result, the user can deepen their understanding of this area and achieve better results on the next exam.

[0603] An example of a prompt message might be, "Generate materials and test questions to help students who want to learn the fundamentals of information technology deepen their understanding of the OSI model." Upon receiving such a prompt message, the system provides optimal learning support.

[0604] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0605] Step 1:

[0606] The user enters their answers to the test questions into a terminal and sends them to the server. The entered data includes the question ID and the answer. The terminal packages this answer information into packets and forwards them to the server. The server decodes the received packets and stores the answer information in its internal database.

[0607] Step 2:

[0608] The server compares the stored answer information with the correct answer database to identify incorrect answers. In the comparison process, the question ID is used as a key to compare the correct answer with the user's answer; if they do not match, the answer is flagged as incorrect. The incorrect answer data includes the question ID and the content of the incorrect answer. This comparison result is then entered into the next processing step.

[0609] Step 3:

[0610] The server passes the incorrect answers as input to the AI ​​model that generates them, and the AI ​​model begins its root cause analysis. The AI ​​model uses prompts to analyze patterns in the incorrect answers and identifies the causes of the errors. The output generated here is detailed attribute information indicating the cause of the incorrect answers. For example, "misunderstanding of concepts" or "lack of terminology" may be identified.

[0611] Step 4:

[0612] Based on the outputted reasons for incorrect answers, the server collects relevant information resources from external databases and the internet. This collection process uses keywords to search for appropriate materials and video links. The collected output data is diverse, including explanatory text, related links, and visual materials.

[0613] Step 5:

[0614] The terminal presents the user with analysis results and information resources received from the server. The terminal's UI is designed to display the information in a user-friendly format. The user can review this display and, if necessary, access supplementary materials to deepen their understanding. This output includes points for improving the user's learning process.

[0615] Step 6:

[0616] Based on the information provided through the device, users understand the detailed reasons for incorrect answers and adjust their learning accordingly. When users provide feedback, that data is returned to the server and saved for future system improvements and as part of the user's learning history. The feedback information, as output, enriches the next cycle and plays a role in improving learning outcomes.

[0617] (Application Example 1)

[0618] 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".

[0619] In recent years, users have sometimes made incorrect transaction behaviors in electronic payment settings, creating a need for means to identify the causes and provide corrective measures. Current systems lack sufficient feedback based on users' past behavioral history, making it difficult to prevent the recurrence of incorrect behavior.

[0620] 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.

[0621] In this invention, the server includes means for receiving answer data and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for analyzing the user's behavior history and identifying the cause of erroneous transaction behavior. This makes it possible to identify the cause when a user engages in erroneous transaction behavior and provide appropriate feedback.

[0622] "Answer data" refers to the answers provided by users, and is the basis for identifying incorrect answers.

[0623] An "incorrect answer" is a response that does not match the correct answer data and is therefore identified as an error.

[0624] "Cause analysis" is the process of analyzing the background and reasons for incorrect answers using generative AI.

[0625] "Response information" refers to supplementary materials and advice collected based on identified causes, which contribute to improving erroneous trading behavior.

[0626] "User activity history" refers to records of transactions and activities that users have performed in the past, and is data used to analyze the causes of incorrect answers.

[0627] "Feedback" refers to information provided to users regarding analysis results and improvement measures, intended to encourage them to reconsider their actions.

[0628] The system that realizes this invention mainly consists of three elements: a server, a terminal, and a user. The server receives answer data transmitted from the user and compares it with correct answer data stored in a database to identify incorrect answers. In this process, a generative AI model is used to analyze the incorrect answers and identify the causes related to the incorrect answers. Based on the identified causes, relevant corresponding information is collected from the database and external information sources.

[0629] The terminal displays analysis results and related information sent from the server in a way that is easy for the user to understand. Specifically, it provides intuitive feedback to the user using a user-friendly interface. It also includes a function to provide related explanatory materials and supplementary materials to further promote understanding.

[0630] Through this system, users can receive feedback on their incorrect transaction behavior. For example, if they have made purchases that exceeded their budget in the past, the system may analyze the cause as "insufficient planning" and send a prompt advising them to use a budget management tool. This prompt might say something like, "Your current spending exceeds your budget. Use a budget management tool to plan for future purchases."

[0631] This system utilizes Google Cloud's AI platform to run generative AI models, and programming is implemented using Python. Furthermore, frameworks such as Django are used for the user interface design. The goal of this configuration is to help users correct their incorrect behaviors and make appropriate payment decisions.

[0632] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0633] Step 1:

[0634] The server receives answer data from users. It identifies incorrect answers by comparing the received data with a database. In this process, it compares the input answer data with the correct answer data and generates a list of incorrect answers as output.

[0635] Step 2:

[0636] The server uses a generative AI model to analyze the identified incorrect answers. The AI ​​is fed the specific content of the incorrect answers as input, and through data processing, it identifies the cause of the error and generates an analysis of the cause as output. Specific examples, such as calculation errors or lack of knowledge, are also presented.

[0637] Step 3:

[0638] The server collects relevant correspondence information from a database or external sources based on the analysis results. This process searches the internet for relevant information regarding the causes of incorrect answers and organizes the collected information as output.

[0639] Step 4:

[0640] The terminal displays analysis results and corresponding information sent from the server to the user. The input is the analysis data received from the server, which is displayed visually through the user interface. Specifically, links to additional learning materials and explanatory videos are provided as needed.

[0641] Step 5:

[0642] Based on the information displayed on the terminal, users can understand the cause of their incorrect answers and identify areas for improvement in their future payment behavior. The output may include specific points for improvement in their next transaction. This allows users to review their actions and prepare themselves for making appropriate payments.

[0643] Step 6:

[0644] The server stores analysis results and feedback provided, which are then used to analyze and suggest future user behavior. The database records past incorrect answers and feedback, enabling the system to produce more accurate output for new inputs.

[0645] 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.

[0646] This invention is a learning support system that utilizes an emotion engine, achieving efficient and effective learning through error analysis by generating AI and recognition of the user's emotions. The system mainly consists of a server, terminals, and users.

[0647] The server identifies incorrect answers based on the answer data received from the user and analyzes the cause using a generation AI. Furthermore, it uses an emotion engine to grasp the user's emotional state in real time and analyzes the learning characteristics of each individual user by comparing it with the accumulated learning history.

[0648] The terminal not only presents the user with analysis results from the server and collected related materials, but also provides learning suggestions and environmental adjustments based on the user's emotional state detected by the emotion engine. For example, if the user is experiencing high stress levels, it can suggest taking a break.

[0649] This system allows users to not only clearly understand the causes of their incorrect answers, but also to adjust their learning strategy and pace according to their emotional state. For example, if a user frequently makes incorrect answers about networks during a mock IT certification exam, the system, upon detecting feelings of "anxiety," will recommend setting up a relaxing learning environment and provide time to watch relevant explanatory videos to help deepen their understanding.

[0650] This enables a system that provides effective learning support through collaboration between the server, terminal, and user, maximizing the user's learning effectiveness.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] Users take a practice test on their device, input their answers, and send them to the server.

[0654] Step 2:

[0655] The server compares the received answer data with the model answer to identify incorrect answers.

[0656] Step 3:

[0657] The server uses a generation AI to analyze the cause of the identified incorrect answers. The analysis includes factors such as lack of knowledge, misunderstanding of the problem, and calculation errors.

[0658] Step 4:

[0659] Based on the analysis results, the server automatically collects relevant explanatory materials and supplementary information from databases and the internet.

[0660] Step 5:

[0661] The emotion engine acquires emotional data from the user's device and analyzes the user's emotional state in real time. The analysis utilizes the user's facial expressions, voice tone, input speed, and other factors.

[0662] Step 6:

[0663] The terminal displays analysis results and collected data from the server and presents the user with optimal learning suggestions based on the results of the emotion engine. For example, if a stressful state is detected, it will suggest relaxation techniques.

[0664] Step 7:

[0665] Based on the displayed suggestions, users adjust their learning pace and, if necessary, engage in activities to improve their emotional state.

[0666] Step 8:

[0667] The server stores the analysis results and changes in the user's emotional state in a database, which will be used as data to support future learning.

[0668] (Example 2)

[0669] 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".

[0670] Modern learning support systems face challenges in accurately identifying the causes of user errors and suggesting appropriate learning strategies. Furthermore, a lack of means to adjust the learning environment to optimize performance based on the user's emotional state prevents the learning effect from being maximized. This can lead to decreased user motivation and difficulty in sustained learning.

[0671] 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.

[0672] In this invention, the server includes means for acquiring answer data and identifying incorrect answers, means for analyzing the causes of incorrect answers and aggregating related information, and means for detecting the user's emotional state in real time and proposing adjustments to the learning environment based on that information. This allows the user to clearly understand the causes of their errors and implement effective learning strategies that match their emotional state.

[0673] "Answer data" refers to information about the questions that users have answered and the content of those answers.

[0674] "Means for identifying incorrect answers" refers to methods or devices that analyze user response data and identify incorrect answers by comparing them with correct answers.

[0675] "Means for analyzing causes and aggregating related information" refers to methods and techniques for identifying the causes of incorrect answers and for comprehensively collecting and organizing knowledge and information related to those causes.

[0676] "Means of providing information to the user" refers to methods or devices for presenting analysis results and aggregated information to the user visually or audibly.

[0677] "Means of real-time detection" refers to methods and technologies for monitoring and detecting a user's emotional state in real time.

[0678] "Means of suggesting adjustments to the learning environment" refers to methods and technologies that suggest adjusting the environment and methods to improve learning efficiency based on the detected emotional state of the user.

[0679] A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and perform specific tasks.

[0680] A "prompt statement" refers to a sentence that serves as a command or question input to a generative AI model, and is used to guide the model's output.

[0681] This invention is a system for supporting user learning, consisting of a server, a terminal, and user participation. The server receives answer data and processes it to identify incorrect answers. This involves database and statistical analysis techniques, and the specific software used is a general database management system and data analysis tools. The server also uses a generative AI model to analyze the causes of incorrect answers and aggregate relevant information. In this process, a generative AI model utilizing natural language processing technology is used, and the AI ​​model is envisioned as a generalized "natural language generation engine."

[0682] The server utilizes sentiment analysis technology to detect the user's real-time emotional state. This sentiment analysis includes technologies such as voice analysis and facial recognition, and is implemented via an API-based general-purpose sentiment analysis engine. Based on this information, it is possible to provide more personalized learning suggestions.

[0683] The terminal presents the analysis results from the server to the user, providing information in a format that is easy for the user to understand. It also has a function to make learning suggestions tailored to the emotional environment and adjust the environment to enhance learning effectiveness. For example, if the terminal detects that the user is feeling stressed, it will display a message such as, "If you are losing focus, take a short break to refresh yourself."

[0684] By using the system, users can comprehensively understand their learning progress and adjust their learning strategy and pace as needed. For example, a user can input a prompt into the system such as, "Please recommend video materials to help me understand network-related questions that I got wrong frequently in recent practice tests. I'm feeling nervous right now," and receive appropriate information to proceed with their studies.

[0685] In this way, the server, terminal, and user work together as a unified team to achieve efficient and effective learning support.

[0686] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0687] Step 1:

[0688] The server receives answer data sent from the user via the terminal. It receives the problem identification information and the user's answer as input and stores this in the database. Next, it compares the incorrect answers with the correct answer data to identify them. Here, an algorithm is used to calculate the accuracy rate and output the locations of the user's incorrect answers. Specifically, the server executes database queries and analyzes the obtained data.

[0689] Step 2:

[0690] The server uses a generative AI model to analyze the causes of incorrect answers. The input consists of identified incorrect answer data and information about the problems associated with those incorrect answers. The generative AI model uses natural language processing to analyze the knowledge errors and misunderstandings underlying the incorrect answers. This process outputs the causes of the incorrect answers as analysis results. Specifically, the server creates prompts for the generative AI model and records the model's responses as analysis results.

[0691] Step 3:

[0692] The server activates an emotion engine to detect the user's emotional state in real time. Inputs include user voice data and webcam images. Based on this data, the server analyzes the emotional state and outputs emotional evaluations such as stress levels and concentration levels. Specifically, the server uses voice analysis APIs and facial recognition software to analyze the data and estimate the emotional state.

[0693] Step 4:

[0694] The terminal provides the user with analysis results sent from the server. Input data includes the causes of incorrect answers, related information, and emotional state assessments. Based on this, the terminal visually displays information to the user and outputs suggestions for learning strategies and environment adjustments. Specifically, the terminal displays information in graph and text formats and uses an interactive user interface as needed.

[0695] Step 5:

[0696] Users adjust their learning methods based on the information displayed on their device. They receive suggested information from the server as input and revise their learning plan. Specifically, users can refer to recommended learning materials and follow the provided break advice. As a result, improved learning efficiency and deeper understanding can be expected.

[0697] (Application Example 2)

[0698] 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".

[0699] In today's learning environment, there is a need for systems that not only identify incorrect answers but also analyze their causes and provide learning suggestions that take into account the user's emotional state, enabling learners to learn effectively while reducing stress. However, conventional learning support systems have been unable to provide real-time feedback or adjust the learning environment while considering the user's emotional state.

[0700] 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.

[0701] In this invention, the server includes means for receiving answer information and identifying incorrect answers, means for analyzing the cause of the incorrect answers and collecting corresponding information, and means for understanding the user's emotional state using an emotion engine and adjusting the learning environment. This enables learning suggestions and environment adjustments based on the user's emotions.

[0702] "Answer information" refers to the answer data submitted by users to learning problems.

[0703] "Incorrect answer" refers to answer information that has been identified as not being the correct answer.

[0704] "Analysis results" refers to the results of the analysis of the causes of incorrect answers by the generating AI.

[0705] An "emotion engine" refers to software that identifies and evaluates a user's emotional state in real time.

[0706] "Adjusting the learning environment" refers to making suggestions or changes to the learning process based on the user's emotional state and learning history.

[0707] A "communication network" refers to a network that enables the exchange of electronic information, such as the Internet.

[0708] The system for implementing this invention mainly consists of a server, a terminal, and a user. The server first receives answer information. At this time, it performs data analysis processing to identify incorrect answers using a generative AI model. As a result, the cause of the incorrect answers is clearly analyzed.

[0709] The server also uses an emotion engine to understand the user's emotional state in real time. This allows it to assess the user's current stress level and agitation level, and adjust the learning environment accordingly.

[0710] The device receives analysis results from the server and presents them to the user. The user can use this information to clearly understand their own error patterns and learning challenges. Furthermore, the device can consider the user's emotional state, detected by the emotion engine, and propose an appropriate learning strategy.

[0711] For example, if a user is solving a math problem and makes frequent mistakes, the server's emotion engine will detect feelings of frustration. In such situations, the device may suggest a break to encourage relaxation or display a link to an explanatory video to help with understanding.

[0712] The following are examples of prompts for a generative AI model.

[0713] "How would you support a user who is struggling with an elementary math problem and can't solve it?"

[0714] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0715] Step 1:

[0716] The server receives answer information submitted by the user. This answer information is the answer data to the question that the user answered. From the answer information received as input, the server performs data processing by comparing it with the correct answer in order to identify incorrect answers, and obtains an output that determines whether the answer is correct or incorrect.

[0717] Step 2:

[0718] The server analyzes the causes of incorrect answers identified using a generative AI model. This process analyzes patterns and trends in incorrect answers and outputs the reasons for the mistakes. The generative AI analyzes the incorrect answer information as input and generates analysis results that can explain the causes in natural language.

[0719] Step 3:

[0720] The server uses an emotion engine to analyze the user's emotional state in real time. It uses the user's facial expressions and behavioral data as input to identify emotional states such as stress and anxiety. The output is the user's current emotional state. This data is stored along with the analysis results.

[0721] Step 4:

[0722] The terminal presents the user with analysis results and emotional state data received from the server. This process receives analysis results and emotional state data as input and notifies the user visually or audibly. The output is to display the information in a format easily understood by the user.

[0723] Step 5:

[0724] The device suggests adjustments to the learning environment and methods based on the user's emotional state. It considers emotional data and past learning history as input, suggesting things like breaks or activities to relax. The output is effective learning suggestions for the user.

[0725] Step 6:

[0726] The user accepts suggestions from the device and adjusts the learning environment as needed. This allows the user to learn at their own pace and in a way that suits their emotional state. The device provides feedback as input, and the learning environment and strategy are adjusted as output.

[0727] 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.

[0728] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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."

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] The following is further disclosed regarding the embodiments described above.

[0749] (Claim 1)

[0750] A means of receiving answer data and identifying incorrect answers,

[0751] A means to analyze the cause of incorrect answers and collect corresponding information,

[0752] A means of presenting analysis results and collected information to the user,

[0753] A means of accumulating analysis results and making suggestions for future learning,

[0754] A system that includes this.

[0755] (Claim 2)

[0756] The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history.

[0757] (Claim 3)

[0758] The system according to claim 1, which automatically collects explanatory and supplementary materials from the internet.

[0759] "Example 1"

[0760] (Claim 1)

[0761] A means of receiving answer information and identifying incorrect answers,

[0762] A means of analyzing incorrect answers using a generation AI model to identify the cause of the incorrect answers,

[0763] Based on the analysis results, means for collecting relevant information resources,

[0764] A means of presenting analysis results and collected information to the user,

[0765] A means of accumulating user feedback and making suggestions for improving learning,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history and problem-solving tendencies.

[0769] (Claim 3)

[0770] The system according to claim 1, which automatically collects explanatory and supplementary materials from an external database.

[0771] "Application Example 1"

[0772] (Claim 1)

[0773] A means of receiving answer data and identifying incorrect answers,

[0774] A means to analyze the cause of incorrect answers and collect corresponding information,

[0775] A means of analyzing the user's behavioral history and identifying the causes of erroneous transaction behavior,

[0776] A means of presenting analysis results and collected information to the user,

[0777] A means of accumulating analysis results and making suggestions for future payment behavior,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history.

[0781] (Claim 3)

[0782] The system according to claim 1, which automatically collects explanatory and supplementary materials from information sources.

[0783] "Example 2 of combining an emotion engine"

[0784] (Claim 1)

[0785] A means of obtaining answer data and identifying incorrect answers,

[0786] A means to analyze the causes of incorrect answers and gather related information,

[0787] Means for providing users with analysis results and collected information,

[0788] A means of accumulating analysis results and making suggestions for future learning,

[0789] A means to detect the user's emotional state in real time and propose adjustments to the learning environment based on that information,

[0790] A method of using generative AI models to analyze the causes of incorrect answers,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history and analyzes the user's learning characteristics.

[0794] (Claim 3)

[0795] The system according to claim 1, which automatically collects explanatory and supplementary materials from information sources and presents them to the user.

[0796] "Application example 2 when combining with an emotional engine"

[0797] (Claim 1)

[0798] A means of receiving answer information and identifying incorrect answers,

[0799] A means to analyze the cause of incorrect answers and collect corresponding information,

[0800] A means of presenting analysis results and collected information to the user,

[0801] A means of accumulating analysis results and making suggestions for future learning,

[0802] A means of understanding the user's emotional state using an emotion engine and adjusting the learning environment accordingly,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history and taking into account their emotional state.

[0806] (Claim 3)

[0807] The system according to claim 1, which automatically collects explanatory and supplementary materials from a communication network and makes learning suggestions based on the user's emotional state. [Explanation of Symbols]

[0808] 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

1. A means of receiving answer data and identifying incorrect answers, A means to analyze the cause of incorrect answers and collect corresponding information, A means of presenting analysis results and collected information to the user, A means of accumulating analysis results and making suggestions for future learning, A system that includes this.

2. The system according to claim 1, which identifies the cause of an incorrect answer by referring to the user's past learning history.

3. The system according to claim 1, which automatically collects explanatory and supplementary materials from the internet.

Images